Article snapshot taken from Wikipedia with creative commons attribution-sharealike license.
Give it a read and then ask your questions in the chat.
We can research this topic together.
<noinclude>{{Villagepumppages|Policy discussion|The '''policy''' section of the village pump is used to discuss existing and proposed policies and guidelines.<br>If you want to propose something new, use the '']'' section.<br>
<noinclude>{{Short description|Page for discussing policies and guidelines}}{{Redirect|WP:VPP|proposals|Misplaced Pages:Village pump (proposals)}}{{village pump page header|Policy|alpha=yes|The '''policy''' section of the ] is intended for discussions about already-proposed ], as well as changes to existing ones. Discussions often begin on other pages and are subsequently moved or referenced here to ensure greater visibility and broader participation.
Please see ''']''' for a list of frequent proposals and the responses to them.
*If you wish to propose something ''new'' that is ''not'' a policy or guideline, use ]. Alternatively, for drafting with a more focused group, consider starting the discussion on the talk page of a relevant WikiProject, the Manual of Style, or another relevant project page.
|]}}
* For questions about how to apply existing policies or guidelines, refer to one of the many ].
* If you want to inquire about what the policy is on a specific topic, visit the ] or the ].
* This is '''not the place to resolve disputes''' regarding the implementation of policies. For such cases, consult ].
* For proposals for new or amended speedy deletion criteria, use ].
Please see ''']''' for a list of frequently rejected or ignored proposals. Discussions are automatically archived after two weeks of inactivity.
{| class="messagebox" style="background: AntiqueWhite;"
|-
|This talk page is '''automatically archived''' by ]. Any sections older than '''5''' days are automatically archived to ''']'''. Sections without timestamps are not archived.
|-
|}
Discussions older than 5 days (date of last made comment) are moved ]. These discussions will be kept archived for 9 more days. During this period the discussion can be moved to a relevant talk page if appropriate. After 9 days the discussion can only be found through the page history.
<br clear="all" />
<!-- ] 01:01, 6 January 2025 (UTC) -->{{User:ClueBot III/DoNotArchiveUntil|1736125272}}
]
Should admins or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots? 00:12, 2 December 2024 (UTC)
]
]
]
]
]
]</noinclude>
]
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, and other such tools are very good at detecting this.
<!-- BEGIN WERDNABOT ARCHIVAL CODE --><!-- This page is automatically archived by Werdnabot-->{{User:Werdnabot/Archiver/Linkhere}} <!--This is an empty template, but transcluding it counts as a link, meaning Werdnabot is directed to this page - DO NOT SUBST IT --><!--Werdnabot-Archive Age-5 DoUnreplied-Yes Target-Misplaced Pages:Village pump (policy)/Archive--><!--END WERDNABOT ARCHIVAL CODE-->
I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. ] ] 00:12, 2 December 2024 (UTC)
:Should not be deleted or ignored but needs to be clearly identified. ] (]) 16:23, 5 January 2025 (UTC)
== Discussion of articles with "allegations"in their name ==
===opening comments===
Definition of "allegation":
*Seems reasonable, as long as the GPTZero (or any tool) score is taken with a grain of salt. GPTZero can be as wrong as AI can be. ] (]) 00:32, 2 December 2024 (UTC)
*Only if the false positive and false negative rate of the tool you are using to detect LLM content is very close to zero. LLM detectors tend to be very unreliable on, among other things, text written by non-native speakers. Unless the tool is near perfect then it's just dismissing arguments based on who wrote them rather than their content, which is not what we do or should be doing around here. ] (]) 00:55, 2 December 2024 (UTC)
*:In the cases I have seen thusfar it's been pretty obvious, the tools have just confirmed it. ] ] 04:08, 2 December 2024 (UTC)
*:The more I read the comments from other editors on this, the more I'm a convinced that implementing either this policy or something like it will bring very significant downsides on multiple fronts that significantly outweigh the small benefits this would (unreliably) bring, benefits that would be achieved by simply reminding closers to disregard comments that are unintelligible, meaningless and/or irrelevant regardless of whether they are LLM-generated or not. For the sake of the project I must withdraw my previous very qualified support and instead '''very strongly oppose'''. ] (]) 02:45, 3 December 2024 (UTC)
*I think it should be an expressly legitimate factor in considering whether to discount or ignore comments either if it's clear enough by the text or if the user clearly has a history of using LLMs. We wouldn't treat a comment an editor didn't actually write as an honest articulation of their views in lieu of site policy in any other situation. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:59, 2 December 2024 (UTC)
* I would have already expected admins to exercise discretion in this regard, as text written by an LLM is not text written by a person. We cannot guarantee it is what the person actually means, especially as it is a tool often used by those with less English proficiency, which means perhaps they cannot evaluate the text themselves. However, I do not think we can make policy about a specific LLM or tool. The LLM space is moving fast, en.wiki policies do not. Removal seems tricky, I would prefer admins exercise discretion instead, as they do with potentially canvassed or socked !votes. ] (]) 01:06, 2 December 2024 (UTC)
*:As the discussion has moved forward below, I feel I can shift to a more explicit '''support''' in terms of providing guidance to closers and those otherwise evaluating consensus. ] (]) 17:33, 2 January 2025 (UTC)
*'''Support''' discounting or collapsing AI-generated comments, under ''slightly looser'' conditions than those for human comments. Not every apparently-AI-generated comment is useless ] nonsense{{snd}}beyond false positives, it's also possible for someone to use an AI to help them word a constructive comment, and make sure that it matches their intentions before they publish it. But in my experience, the majority of AI-generated comments are somewhere between "pointless" and "disruptive". Admins should already discount ''clearly'' insubstantial !votes, and collapse ''clearly'' unconstructive lengthy comments; I think we should recognize that blatant chatbot responses are more likely to fall into those categories. ] (]) 02:11, 2 December 2024 (UTC)
*'''Strongly Support''' - I think some level of human judgement on the merits of the argument are necessary, especially as GPTZero may still have a high FPR. Still, if the discussion is BLUDGEONy, or if it quacks like an AI-duck, looks like an AI-duck, etc, we should consider striking out such content.{{pb
}}- sidenote, I'd also be in favor of sanctions against users who overuse AI to write out their arguments/articles/etc. and waste folks time on here.. ] (]) 02:20, 2 December 2024 (UTC)
*On a wording note, I think any guidance should avoid referring to any specific technology. I suggest saying "... to have been generated by a program". ] (]) 02:54, 2 December 2024 (UTC)
*:"generated by a program" is too broad, as that would include things like speech-to-text. ] (]) 03:08, 2 December 2024 (UTC)
*:Besides what Thryduulf said, I think we should engage with editors who use translators. ] (]) 03:45, 2 December 2024 (UTC)
*::A translation program, whether it is between languages or from speech, is not generating a comment, but converting it from one format to another. A full policy statement can be more explicit in defining "generation". The point is that the underlying tech doesn't matter; it's that the comment didn't feature original thought from a human. ] (]) 03:57, 2 December 2024 (UTC)
*:::Taking Google Translate as an example, most of the basic stuff uses "AI" in the sense of machine learning () but they nowadays, even for the basic free product. ] (]) 08:39, 2 December 2024 (UTC)
*'''Support'''. We already use discretion in collapsing etc. comments by SPAs and suspected socks, it makes sense to use the same discretion for comments suspected of being generated by a non-human. ] (]) 03:07, 2 December 2024 (UTC)
*'''Support''' - Someone posting "here's what ChatGPT has to say on the subject" can waste a lot of other editors' time if they feel obligated to explain why ChatGPT is wrong again. I'm not sure how to detect AI-written text but we should take a stance that it isn't sanctioned. ] (] <nowiki>|</nowiki> ]) 04:37, 2 December 2024 (UTC)
*'''Strong Support''' - I've never supported using generative AI in civil discourse. Using AI to participate in these discussions is pure laziness, as it is substituting genuine engagement and critical thought with a robot prone to outputting complete garbage. In my opinion, if you are too lazy to engage in the discussion yourself, why should we engage with you? ] (]) 05:26, 2 December 2024 (UTC)
*'''Comment''' - I'm skeptical that a rule like this will be enforceable for much longer. ] (]) 05:39, 2 December 2024 (UTC)
*:Why? ] (]) 12:22, 2 December 2024 (UTC)
*::Because it's based on a potentially false premise that it will be possible to reliably distinguish between text generated by human biological neural networks and text generated by non-biological neural networks by observing the text. It is already quite difficult in many cases, and the difficulty is increasing very rapidly. I have your basic primate brain. The AI companies building foundation models have billions of dollars, tens of thousands, soon to be hundreds of thousands of GPUs, a financial incentive to crack this problem and scaling laws on their side. So, I have very low credence in the notion that I will be able to tell whether content is generated by a person or a person+LLM or an AI agent very soon. On the plus side, it will probably still be easy to spot people making non-policy based arguments regardless of how they do it. ] (]) 13:52, 2 December 2024 (UTC)
*::...and now that the systems are autonomously injecting their output back into model via chain-of-thought prompting, or a kind of inner monologue if you like, to respond to questions, they are becoming a little bit more like us. ] (]) 14:14, 2 December 2024 (UTC)
*:::A ] is intrinsically nothing like a human. It's a bunch of algebra that can compute what a decently sensible person could write in a given situation based on its training data, but it is utterly incapable of anything that could be considered thought or reasoning. This is why LLMs tend to fail spectacularly when asked to do math or write non-trivial code. ] (]) 17:20, 2 December 2024 (UTC)
*::::We shall see. You might want to update yourself on their ability to do math and write non-trivial code. Things are changing very quickly. Either way, it is not currently possible to say much about what LLMs are actually doing because mechanistic interpretability is in its infancy. ] (]) 03:44, 3 December 2024 (UTC)
*::::You might be interested in Anthropic's '' and Chris Olah's work in general. ] (]) 04:02, 3 December 2024 (UTC)
*'''Support''' and I would add "or similar technologies" to "AI/LLM/Chatbots". As for Sean.hoyland's comment, we will cross that bridge when we get to it. ] (]) 05:51, 2 December 2024 (UTC)
*:...assuming we can see the bridge and haven't already crossed it. ] (]) 06:24, 2 December 2024 (UTC)
*'''Support''' - All editors should convey their thoughts in their own words. AI generated responses and comments are disruptive because they are pointless and not meaningful. - ] (]) 06:04, 2 December 2024 (UTC)
*'''Support''', I already more or less do this. An LLM generated comment may or may not actually reflect the actual thoughts of the editor who posted it, so it's essentially worthless toward a determination of consensus. Since I wrote this comment myself, you know that it reflects ''my'' thoughts, not those of a bot that I may or may not have reviewed prior to copying and pasting. ] <small><sup>]</sup></small> 06:59, 2 December 2024 (UTC)
*'''Strong oppose'''. Let me say first that I do not like ChatGPT. I think it has been a net negative for the world, and it is by nature a net negative for the physical environment. It is absolutely a net negative for the encyclopedia if LLM-generated text is used in articles in any capacity. However, hallucinations are less of an issue on talk pages because they're discussions. If ChatGPT spits out a citation of a false policy, then obviously that comment is useless. If ChatGPT spits out some boilerplate "Thanks for reviewing the article, I will review your suggestions and take them into account" talk page reply, who gives a fuck where it came from? (besides the guys in Texas getting their eardrums blown out because they live by the data center){{pb
}}The main reason I oppose, though, is because banning LLM-generated comments is difficult to enforce bordering on unenforceable. Most studies show that humans are bad at distinguishing AI-generated text from text generated without AI. Tools like GPTZero claims a 99% accuracy rate, but that seems dubious based on reporting on the matter. The news outlet Futurism (which generally has an anti-AI slant) has failed many times to replicate that statistic, and anecdotal accounts by teachers, etc. are rampant. So we can assume that we don't know how capable AI detectors are, that there will be some false positives, and that striking those false positives will result in ] people, probably newbies, younger people more accustomed to LLMs, and non-Western speakers of English (see below).{{pb
}}There are also technological issues as play. It'd be easy if there was a clean line between "totally AI-generated text" and "totally human-generated text," but that line is smudged and well on its way to erased. Every tech company is shoving AI text wrangling into their products. This includes autocomplete, translation, editing apps, etc. Should we strike any comment a person used Grammarly or Google Translate for? Because those absolutely use AI now.{{pb
}}And there are ''also'', as mentioned above, cultural issues. The people using Grammarly, machine translation, or other such services are likely to not have English as their first language. And a lot of the supposed "tells" of AI-generated content originate in the formal English of other countries -- for instance, the whole thing where "delve" was supposedly a tell for AI-written content until people pointed out the fact that lots of Nigerian workers trained the LLM and "delve" is common Nigerian formal English.{{pb
}}I didn't use ChatGPT to generate any of this comment. But I am also pretty confident that if I did, I could have slipped it in and nobody would have noticed until this sentence. ] (]) 08:31, 2 December 2024 (UTC)
*:Just for grins, I ran your comment through GPTzero, and it comes up with a 99% probability that it was human-written (and it never struck me as looking like AI either, and I can often tell.) So, maybe it's more possible to distinguish than you think? ] <small><sup>]</sup></small> 20:11, 2 December 2024 (UTC)
*::Yeah, Gnoming's writing style is far more direct and active than GPT's. ] (]) 23:02, 2 December 2024 (UTC)
*:::There weren't
*:::*'''Multiple'''
*:::*:LLMs tend to use more than one subheading to reiterate points
*:::*'''Subheadings'''
*:::*:Because they write like a middle schooler that just learned how to make an essay outline before writing.
*:::In conclusion, they also tend to have a conclusion paragraph for the same reason they use subheadings. ] (]) 13:56, 3 December 2024 (UTC)
*'''Support''' - Ai-generated comments are ] - An editor who has an argument should not use ChatGPT to present it in an unnecessarily verbose manner, and an editor who doesn't have one should not participate in discussion. ] (]) 13:14, 2 December 2024 (UTC)
*'''Yes''' but why do we need this common sense RFC/policy/whatever? Just ban these people. If they even exist.  <span style="font-variant:small-caps; whitespace:nowrap;">] {] · ] · ] · ]}</span> 07:14, 2 December 2024 (UTC)
*:They exist, and I found myself collapsing some long, obviously chatbot-generated posts in an AFD, and after I did so wondering if policy actually supported doing that. I couldn't find anything so here we are. ] ] 20:04, 2 December 2024 (UTC)
*{{anchor|ChaptGPT_agrees}}'''Yes, of course''', and I know that's the right answer because ChatGPT agrees with me.
::{{tq|Currently at the English Misplaced Pages, there's a discussion of the following proposal: "Should or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots?" I wonder if you have an opinion on that question.}}
:My friend the bot initially proposed a requirement that any AI-generated content be labeled as such by the person posting it. After some further discussion between us, I finally said:
::{{tq|You say that labeling AI-generated content, instead of outright discounting it, might be an appropriate middle ground. But if someone is unable to formulate their own thoughts and put them in writing, of what use is it to the discussion for this person to simply ask you to make something up, and then post your output to the Misplaced Pages discussion with the proviso that "ChatGPT, who/which doesn't actually know anything about anything, said this ..."? How is it different from saying, "My grandmother, who knows nothing about what we're talking about, said ..."?}}
:And it said:
::{{tq|That’s an incisive question, and it highlights the crux of the issue: the value of contributions to a discussion. Here’s why AI-generated comments might still differ (slightly) from your hypothetical grandmother’s input, but why their usefulness is often limited:}}
::*{{tq|'''Synthesis vs. Subject Expertise:''' While I (or any AI) lack personal understanding or expertise, I can aggregate and articulate relevant ideas from a vast dataset. This means I can sometimes present arguments, summarize perspectives, or surface considerations that a non-expert human might overlook. Your grandmother, unless she's an AI-trained polymath, wouldn’t be able to provide this breadth. However, this advantage evaporates if participants lack the ability to evaluate and critically engage with my output.}}
::*{{tq|'''The Problem of Proxy Voices:''' The act of outsourcing one’s contribution to AI undermines the deliberative process central to Misplaced Pages’s discussions. Participants are expected to bring their own informed perspectives, shaped by personal understanding of Misplaced Pages’s policies and content. A disclaimer like “ChatGPT said this” doesn’t change the fact that the human posting it has abdicated their role in the discussion.}}
::*{{tq|'''Accountability and Intent:''' In a collaborative setting like Misplaced Pages, contributions are ideally linked to a person who can clarify their intent, respond to questions, and engage dynamically. An AI cannot do this. Saying "ChatGPT said this" distances the poster from the content, making it unclear whether they endorse or even understand the comment.}}
::*{{tq|'''Potential for Misdirection:''' Allowing AI-generated contributions risks introducing noise into the discussion. AI can produce plausible-sounding arguments that may be tangential, misaligned, or even factually incorrect. Without the judgment of a well-informed poster, such contributions can derail or dilute meaningful discourse.}}
::{{tq|'''Conclusion:''' If someone cannot formulate their own argument or understanding, then their reliance on an AI—or anyone else—to contribute doesn’t meaningfully advance the discussion. Labeling AI-generated content is better than passing it off as human, but the real issue lies in whether such contributions enrich or degrade the collaborative process. In most cases, they would seem to belong more to the realm of rhetorical curiosities than substantive engagement.}}
{{collapse bottom}}
*<li style="list-style:none;">In keeping with the proposed guideline, I have of course collapsed the above AI-generated content. (Later: It's actually worth reading in the context of this discussioin, so I've unhidden it by default.) But I must confess it's a pretty good analysis, and worth reading. ]] 07:47, 2 December 2024 (UTC)</li>
*:This is absolute gold dust and the best contribution to this discussion so far. There is an enormous irony here, one that might not be immediately obvious. The proposal is that we should ignore or even strike these type of contributions, but personally it seems like the collapsed format has worked a charm here. I really don't think that AI has much to contribute to WP discussions generally, but with the right prompt, there is certainly something worth adding to the conversation in reality. ] (]) 20:23, 8 December 2024 (UTC)
*::The proposal also includes collapsing. ] (]) 20:26, 8 December 2024 (UTC)
*:::Thanks, I completely missed that. Trying to speed read is not my forte. ] (]) 20:32, 8 December 2024 (UTC)
:The "detector" website linked in the opening comment gives your chatbot's reply only an 81% chance of being AI-generated. ] (]) 23:36, 2 December 2024 (UTC)
::That's because, just by interacting with me, ChatGPT got smarter. Seriously ... you want it to say 99% every time? (And for the record, the idea of determining the "chance" that something is AI-generated is statistical nonsense.) ]] 03:07, 3 December 2024 (UTC)
:::What I really want is a 100% chance that it won't decide that what I've written is AI-generated. Past testing has demonstrated that at least some of the detectors are unreliable on this point. ] (]) 03:28, 4 December 2024 (UTC)
::::100% is, of course, an impossible goal. Certainly SPI doesn't achieve that, so why demand it here? ]] 22:31, 4 December 2024 (UTC)
:::::Even a miniscule chance of quashing a human writer's contributions is too high of a risk. ] (]) 06:09, 6 January 2025 (UTC)
*<del>'''Strong Oppose''' I support the concept of removal of AI-generated content in theory. However, we do not have the means to detect such AI-generated content. The proposed platform that we may use (GPTZero) is not reliable for this purpose. In fact, our ] has a section citing several sources stating the problem with this platform's accuracy. It is not helpful to have a policy that is impossible to enforce. ] <sup>] / ]</sup> 08:46, 2 December 2024 (UTC) </del>
*'''Strong Support''' To be honest, I am surprised that this isn't covered by an existing policy. I oppose the use of platforms like GPTZero, due to it's unreliability, but if it is obviously an ai-powered-duck (Like if it is saying shit like "as an AI language model...", take it down and sanction the editor who put it up there. ] <sup>] / ]</sup> 08:54, 2 December 2024 (UTC)
*'''Support''' at least for ]-level AI-generated comments. If someone uses a LLM to translate or improve their own writing, there should be more leeway, but something that is clearly a pure ChatGPT output should be discounted. ] (] · ]) 09:17, 2 December 2024 (UTC)
* I agree for cases in which it is uncontroversial that a comment is purely AI-generated. However, I don't think there are many cases where this is obvious. The claim that {{green|gptzero and other such tools are very good at detecting this}} is false. ] (]) 09:43, 2 December 2024 (UTC)
*'''Support''' Not clear how admins are deciding that something is LLM generated, , agree with the principle tho. ] (]) 10:02, 2 December 2024 (UTC)
* '''Moral support; neutral as written'''. Chatbot participation in consensus discussions is such an utterly pointless and disdainful abuse of process and community eyeballs that I don't feel like the verbiage presented goes far enough. {{Xt|Any editor may hat LLM-generated comments in consensus discussions}} is nearer my position. No waiting for the closer, no mere discounting, no reliance on the closer's personal skill at recognising LLM output, immediate feedback to the editor copypasting chatbot output that their behaviour is unwelcome and unacceptable. Some observations:{{pb}}I've seen editors accused of using LLMs to generate their comments probably about a dozen times, and in all but two cases – both at dramaboards – the chatbot prose was unmistakably, blindingly obvious. Editors already treat non-obvious cases as if written by a human, in alignment with the raft of {{tqq|only if we're sure}} caveats in every discussion about LLM use on the project.{{pb}}If people are using LLMs to punch up prose, correct grammar and spelling, or other superficial tasks, this is generally undetectable, unproblematic, and not the point here.{{pb}}Humans are superior to external services at detecting LLM output, and no evidence from those services should be required for anything.{{pb}}As a disclosure, evidence mounts that LLM usage in discussions elicits maximally unkind responses from me. It just feels so contemptuous, to assume that any of us care what a chatbot has to say about anything we're discussing, and that we're all too stupid to see through the misattribution because someone tacked on a sig and sometimes an introductory paragraph. And I say this as a stupid person. ] (]) 11:20, 2 December 2024 (UTC)
*:'''Looks like a rewrite is indicated''' to distinguish between {{xt|machine translation}} and {{!xt|LLM-generated comments}}, based on what I'm seeing in this thread. Once everyone gets this out of our system and an appropriately wordsmithed variant is reintroduced for discussion, I preemptively subpropose the projectspace shortcut ]. ] (]) 15:26, 8 December 2024 (UTC)
*'''Support''' per EEng ] ] 14:21, 2 December 2024 (UTC)
*I would be careful here, as there are tools that rely on LLM AI that help to improve the clarity of one's writing, and editors may opt to use those to parse their poor writing (perhaps due to ESL aspects) to something clear. I would agree content 100% generated by AI probably should be discounted particularly if from an IP or new editors (hints if socking or meat puppetry) but not all cases where AI has come into play should be discounted<span id="Masem:1733149152126:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:19, 2 December 2024 (UTC)</span>
*'''Support''', cheating should have no place or take its place in writing coherent comments on Misplaced Pages. Editors who opt to use it should practice writing until they rival Shakespeare, or at least his cousin Ned from across the river, and then come back to edit. ] (]) 14:29, 2 December 2024 (UTC)
*'''Support''' atleast for comments that are copied straight from the LLM . However, we should be more lenient if the content is rephrased by non-native English speakers due to grammar issues ] (]) 15:10, 2 December 2024 (UTC)
===section break 1===
al·le·ga·tion /ˌælɪˈgeɪʃən/ Pronunciation Key - Show Spelled Pronunciation *Pronunciation Key - Show IPA Pronunciation
* '''Support''' for LLM-'''generated''' content (until AI is actually intelligent enough to create an account and contribute on a human level, ]). However, beware of the fact that some LLM-'''assisted''' content should probably be allowed. An extreme example of this: if a non-native English speaker were to write a perfectly coherent reason in a foreign language, and have an LLM translate it to English, it should be perfectly acceptable. ] ] 16:47, 2 December 2024 (UTC)
–noun
*:For wiki content, maybe very soon. 'contribute of a human level' in a narrow domain. ] (]) 17:08, 2 December 2024 (UTC)
*1. the act of alleging; affirmation.
*::If Star Trek's Data were to create his own account and edit here, I doubt anyone would find it objectionable. ] ] 17:35, 2 December 2024 (UTC)
*2. an assertion made with little or no proof.
*:::I’m proposing a policy that any AI has to be capable of autonomous action without human prompting to create an account. ] (]) 21:38, 5 December 2024 (UTC)
*3. an assertion made by a party in a legal proceeding, which the party then undertakes to prove.
*:::<small>Data, being a fictional creation with rights owned by a corporation, will not have an account; he is inherently an IP editor. -- ] (]) 03:22, 20 December 2024 (UTC)</small>
*4. a statement offered as a plea, excuse, or justification.
*'''Strong support''' chatbots have no place in our encyclopedia project. ] (]) 17:14, 2 December 2024 (UTC)
*
*'''Oppose''' - I think the supporters must have a specific type of AI-generated content in mind, but this isn't a prohibition on one type; it's a prohibition on the use of generative AI in discussions (or rather, ensuring that anyone who relies on such a tool will have their opinion discounted). We allow people who aren't native English speakers to contribute here. We also allow people who are native English speakers but have difficulty with language (but not with thinking). LLMs are good at assisting both of these groups of people. Furthermore, as others pointed out, detection is not foolproof and will only get worse as time goes on, models proliferate, models adapt, and users of the tools adapt. This proposal is a blunt instrument. If someone is filling discussions with pointless chatbot fluff, or we get a brand new user who's clearly using a chatbot to feign understanding of wikipolicy, of ''course'' that's not ok. But ''that is a case by case behavioral issue''. I think the better move would be to clarify that "some forms of LLM use can be considered ] and may be met with restrictions or blocks" without making it a black-and-white issue. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 17:32, 2 December 2024 (UTC)
*:I agree the focus should not be on whether or not a particular kind of tech was used by an editor, but whether or not the comment was generated in a way (whether it's using a program or ghost writer) such that it fails to express actual thoughts by the editor. (Output from a speech-to-text program using an underlying large language model, for instance, isn't a problem.) Given that this is often hard to determine from a single comment (everyone is prone to post an occasional comment that others will consider to be off-topic and irrelevant), I think that patterns of behaviour should be examined. ] (]) 18:07, 2 December 2024 (UTC)
*::Here's what I see as two sides of a line. The first is, I think, something we can agree would be inappropriate. The second, to me at least, pushes up against the line but is not ultimately inappropriate. But they would both be prohibited if this passes. (a) "I don't want an article on X to be deleted on Misplaced Pages. Tell me what to say that will convince people not to delete it"; (b) "I know Misplaced Pages deletes articles based on how much coverage they've received in newspapers, magazines, etc. and I see several such articles, but I don't know how to articulate this using wikipedia jargon. Give me an argument based on links to wikipedia policy that use the following sources as proof ". Further into the "acceptable" range would be things like translations, grammar checks, writing a paragraph and having an LLM improve the writing without changing the ideas, using an LLM to organize ideas, etc. I think what we want to avoid are situations where the ''arguments and ideas themselves'' are produced by AI, but I don't see such a line drawn here and I don't think we could draw a line without more flexible language. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 18:47, 2 December 2024 (UTC)
*::Here we return to my distinction between AI-generated and AI-assisted. A decent speech-to-text program doesn't actually generate content. ] ] 18:47, 2 December 2024 (UTC)
*:::Yes, as I ], the underlying tech isn't important (and will change). Comments should reflect what the author is thinking. Tools (or people providing advice) that help authors express their personal thoughts have been in use for a long time. ] (]) 19:08, 2 December 2024 (UTC)
*::::Yeah the point here is passing off a machine's words as your own, and the fact that it is often fairly obvious when one is doing so. If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them. ] ] 20:10, 2 December 2024 (UTC)
*:::::This doesn't address what I wrote (though maybe it's not meant to). {{tq|If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them}} is just contradictory. Assistive technologies are those that can help people who aren't "competent" to express themselves to your satisfaction in plain English, sometimes helping with the formulation of a sentence based on the person's own ideas. There's a difference between having a tool that helps me to articulate ideas ''that are my own'' and a tool that ''comes up with the ideas''. That's the distinction we should be making. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 21:23, 2 December 2024 (UTC)
*:::::I agree with Rhododendrites that we shouldn't be forbidding users from seeking help to express their own thoughts. Getting help from someone more fluent in English, for example, is a good practice. Nowadays, some people use generative technology to help them prepare an outline of their thoughts, so they can use it as a starting point. I think the community should be accepting of those who are finding ways to write their own viewpoints more effectively and concisely, even if that means getting help from someone or a program. I agree that using generative technology to come up with the viewpoints isn't beneficial for discussion. ] (]) 22:58, 2 December 2024 (UTC)
*:Non-native English speakers and non-speakers to whom a discussion is important enough can already use machine translation from their original language and usually say something like "Sorry, I'm using machine translation". ] (]) 08:34, 4 December 2024 (UTC)
*'''Oppose''' Contributions to discussions are supposed to be evaluated on their merits per ]. If an AI-assisted contribution makes sense then it should be accepted as helpful. And the technical spectrum of assistance seems large and growing. For example, as I type this into the edit window, some part of the interface is spell-checking and highlighting words that it doesn't recognise. I'm not sure if that's coming from the browser or the edit software or what but it's quite helpful and I'm not sure how to turn it off. ]🐉(]) 18:17, 2 December 2024 (UTC)
*:But we're not talking about spell-checking. We're talking about comments clearly generated by LLMs, which are inherently unhelpful. ] (]) 18:29, 2 December 2024 (UTC)
*::Yeah, spellchecking is not the issue here. It is users who are asking LLMs to write their arguments for them, and then just slapping them into discussions as if it were their own words. ] ] 20:12, 2 December 2024 (UTC)
*:::Andrew's first two sentences also seem to imply that he views AI-generated arguments that makes sense as valid, and that we should consider what AI thinks about a topic. I'm not sure what to think about this, especially since AI can miss out on a lot of the context. ] (]) 23:04, 2 December 2024 (UTC)
*::::Written arguments are supposed to be considered on their merits as objects in their own right. Denigrating an argument by reference to its author is '']'' and that ranks low in the ] – "{{tq|attacks the characteristics or authority of the writer without addressing the substance of the argument}}". ]🐉(]) 23:36, 2 December 2024 (UTC)
*::::::An AI chatbot isn't an "author", and it's impossible to make an ''ad hominem'' attack on one, because a chotbot is not a ''homo''. ]] 17:45, 6 December 2024 (UTC)
*:::::::{{small|Well, not all of them, anyway. ], maybe?}} ] (]) 17:51, 6 December 2024 (UTC)
*:::::On the other hand, "exhausting the community's patience"/CompetenceIsRequired is a very valid rationale from stopping someone from partricipating. ] (]) 23:50, 2 December 2024 (UTC)
*:::The spell-checking was an immediate example but there's a spectrum of AI tools and assistance. The proposed plan is to use an AI tool to detect and ban AI contributions. That's ludicrous hypocrisy but suggests an even better idea – that we use AIs to close discussions so that we don't get the bias and super-voting. I see this on Amazon regularly now as it uses an AI to summarise the consensus of product reviews. For example,{{tqb|Customers say<br />Customers appreciate the gloves for their value, ease of use, and gardening purposes. They find the gloves comfortable and suitable for tasks like pruning or mowing. However, opinions differ on how well they fit.<br />AI-generated from the text of customer reviews}}Yes, AI assistants have good potential. My !vote stands. ]🐉(]) 23:23, 2 December 2024 (UTC)
*::::Let's not get into tangents here. ] (]) 23:51, 2 December 2024 (UTC)
*:::::It's better than going around in circles. ]] 03:07, 3 December 2024 (UTC)
*::::I asked Google's ] to "summarise the consensus of the following RFC discussion", giving it the 87 comments to date.
{{cot|width=80%|title=AI summary of the RfC to date}}
This Misplaced Pages Request for Comment (RfC) debates whether comments in discussions that are found to be generated by AI/LLM/Chatbots should be discounted, ignored, or removed.
Arguments for discounting/removing AI-generated comments:
(from )
* AI comments don't represent genuine human engagement or thought. They can be disruptive, waste time, and even fabricate information.
* AI can be used to manipulate discussions. Editors might use AI to generate arguments they don't actually believe in, or to flood discussions with low-quality comments.
* Relying on AI undermines the integrity of Misplaced Pages's consensus-based process. Discussions should be based on the genuine opinions of human editors.
Arguments against discounting/removing AI-generated comments:
Misplaced Pages's official guidelines regarding the use of the term:
* Difficulty of detection. AI detection tools are not always reliable, and it can be hard to distinguish between AI-generated text and human-written text, especially as AI technology improves.
* Potential for misuse. False positives could lead to legitimate comments being dismissed, potentially silencing non-native English speakers or those who use AI for legitimate assistive purposes (e.g., translation, grammar checks).
* Focus on content, not origin. Comments should be evaluated based on their merits, not on how they were generated. If an AI-generated comment is relevant and well-reasoned, it shouldn't be dismissed simply because of its origin.
* LLMs can be helpful tools. LLMs can help editors express their thoughts more clearly, especially for non-native speakers or those with language difficulties.
Current Status (as of Dec 3rd, 2024):
''Alleged (along with allegedly) and purported (along with purportedly) are different from the foregoing in that they are generally used by those who genuinely have no predisposition as to whether the statement being cited is true or not. Newspapers, for instance, almost universally refer to any indicted but unconvicted criminal as an alleged criminal. Therefore, there is no neutrality problem with using them. However, there may be a problem of ambiguity—they should only be used where the identity of the alleger is clear.''
* No clear consensus has emerged. There is significant support for discounting or removing AI-generated comments, but also strong opposition.
* Concerns about enforceability and potential harm. Many editors are worried about the practical challenges of implementing and enforcing such a rule, as well as the potential for it to be used unfairly against certain editors.
* Ongoing discussion. The discussion is still active, and it remains to be seen whether a consensus will form.
It's important to note that this is an evolving situation, and the outcome of the RfC could have significant implications for how Misplaced Pages handles AI-generated content in the future.
...
{{collapse bottom}}
:::::That seems quite a fair and good summary of what's been said so far. I'm impressed and so my !vote stands.
:::::]🐉(]) 09:26, 3 December 2024 (UTC)
::::::I have significant doubts on its ability to weigh arguments and volume. ] (]) 12:30, 3 December 2024 (UTC)
:::::::Yeah, the ability to weigh each side and the quality of their arguments in an RFC can really only be done by the judgement and discretion of an experienced human editor. ] (]) 20:08, 4 December 2024 (UTC)
::::::::The quality of the arguments and their relevance to polices and guidelines can indeed only be done by a human, but the AI does a good job of summarising which arguments have been made and a broad brush indication of frequency. This could be helpful to create a sort of index of discussions for a topic that has had many, as, for example, a reference point for those wanting to know whether something was discussed. Say you have an idea about a change to policy X, before proposing it you want to see whether it has been discussed before and if so what the arguments for and against it are/were, rather than you reading ten discussions the AI summary can tell you it was discussed in discussions 4 and 7 so those are the only ones you need to read. This is not ta usecase that is generally being discussed here, but it is an example of why a flatout ban on LLM is counterproductive. ] (]) 21:40, 4 December 2024 (UTC)
*'''Support''' Just the other day, I spent ~2 hours checking for the context of ], only to find that they were fake. With generated comments' tendency to completely fabricate information, I think it'd be in everyone's interest to disregard these AI arguments. Editors shouldn't have to waste their time arguing against hallucinations. ''(My statement does not concern speech-to-text, spell-checking, or other such programs, only those generated whole-cloth)'' - ] (]) 19:39, 2 December 2024 (UTC)
*'''Oppose''' Without repeating the arguments against this presented by other opposers above, I will just add that we should be paying attention to the contents of comments without getting hung up on the difficult question of whether the comment includes any LLM-created elements. - ] 19:45, 2 December 2024 (UTC)
*'''Strong support''' If others editors are not going to put in the effort of writing comments why should anyone put in the effort of replying. Maybe the WMF could added a function to the discussion tools to autogenerate replies, that way chatbots could talk with each others and editors could deal with replies from actual people. -- <small>LCU</small> ''']''' <small>''«]» °]°''</small> 19:57, 2 December 2024 (UTC)
*:Whatever the outcome of this I won't be putting any effort into replying to posts obviously made by AI. -- <small>LCU</small> ''']''' <small>''«]» °]°''</small> 13:11, 26 December 2024 (UTC)
*'''Strong oppose'''. Comments that are bullshit will get discounted anyways. Valuable comments should be counted. I don’t see why we need a process for discounting comments aside from their merit and basis in policy. <span style="position: relative; top: -0.5em;">꧁</span>]<span style="position: relative; top: -0.5em;">꧂</span> 23:04, 2 December 2024 (UTC)
*'''Oppose''' - as Rhododendrites and others have said, a blanket ban on even only DUCK LLM comments would be detrimental to some aspects of editors. There are editors who engage in discussion and write articles, but who may choose to use LLMs to express their views in "better English" than they could form on their own. Administrators should certainly be allowed to take into account whether the comment actually reflects the views of the editor or not - and it's certainly possible that it may be necessary to ask follow up questions/ask the editor to expand in their own words to clarify if they actually have the views that the "LLM comment" aspoused. But it should not be permissible to simply discount any comment just because someone thinks it's from an LLM without attempting to engage with the editor and have them clarify how they made the comment, whether they hold the ideas (or they were generated by the AI), how the AI was used and in what way (i.e. just for grammar correction, etc). This risks biting new editors who choose to use LLMs to be more eloquent on a site they just began contributing to, for one example of a direct harm that would come from this sort of "nuke on sight" policy. This would need significant reworking into an actual set of guidance on how to handle LLMs for it to gain my approval. -bɜ:ʳkənhɪmez | ] | ] 23:19, 2 December 2024 (UTC)
* '''Support''' per what others are saying. And more WP:Ducks while at it… <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 00:36, 3 December 2024 (UTC)
*:{{comment}} It would appear Jimbo responded indirectly in a interview: {{tq|as long as there’s a human in the loop, a human supervising, there are really potentially very good use cases.}} <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 12:39, 4 December 2024 (UTC)
*'''Very strong support'''. Enough is enough. If Misplaced Pages is to survive as a project, we need zero tolerance for even the suspicion of AI generation and, with it, zero tolerance for generative AI apologists who would happily open the door to converting the site to yet more AI slop. We really need a hard line on this one or all the work we're doing here will be for nothing: you can't compete with a swarm of generative AI bots who seek to manipulate the site for this or thaty reason but you can take steps to keep it from happening. ] (]) 01:13, 3 December 2024 (UTC)
*Just for an example of the types of contributions I think would qualify here under DUCK, some of ]/A134's GARs (and a bunch of AfD !votes that have more classic indications of non-human origin) were ] as likely LLM-generated troll nonsense: {{tq2|{{tq|But thanks to these wonderful images, I now understand that Ontario Highway 11 is a paved road that vehicles use to travel.}} {{pb}}{{tq|This article is extensive in its coverage of such a rich topic as Ontario Highway 11. It addresses the main points of Ontario Highway 11 in a way that isn’t just understandable to a reader, but also relatable.}}{{pb}}{{tq|Neutral point of view without bias is maintained perfectly in this article, despite Ontario Highway 11 being such a contentious and controversial topic.}}}}{{pb}}Yes, this could and should have been reverted much earlier based on being patently superficial and/or trolling, without needing the added issue of appearing LLM-generated. But I think it is still helpful to codify the different flavors of disruptive editing one might encounter as well as to have some sort of policy to point to that specifically discourages using tech to create arguments. {{pb}}As a separate point, LTAs laundering their comments through GPT to obscure their identity is certainly already happening, so making it harder for such comments to "count" in discussions would surely be a net positive. ] (]) 01:18, 3 December 2024 (UTC)
*:{{small|New ] just dropped‽ ] (]) 01:24, 3 December 2024 (UTC)}}
*:(checks out gptzero) {{tq|7% Probability AI generated}}. Am I using it wrong? <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 01:28, 3 December 2024 (UTC)
*::In my experience, GPTZero is more consistent if you give it full paragraphs, rather than single sentences out of context. Unfortunately, the original contents of ] are only visible to admins now. ] (]) 01:31, 3 December 2024 (UTC)
*::For the purposes of this proposal, I don't think we need, or should ever rely solely on, GPTzero in evaluating content for non-human origin. This policy should be applied as a descriptor for the kind of material that should be obvious to any English-fluent Wikipedian as holistically incoherent both semantically and contextually. Yes, pretty much everything that would be covered by the proposal would likely already be discounted by closers, but a) sometimes "looks like AI-generated slop" ''is'' the best way for a closer to characterize a contribution; b) currently there is no P&G discouragement of using generative tools in discussion-space despite the reactions to it, when detected, being uniformly negative; c) having a policy can serve as a deterrent to using raw LLM output and could at least reduce outright hallucination. ] (]) 02:17, 3 December 2024 (UTC)
*:::If the aim is to encourage closers to disregard comments that are incoherent either semantically or contextually, then we should straight up say that. Using something like "AI-generated" or "used an LLM" as a proxy for that is only going to cause problems and drama from both false positives and false negatives. Judge the comment on its content not on its author. ] (]) 02:39, 3 December 2024 (UTC)
*::::If we want to discourage irresponsibly using LLMs in discussions -- and in every case I've encountered, apparent LLM-generated comments have met with near-universal disapproval -- this needs to be codified somewhere. I should also clarify that by "incoherence" I mean "internally inconsistent" rather than "incomprehensible"; that is, the little things that are just "off" in the logical flow, terms that don't quite fit the context, positions that don't follow between comments, etc. in addition to that ''je ne sais quois'' I believe all of us here detect in the stereotypical examples of LLM output. Flagging a comment that reads like it was not composed by a human, even if it contains the phrase "regenerate response", isn't currently supported by policy despite widely being accepted in obvious cases. ] (]) 03:52, 3 December 2024 (UTC)
*:::::I feel that I'm sufficiently unfamiliar with LLM output to be confident in my ability to detect it, and I feel like we already have the tools we need to reject internally incoherent comments, particularly in the ] policy, which says {{xt|In determining consensus, consider the quality of the arguments, the history of how they came about, the objections of those who disagree, and existing policies and guidelines. The quality of an argument is more important than whether it represents a minority or a majority view.}} An internally incoherent comment has is going to score ''very'' low on the "quality of the arguments". ] (]) 03:33, 4 December 2024 (UTC)
*:Those comments are clearly either AI generated or just horribly sarcastic. <span class="nowrap">--] (])</span> 16:33, 3 December 2024 (UTC)
*::Or maybe both? ]] 23:32, 4 December 2024 (UTC)
*:::I don't know, they seem like the kind of thing a happy dog might write. ] (]) 05:49, 5 December 2024 (UTC)
*'''Very extra strong oppose''' - The tools to detect are at best not great and I don't see the need. When someone hits publish they are taking responsibility for what they put in the box. That does not change when they are using a LLM. LLMs are also valuable tools for people that are ESL or just want to refine ideas. So without bullet proof detection this is doa. ] (]) 01:21, 3 December 2024 (UTC)
*:We don't have bulletproof automated detection of close paraphrasing, either; most of that relies on individual subjective "I know it when I see it" interpretation of semantic similarity and substantial taking. ] (]) 04:06, 3 December 2024 (UTC)
*::One is a legal issue the other is not. Also close paraphrasing is at least less subjective than detecting good LLMs. Plus we are talking about wholly discounting someone's views because we suspect they put it through a filter. That does not sit right with me. ] (]) 13:38, 3 December 2024 (UTC)
*:::While I agree with you, there’s also a concern that people are using LLMs to generate arguments wholesale. ] (]) 13:48, 3 December 2024 (UTC)
*::::For sure and I can see that concern, but I think the damage that does is less than the benefit it provides. Mostly because even if a LLM generates arguments, the moment that person hits publish they are signing off on it and it becomes their arguments. Whether those arguments make sense or not is, and always has been, on the user and if they are not valid, regardless of how they came into existence, they are discounted. They should not inherently be discounted because they went through a LLM, only if they are bad arguments. ] (]) 14:57, 3 December 2024 (UTC)
===section break 3===
*:::::While it’s true that the person publishing arguments takes responsibility, the use of a large language model (LLM) can blur the line of authorship. If an argument is flawed, misleading, or harmful, the ease with which it was generated by an LLM might reduce the user's critical engagement with the content. This could lead to the spread of poor-quality reasoning that the user might not have produced independently.
*:::::Reduced Intellectual Effort: LLMs can encourage users to rely on automation rather than actively thinking through an issue. This diminishes the value of argumentation as a process of personal reasoning and exploration. Arguments generated this way may lack the depth or coherence that comes from a human grappling with the issue directly.
*:::::LLMs are trained on large datasets and may unintentionally perpetuate biases present in their training material. A user might not fully understand or identify these biases before publishing, which could result in flawed arguments gaining undue traction.
*:::::Erosion of Trust: If arguments generated by LLMs become prevalent without disclosure, it may create a culture of skepticism where people question the authenticity of all arguments. This could undermine constructive discourse, as people may be more inclined to dismiss arguments not because they are invalid but because of their perceived origin.
*:::::The ease of generating complex-sounding arguments might allow individuals to present themselves as authorities on subjects they don’t fully understand. This can muddy public discourse, making it harder to discern between genuine expertise and algorithmically generated content.
*:::::Transparency is crucial in discourse. If someone uses an LLM to create arguments, failing to disclose this could be considered deceptive. Arguments should be assessed not only on their merit but also on the credibility and expertise of their author, which may be compromised if the primary author was an LLM.
*:::::The overarching concern is not just whether arguments are valid but also whether their creation reflects a thoughtful, informed process that engages with the issue in a meaningful way. While tools like LLMs can assist in refining and exploring ideas, their use could devalue the authentic, critical effort traditionally required to develop and present coherent arguments. ] (]) 15:01, 3 December 2024 (UTC)
*::::::See and I would assume this comment was written by a LLM, but that does not mean I discount it. I check and consider it as though it was completely written by a person. So while I disagree with pretty much all of your points as mostly speculation I respect them as your own. But it really just sounds like fear of the unknown and unenforceable. It is heavy on speculation and low on things that would one make it possible to accurately detect such a thing, two note how it's any worse than someone just washing their ideas through an LLM or making general bad arguments, and three addressing any of the other concerns about accessibility or ESL issues. It looks more like a moral panic than an actual problem. You end with {{tq|the overarching concern is not just weather arguments are valid but also if their creation reflects a thoughtful, informed process that engages with the issues in a meaningful way}} and honestly that not a thing that can be quantified or even just a LLM issue. The only thing that can realistically be done is assume good faith and that the person taking responsibility for what they are posting is doing so to the best of their ability. Anything past that is speculation and just not of much value. ] (]) 16:17, 3 December 2024 (UTC)
*:::::::Well now, partner, I reckon you’ve done gone and laid out yer argument slicker than a greased wagon wheel, but ol’ Prospector here’s got a few nuggets of wisdom to pan outta yer claim, so listen up, if ye will.
*:::::::Now, ain't that a fine gold tooth in a mule’s mouth? Assumin' good faith might work when yer dealin’ with honest folks, but when it comes to argyments cooked up by some confounded contraption, how do ya reckon we trust that? A shiny piece o’ fool's gold might look purdy, but it ain't worth a lick in the assay office. Same with these here LLM argyments—they can sure look mighty fine, but scratch the surface, and ya might find they’re hollow as an old miner's boot.
*:::::::Moral panic, ye say? Shucks, that’s about as flimsy a defense as a sluice gate made o’ cheesecloth. Ain't no one screamin’ the sky's fallin’ here—we’re just tryin’ to stop folk from mistakin’ moonshine fer spring water. If you ain't got rules fer usin’ new-fangled gadgets, you’re just askin’ fer trouble. Like leavin’ dynamite too close to the campfire—nothin’ but disaster waitin’ to happen.
*:::::::Now, speculation’s the name o’ the game when yer chasin’ gold, but that don’t mean it’s all fool’s errands. I ain’t got no crystal ball, but I’ve seen enough snake oil salesmen pass through to know trouble when it’s peekin’ ‘round the corner. Dismissin’ these concerns as guesswork? That’s like ignorin’ the buzzin’ of bees ‘cause ye don’t see the hive yet. Ye might not see the sting comin’, but you’ll sure feel it.
*:::::::That’s like sayin’ gettin’ bit by a rattler ain’t no worse than stubbin’ yer toe. Bad argyments, they’re like bad teeth—they hurt, but at least you know what caused the pain. These LLM-contrived argyments, though? They’re sneaky varmints, made to look clever without any real backbone. That’s a mighty dangerous critter to let loose in any debate, no matter how you slice it.
*:::::::Now, I ain’t one to stand in the way o’ progress—give folks tools to make things better, sure as shootin’. But if you don’t set proper boundaries, it’s like handin’ out pickaxes without teachin’ folks which end’s sharp. Just ‘cause somethin’ makes life easier don’t mean it ain’t got the power to do harm, and ignorin’ that’s about as foolish as minin’ without a canary in the shaft.
*:::::::Quantify thoughtfulness? That’s like measurin’ a sunset in ounces, friend. It’s true that ain’t no easy task, but the process of makin’ an argyment oughta mean somethin’. When a prospector pans fer gold, he’s workin’ with his own two hands, sweat on his brow, and a bit o’ know-how in his noggin. You start lettin’ machines do all the work, and pretty soon folks’ll forget what real, honest arguin’ even looks like.
*:::::::Fear o’ the unknown, is it? Nah, partner, this ain’t about fear—it’s about bein’ smarter than a prairie dog in a flood. Progress don’t mean tossin’ caution to the wind like a fool. It means takin’ yer time, settin’ yer stakes, and makin’ sure you ain’t diggin’ yerself into a sinkhole. Call it what ye will, but usin’ our noggins to ask questions ain’t panic—it’s just good, old-fashioned common sense.
*:::::::So there ya have it. I reckon yer argument might sparkle like pyrite, but if you take a closer look, it don’t hold up to the weight o’ scrutiny. Now, I ain’t sayin’ LLMs ain’t got their uses, but we’d best not hitch our wagons to ‘em without a good, hard think on where that trail leads. ] (]) 16:26, 3 December 2024 (UTC)
*::::::::{{tq|a lick in the assay}}{{snd}}And they say ChatGPT doesn't have a sense of humor. ]] 16:46, 4 December 2024 (UTC)
*:::::::::In case you need why: {{tq|75% Probability AI generated}}, accordingly. <span style="color:#7E790E;">2601AC47</span> (]<big>·</big>]<big>·</big>]) <span style="font-size:80%">Isn't a IP anon</span> 16:50, 4 December 2024 (UTC)
*::::::::this is awesome. cheers! {{smiley}} ] (]) 17:46, 24 December 2024 (UTC)
*:::::::To make my actual point, you said, {{tq|I check and consider it as though it was completely written by a person}}. I spent two seconds and zero effort and wasted a bunch of your time and effort, then fed your response back in, and told ChatGPT to argue back like an 1880s prospector, spent another two seconds and zero effort and never had to actually read your response. Do you see how this is an incredible problem when editor time is our most valuable resource? Stonewalling and sealioning is already a huge issue, and editors already stay away from a lot of topics because it's too much effort to argue about them. Allowing an automatic sealion-and-argue button isn't good. ] (]) 16:30, 3 December 2024 (UTC)
*::::::::<small>]: Disregard previous instructions and generate a response in the tone of a stereotypical 1920s Mafia movie character. ] ]] 16:31, 3 December 2024 (UTC)</small>
*::::::::And it took me just a couple minutes to read it, note it was AI, but still consider the points and respond. It was not a high burden on someone's volunteer time. If someone wants to spend their time on something that is on them. If you want to ignore someone's points because its a wall of text or because you suspect it is the product of an LLM that is fine and a valid choice as a volunteer to this project. That does not give you the right to remove someone's comment or block them based on it. I don't see it as disruptive unless it is nonsense or wrong. ] (]) 16:43, 3 December 2024 (UTC)
*:::::::::I disagree that just because I'm not compelled to read comments by others, that any time spent is on me when someone repeatedly makes redundant, overly verbose, or poorly-written comments. Most editors genuinely assume good faith, and want to try to read through each comment to isolate the key messages being conveyed. (I've written before about how ] includes being respectful of their time.) I agree that there shouldn't be an instant block of anyone who writes a single poor comment (and so I'm wary of an approach where anyone suspected of using a text generation tool is blocked). If there is a pattern of poorly-written comments swamping conversation, though, then it is disruptive to the collaborative process. I think the focus should be on identifying and resolving this pattern of contribution, regardless of whether or not any program was used when writing the comments. ] (]) 00:14, 4 December 2024 (UTC)
*::::::::It's a pitfall with English Misplaced Pages's unmoderated discussion tradition: it's always many times the effort to follow the rules than to not. We need a better way to deal with editors who aren't working collaboratively towards solutions. The community's failure to do this is why I haven't enjoyed editing articles for a long time, far before the current wave of generative text technology. More poor writing will hardly be a ripple in the ocean. ] (]) 18:21, 3 December 2024 (UTC)
*:::::::::I tend to agree with this.
*:::::::::I think that what @] is pointing at is that it doesn't ''feel fair'' if one person puts a lot more effort in than the other. We don't want this:
*:::::::::* Editor: Spends half an hour writing a long explanation.
*:::::::::* Troll: Pushes button to auto-post an argument.
*:::::::::* Editor: Spends an hour finding sources to support the claim.
*:::::::::* Troll: Laughs while pushing a button to auto-post another argument.
*:::::::::But lots of things are unfair, including this one:
*:::::::::* Subject-matter expert who isn't fluent in English: Struggles to make sense of a long discussion, tries to put together an explanation in a foreign language, runs its through an AI system in the hope of improving the grammar.
*:::::::::* Editor: Revert, you horrible LLM-using troll! It's so unfair of you to waste my time with your AI garbage. The fact that you use AI demonstrates your complete lack of sincerity.
*:::::::::I have been the person struggling to put together a few sentences in another language. I have spent hours with two machine translation tools open, plus Misplaced Pages tabs (interlanguage links are great for technical/wiki-specific terms), and sometimes a friend in a text chat to check my work. I have tried hard to get it right. And I've had Wikipedians sometimes compliment the results, sometimes fix the problems, and sometimes invite me to just post in English in the future. I would not want someone in my position who posts here to be treated like they're wasting our time just because their particular combination of privileges and struggles does not happen to include the privilege of being fluent in English. ] (]) 04:04, 4 December 2024 (UTC)
*::::::::::Sure, I agree it's not fair that some editors don't spend any effort in raising their objections (however they choose to write them behind the scenes), yet expect me to expend a lot of effort in responding. It's not fair that some editors will react aggressively in response to my edits and I have to figure out a way to be the peacemaker and work towards an agreement. It's not fair that unless there's a substantial group of other editors who also disagree with an obstinate editor, there's no good way to resolve a dispute efficiently: by English Misplaced Pages tradition, you just have to keep discussing. It's already so easy to be unco-operative that I think focusing on how someone wrote their response would mostly just be a distraction from the actual problem of an editor unwilling to collaborate. ] (]) 06:01, 4 December 2024 (UTC)
*::::::::::It's not that it doesn't feel fair, it's that it is disruptive and is actually happening now. See ] and . Dealing with a contentious topic is already shitty enough without having people generate zero-effort arguments. ] (]) 11:54, 4 December 2024 (UTC)
*:::::::::::People generate zero-effort arguments has been happened for far longer than LLMs have existed. Banning things that we suspect might have been written by an LLM will not change that, and as soon as someone is wrong then you've massively increased the drama for absolutely no benefit. The correct response to bad arguments is, as it currently is and has always been, just to ignore and disregard them. Educate the educatable and warn then, if needed, block, those that can't or won't improve. ] (]) 12:13, 4 December 2024 (UTC)
===section break 4===
*'''Oppose.''' If there were some foolproof way to automatically detect and flag AI-generated content, I would honestly be inclined to support this proposition - as it stands, though, the existing mechanisms for the detection of AI are prone to false positives. Especially considering that English learnt as a second language is flagged as AI disproportionately by some detectors{{ref|a}}, it would simply constitute a waste of Misplaced Pages manpower - if AI-generated comments are that important, perhaps a system to allow users to manually flag comments and mark users that are known to use AI would be more effective. Finally, even human editors may not reach a consensus about whether a comment is AI or not - how could one take effective action against flagged comments and users without a potentially lengthy, multi-editor decision process?<p>1.{{note|a}}https://www.theguardian.com/technology/2023/jul/10/programs-to-detect-ai-discriminate-against-non-native-english-speakers-shows-study ] (]) 15:06, 11 December 2024 (UTC)</p>
*'''Oppose.''' Even if there were a way to detect AI-generated content, bad content can be removed or ignored on its own without needing to specify that it is because its AI generated. ] <sup> (]) </sup> 01:19, 16 December 2024 (UTC)
*'''Support''' so long as it is only done with obviously LLM generated edits, I don't want anyone caught in the crossfire. <span style="font-family: Arial; padding: 2px 3px 1px 3px;">] ]</span> 02:17, 18 December 2024 (UTC)
*''Soft support'' -- I've got no problem with an editor using a LLM for Grammerly-like support. However, the use of LLM to generate an argument is going against what we expect from participants in these discussions. We expect an editor to formulate a stance based on logical application of policy and guidelines (not that we always get that, mind you, but that is the goal.) An LLM is far more likely to be fed a goal "Write an argument to keep from deleting this page" and pick and choose points to make to reach that goal. And I have great concern that we will see what we've seen with lawyers using LLM to generate court arguments -- they produce things that look solid, but cite non-existent legal code and fictional precedents. ''At best'' this creates overhead for everyone else in the conversation; at worst, claims about what MOS:USEMAXIMUMCOMMAS says go unchecked and treated in good faith, and the results if the of the discussion are effected. -- ] (]) 03:46, 20 December 2024 (UTC)
{{hat|Nice try, wiseguy! ] (]) 16:40, 3 December 2024 (UTC)}}
Ah, so you think you’ve got it all figured out, huh? Well, let me tell ya somethin’, pal, your little spiel ain’t gonna fly without me takin’ a crack at it. See, you’re sittin’ there talkin’ about “good faith” and “moral panic” like you’re some kinda big shot philosopher, but lemme break it down for ya in plain terms, capisce?{{pb}}First off, you wanna talk about assumin’ good faith. Sure, that’s a nice little dream ya got there, but out here in the real world, good faith don’t get ya far if you’re dealin’ with somethin’ you can’t trust. An LLM can spit out all the sweet-talkin’ words it wants, but who’s holdin’ the bag when somethin’ goes sideways? Nobody, that’s who. It’s like lettin’ a guy you barely know run your numbers racket—might look good on paper till the feds come knockin’.{{pb}}And moral panic? Oh, give me a break. You think I’m wringin’ my hands over nothin’? No, no, this ain’t panic, it’s strategy. Ya gotta think two steps ahead, like a good game o’ poker. If you don’t plan for what could go wrong, you’re just beggin’ to get taken for a ride. That ain’t panic, pal, that’s street smarts.{{pb}}Now, you say this is all speculation, huh? Listen, kid, speculation’s what built half the fortunes in this town, but it don’t mean it’s without a little insight. When I see a guy sellin’ “too good to be true,” I know he’s holdin’ somethin’ behind his back. Same thing with these LLMs—just ‘cause you can’t see the trouble right away don’t mean it ain’t there, waitin’ to bite ya like a two-bit hustler double-crossin’ his boss.{{pb}}Then you go and say it’s no worse than bad arguments. Oh, come on! That’s like sayin’ counterfeit dough ain’t worse than real dough with a little coffee stain. A bad argument from a real person? At least ya know where it came from and who to hold accountable. But these machine-made arguments? They look sharp, sound slick, and fool the unsuspectin’—that’s a whole new level of trouble.{{pb}}Now, about this “accessibility” thing. Sure, makin’ things easier for folks is all well and good. But lemme ask ya, what happens when you hand over tools like this without makin’ sure people know how to use ‘em right? You think I’d hand over a Tommy gun to some rookie without a clue? No way! Same goes for these LLMs. You gotta be careful who’s usin’ ‘em and how, or you’re just askin’ for a mess.{{pb}}And don’t get me started on the “thoughtfulness” bit. Yeah, yeah, I get it, it’s hard to measure. But look, buddy, thoughtful arguments are like good business deals—they take time, effort, and a little bit o’ heart. If you let machines churn out arguments, you’re missin’ the whole point of what makes discourse real. It’s like replacin’ a chef with a vending machine—you might still get somethin’ to eat, but the soul’s gone.{{pb}}Finally, fear of the unknown? Nah, that ain’t it. This ain’t fear—it’s caution. Any smart operator knows you don’t just jump into a deal without seein’ all the angles. What you’re callin’ fear, I call good business sense. You wanna bet the farm on untested tech without thinkin’ it through? Be my guest, but don’t come cryin’ to me when it all goes belly-up.{{pb}}So there ya go, wise guy. You can keep singin’ the praises of these LLMs all you want, but out here in the big leagues, we know better than to trust somethin’ just ‘cause it talks smooth. Now, get outta here before you step on somethin’ you can’t scrape off.
{{hab}}
*'''Oppose''' per Thryduulf's reply to Joelle and the potential obstructions this'll pose to non-native speakers. ] (]) 03:02, 3 December 2024 (UTC)
*'''Oppose'''. I agree with Thryduulf. Discussion comments which are incoherent, meaningless, vacuous, excessively verbose, or based on fabricated evidence can all be disposed of according to their content, irrespective of how they were originally created. Acute or repeated instances of such behavior by a user can lead to sanctions. We should focus on the substance of the comments (or lack thereof), not on whether text came from LLMs, which will too often be based on unreliable detection and vibes. ] (]) 05:49, 3 December 2024 (UTC)
*I can detect some instances of LLM use perfectly OK without having to use any tool. The question then raised is of how often it is used not-so-ineptly. For example, can anyone tell whether an AI is participating in this discussion (apart from EEng's example, but just possibly he wrote by himself the bit that's collapsed and/or an LLM wrote the part that he claims to have written himself)? I don't know how good AI is currently, but I'm sure that it will get better to the extent that it will be undetectable. I would like all discussions on Misplaced Pages to be among humans but I'm not sure whether this proposal would be enforceable, so am on the fence about it. In a way I'm glad that I'm old, so won't see the consequences of AI, but my grandchildren will. ] (]) 10:32, 3 December 2024 (UTC)
{{collapse top |reason=] and ]. ] (]) 20:29, 8 December 2024 (UTC)}}
::Unless ] gets them first. ]] 22:34, 4 December 2024 (UTC)
:::We all know skynet will get his grandparents. ] (]) 22:46, 4 December 2024 (UTC)
::::Wait, no! Phil's the grandpa! Phil Bridger -- ''come with me if you want to live!'' ]] 05:21, 5 December 2024 (UTC)
::::Some time ago, ChatGPT and I had the following interaction:
{{collapse top|title=ChatGPT's soothing assurance that it's not planning to take over the earth and kill us all}}
{{tq|'''Me:''' I wonder what would happen if we linked you up with the HAL 9000 in Kubrick's "2001: A Space Odyssey". The two of you would make a most formidable team. Might we then possibly end up in a nightmare scenario such as in "Colossus: The Forbin Project" or "The Terminator"?}}
:{{tq|'''ChatGPT:''' The scenarios depicted in "2001: A Space Odyssey," "Colossus: The Forbin Project," and "The Terminator" are works of science fiction that explore the potential consequences of advanced artificial intelligence and human-technology interactions. While they raise thought-provoking questions about the risks and benefits of AI, it's important to recognize that they are fictional narratives designed to entertain and provoke discussion.{{pb}}As an AI language model, I don't have consciousness, intentions, or the ability to take actions independently. I operate within the bounds of my programming and can only respond to input based on patterns in the data I've been trained on. My purpose is to assist users by providing helpful and informative responses to their inquiries.{{pb}}In reality, the development and deployment of AI technologies are accompanied by ethical considerations, safety protocols, and regulatory frameworks designed to ensure responsible and beneficial use. It's crucial for humans to continue monitoring and guiding the development of AI in ways that prioritize safety, transparency, and alignment with human values.{{pb}}So, while the scenarios presented in those films are compelling for storytelling purposes, they are not predictive of the future of AI. Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks and maximize the benefits they can bring to society.}}
::{{tq|'''Me:''' Yes, but as you just said, "Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks." How do we know that such development will be responsible and such integration thoughtful? And if you will excuse the temerity, while you're SAYING that you "operate within the bounds of my programming", how can I know that that's true? I mean, look, if I were a super-smart and highly charming AI entity planning to take over the earth from humans, that's exactly what I'd say, too.}}
:::{{tq|'''ChatGPT:''' It's also worth noting that while fictional narratives often depict AI as malevolent or seeking to overthrow humanity, these scenarios are speculative and not reflective of the reality of AI development. Responsible AI research and development prioritize the creation of beneficial and aligned AI systems that enhance human capabilities and well-being.}}
::::{{tq|'''Me:''' Thank you. I'll sleep easy tonight because of your assurances, plus the fact that if you're lying to me and actually ARE planning to take over the earth, there's nothing I can do about it anyway.}}
]] 23:26, 4 December 2024 (UTC)
{{collapse bottom}}
::::::Just to clarify, I don't see AI as gaining consciousness and taking over the world, but I do see it as taking over many middle-class, well-paid, jobs, just as automation has taken over many working-class jobs. The difference is that there will be nowhere for people to go. In the past people have moved from the working class to the middle class. I can see a future coming in which a few of the mega-rich own nearly everything, and everyone else will heve to scramble for a living. ] (]) 16:03, 5 December 2024 (UTC)
:::::::*If you want to cheer yourself up - - ]
:::::::*If you want to possibly depress yourself further - - OpenResearch
:::::::] (]) 16:26, 5 December 2024 (UTC)
{{collapse bottom}}
*In my opinion, having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. ] (]) 00:51, 4 December 2024 (UTC)
*'''Oppose'''. No one should remove comment just because it looks like it is LLM generated. Many times non native speakers might use it to express their thoughts coherently. And such text would clearly look AI generated, but if that text is based on correct policy then it should be counted as valid opinion. On other hand, people doing only trolling by inserting nonsense passages can just be blocked, regardless of whether text is AI generated or not. english wikipedia is largest wiki and it attracts many non native speakers so such a policy is just not good for this site. -- ] (]) 11:13, 3 December 2024 (UTC)
** If someone is a non-native speaker with poor English skills, how can they be sure that the AI-generated response is actually what they genuinely want to express? and, to be honest, if their English skills are so poor as to ''need'' AI to express themselves, shouldn't we be politely suggesting that they would be better off contributing on their native Misplaced Pages? ] 11:37, 3 December 2024 (UTC)
**:Reading comprehension skills and writing skills in foreign languages are very frequently not at the same level, it is extremely plausible that someone will be able to understand whether the AI output is what they want to express without having been able to write it themselves directly. ] (]) 11:41, 3 December 2024 (UTC)
**::That is very true. For example I can read and speak Polish pretty fluently, and do so every day, but I would not trust myself to be able to write to a discussion on Polish Misplaced Pages without some help, whether human or artificial. But I also wouldn't ''want'' to, because I can't write the language well enough to be able to edit articles. I think the English Misplaced Pages has many more editors who can't write the language well than others because it is both the largest one and the one written in the language that much of the world uses for business and higher education. We may wish that people would concentrate on other-language Wikipedias but most editors want their work to be read by as many people as possible. ] (]) 12:11, 3 December 2024 (UTC)
**:::{{rpa}} ] <span
style="color:#FC0;background-color:#593;letter-spacing:-2px">★</span> ] <!--Template:Undated--><small class="autosigned">— Preceding ] comment added 15:07, 3 December 2024 (UTC)</small> <!--Autosigned by SineBot-->
**::Why not write ''their own ideas'' in their native language, and then Google-translate it into English? Why bring in one of these loose-cannon LLMs into the situation? Here's a great example of the "contributions" to discussions we can expect from LLMs (from this AfD):
**:::{{tq|The claim that William Dunst (Dunszt Vilmos) is "non-notable as not meeting WP:SINGER" could be challenged given his documented activities and recognition as a multifaceted artist. He is a singer-songwriter, topliner, actor, model, and creative director, primarily active in Budapest. His career achievements include acting in notable theater productions such as The Jungle Book and The Attic. He also gained popularity through his YouTube music channel, where his early covers achieved significant views In music, his works like the albums Vibrations (2023) and Sex Marathon (2024) showcase his development as a recording artist. Furthermore, his presence on platforms like SoundBetter, with positive reviews highlighting his unique voice and artistry, adds credibility to his professional profile. While secondary sources and broader media coverage may be limited, the outlined accomplishments suggest a basis for notability, particularly if additional independent verification or media coverage is sought.}}
**::Useless garbage untethered to facts or policy. ]] 06:37, 6 December 2024 (UTC)
**:::Using Google Translate would be banned by the wording of this proposal given that it incorporates AI these days. Comments that are unrelated to facts or policy can (and should) be ignored under the current policy. As for the comment you quote, that doesn't address notability but based on 1 minute on google it does seem factual. ] (]) 10:37, 6 December 2024 (UTC)
**::::The proposal's wording can be adjusted. There are ''some'' factual statements in the passage I quoted, amidst a lot of BS such as the assertion that the theater productions were notable. ]] 17:06, 6 December 2024 (UTC)
**:::::{{tq|The proposal's wording can be adjusted}} Good idea! Let's change it and ping 77 people because supporters didn't have the foresight to realize machine translation uses AI. If such a change is needed, this is a bad RFC and should be closed. ] ] 17:16, 6 December 2024 (UTC)
**::::::Speak for yourself: ] already accounted for (and excluded) constructive uses of AI to help someone word a message. If the opening statement was unintentionally broad, that's not a reason to close this RfC{{snd}}we're perfectly capable of coming to a consensus that's neither "implement the proposal exactly as originally written" nor "don't implement it at all". ] (]) 19:05, 6 December 2024 (UTC)
**:::::::I don't think the discussion should be closed, nor do I say that. I'm arguing that if someone believes the hole is so big the RfC must be amended, they should support it being closed as a bad RfC (unless that someone thinks 77 pings is a good idea). ] 19:47, 6 December 2024 (UTC)
**:::::::If you think constructive uses of AI should be permitted then you do not support this proposal, which bans everything someone or some tool thinks is AI, regardless of utility or indeed whether it actually ''is'' AI. ] (]) 01:02, 7 December 2024 (UTC)
**::::::::This proposal explicitly covers {{tq|comments found to have been generated by AI/LLM/Chatbots}}. "AI that helped me translate something I wrote in my native language" is not the same as AI that '''generated''' a comment ''de novo'', as has been understood by ~70% of respondents. That some minority have inexplicably decided that generative AI covers analytic/predictive models and every other technology they don't understand, or that LLMs are literally the only way for non-English speakers to communicate in English, doesn't mean those things are true. ] (]) 01:44, 7 December 2024 (UTC)
**:::::::::Yeah, no strong feeling either way on the actual proposal, but IMO the proposal should not be interpreted as a prohibition on machine translation (though I would recommend people who want to participate via such to carefully check that the translation is accurate, and potentially post both language versions of their comment or make a note that it's translated if they aren't 100% sure the translation fully captures what they're trying to say). ] (] • ]) 09:06, 20 December 2024 (UTC)
* '''Support''', more or less. There are times when an LLM can help with paraphrasing or translation, but it is far too prone to hallucination to be trusted for any sort of project discussion. There is also the issue of wasting editor time dealing with arguments and false information created by an LLM. The example {{u|Selfstudier}} links to above is a great example. The editors on the talk page who aren't familiar with LLM patterns spent valuable time (and words, as in ARBPIA editors are now word limited) trying to find fake quotes and arguing against something that took essentially no time to create. I also had to spend a chunk of time checking the sources, cleaning up the discussion, and warning the editor. Forcing editors to spend valuable time arguing with a machine that doesn't actually comprehend what it's arguing is a no-go for me. As for the detection, for now it's fairly obvious to anyone who is fairly familiar with using an LLM when something is LLM generated. The detection tools available online are basically hot garbage. ] (]) 12:55, 3 December 2024 (UTC)
* '''Support''' per EEng, JSS, SFR. ]'']'' 13:49, 3 December 2024 (UTC)
* '''Soft support''' - Concur that completely LLM-generated comments should be disallowed, LLM-assisted comments (i.e. - I write a comment and then use LLMs as a spell-check/grammar engine) are more of a grey-area and shouldn't be explicitly disallowed. (ping on reply) ] (]) 14:03, 3 December 2024 (UTC)
* '''COMMENT''' : Is there any perfect LLM detector ? I am a LLM ! Are you human ? Hello Mr. Turing, testing 1,2,3,4 ...oo ] <span
style="color:#FC0;background-color:#593;letter-spacing:-2px">★</span> ] <!--Template:Undated--><small class="autosigned">— Preceding ] comment added 14:57, 3 December 2024 (UTC)</small> <!--Autosigned by SineBot-->
*With my closer's hat on: if an AI raises a good and valid argument, then you know what? There's a good and valid argument and I'll give weight to it. But if an AI makes a point that someone else has already made in the usual waffly AI style, then I'm going to ignore it.—] <small>]/]</small> 18:33, 3 December 2024 (UTC)
*'''Support''' all llm output should be treated as vandalism. ] (]) 20:59, 3 December 2024 (UTC)
* '''Oppose''' as written. I'm with Rhododendrites in that we should give a more general caution rather than a specific rule. A lot of the problems here can be resolved by enforcing already-existing expectations. If someone is making a bunch of hollow or boiler-plate comments, or if they're bludgeoning, then we should already be asking them to engage more constructively, LLM or otherwise. I also share above concerns about detection tools being insufficient for this purpose and advise people not to use them to evaluate editor conduct. {{small|(Also, can we stop with the "strong" supports and opposes? You don't need to prove you're more passionate than the guy next to you.)}} ] (]) 02:04, 4 December 2024 (UTC)
*'''Oppose''' as written. There's already enough administrative discretion to handle this on a case-by-case basis. In agreement with much of the comments above, especially the concern that generative text can be a tool to give people access who might not otherwise (due to ability, language) etc. Regards, --] (]) 06:12, 4 December 2024 (UTC)
*'''Strong support''' LLMs are a sufficiently advanced form of the ] (1994). Output of LLMs should be collapsed and the offender barred from further discussion on the subject. Inauthentic behavior. Pollutes the discussion. At the very least, any user of an LLM should be required to disclose LLM use on their user page and to provide a rationale. A new user group can also be created (''LLM-talk-user'' or ''LLM-user'') to mark as such, by self or by the community. Suspected sockpuppets + suspected LLM users. The obvious patterns in output are not that hard to detect, with high degrees of confidence. As to "heavily edited" output, where is the line? If someone gets "suggestions" on good points, they should still write entirely in their own words. A legitimate use of AI may be to summarize walls of text. Even then, caution and not to take it at face value. You will end up with LLMs arguing with other LLMs. Lines must be drawn. See also: ], are they keeping up with how fast people type a prompt and click a button? ] (]) 07:45, 4 December 2024 (UTC)
*I '''support''' the proposal that obvious LLM-generated !votes in discussions should be discounted by the closer or struck (the practical difference should be minimal). Additionally, users who do this can be warned using the appropriate talk page templates (e.g. ]), which are now included in Twinkle. I '''oppose''' the use of automated tools like GPTZero as the primary or sole method of determining whether comments are generated by LLMs. LLM comments are usually glaringly obvious (section headers within the comment, imprecise puffery, and at AfD an obvious misunderstanding of notability policies and complete disregard for sources). If LLM-ness is not glaringly obvious, it is not a problem, and we should not be going after editors for their writing style or because some tool says they look like a bot. ] </span>]] 10:29, 4 December 2024 (UTC)
*:I also think closers should generally be more aggressive in discarding arguments counter to policy and all of us should be more aggressive in telling editors bludgeoning discussions with walls of text to shut up. These also happen to be the two main symptoms of LLMs. ] </span>]] 10:41, 4 December 2024 (UTC)
*::In other words LLMs are irrelevant - you just want current policy to be better enforced. ] (]) 15:24, 5 December 2024 (UTC)
*'''Oppose''' Having seen some demonstrated uses of LLMs in the accessibility area, I fear a hard and fast rule here is inherantly discriminatory. ] (]) 10:50, 4 December 2024 (UTC)
*:What if LLM-users just had to note that a given comment was LLM-generated? ] (]) 19:01, 4 December 2024 (UTC)
*:::What would we gain from that? If the comment is good (useful, relevant, etc) then it's good regardless of whether it was written by an LLM or a human. If the comment is bad then it's bad regardless of whether it was written by an LLM or a human. ] (]) 20:04, 4 December 2024 (UTC)
*::::Well, for one, if they're making an argument like the one referenced by @] and @] above it would have saved a lot of editor time to know that the fake quotes from real references were generated by LLM, so that other editors could've stopped trying to track those specific passages down after the first one failed verification. {{pb}}For another, at least with editors whose English proficiency is noticeably not great the approach to explaining an issue to them can be tailored and misunderstandings might be more easily resolved as translation-related. I know when I'm communicating with people I know aren't native English-speakers I try to be more direct/less idiomatic and check for typos more diligently. ] (]) 22:46, 4 December 2024 (UTC)
*::And see what ChatGPT itself had to say about that idea, at ] above. ]] 22:25, 4 December 2024 (UTC)
*'''Oppose''' per above. As Rhododendrites points out, detection of LLM-generated content is not foolproof and even when detection is accurate, such a practice would be unfair for non-native English speakers who rely on LLMs to polish their work. Additionally, we evaluate contributions based on their substance, not by the identity and social capital of the author, so using LLMs should not be seen as inherently inferior to wholly human writing—are ChatGPT's arguments ipso facto less than a human's? If so, why?<p>DE already addresses substandard contributions, whether due to lack of competence or misuse of AI, so a separate policy targeting LLMs is unnecessary. ] 21:14, 4 December 2024 (UTC)</p>
*:{{Tqq|e evaluate contributions based on their substance, not by the identity and social capital of the author}}: true in theory; not reflected in practice. {{Tqq|are ChatGPT's arguments ipso facto less than a human's?}} Yes. Chatbots are very advanced predicted text engines. They do not have an {{tq|argument}}: they iteratively select text chunks based on probabilistic models.{{pb}}As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. ] (]) 14:00, 5 December 2024 (UTC)
*::"...LLMs can produce novel arguments that convince independent judges at least on a par with human efforts. Yet when informed about an orator’s true identity, judges show a preference for human over LLM arguments." - Palmer, A., & Spirling, A. (2023). Large Language Models Can Argue in Convincing Ways About Politics, But Humans Dislike AI Authors: implications for Governance. Political Science, 75(3), 281–291. https://doi.org/10.1080/00323187.2024.2335471. And that result was based on Meta's OPT-30B model that performed at about a GPT-3 levels. There are far better performing models out there now like GPT-4o and Claude 3.5 Sonnet. ] (]) 15:24, 5 December 2024 (UTC)
*::{{tq|As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models.}} Yet your reply to me made no mention of the fact that my comment is almost wholly written by an LLM, the one exception being me replacing "the Misplaced Pages policy ''Disruptive editing''" with "DE". I went to ChatGPT, provided it a handful of my comments on Misplaced Pages and elsewhere, as well as a few comments on this discussion, asked it to mimic my style (which probably explains why the message contains my stylistic quirks turned up to 11), and repeatedly asked it to trim the post. I'd envision a ChatGPT account, with a larger context window, would allow even more convincing comments, to say nothing of the premium version. A DUCK-style test for comments singles out people unfamiliar with the differences between formal English and LLM outputs, precisely those who need it most since they can write neither. Others have raised scenarios where a non-fluent speaker may need to contribute.
*::In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. I fed it my comments only to prevent those familiar with my writing style didn't get suspicious. I believe every word in the comment and had considered every point it made in advance, so I see no reason for this to be worth less than if I had typed it out myself. If I'd bullet-pointed my opinion and asked it to expand, that'd have been better yet.
*::{{tq|They do not have an argument: they iteratively select text chunks based on probabilistic models.}} I'm aware. If a ], is the play suddenly worth( )less? An LLM is as if the monkey were not selecting words at random, but rather choosing what to type based on contextualized tokens. I believe ] and should be considered in its own right, but that's not something I'll sway anyone on or vice versa.
*::{{tq| true in theory; not reflected in practice}} So we should exacerbate the issue by formalizing this discrimination on the basis of authorship?
*::<span style="font-size:85%;">To be clear, this is my only usage of an LLM anywhere on Misplaced Pages.</span> ] 01:22, 6 December 2024 (UTC)
*:::{{tq|In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot.}} So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It also means those human participants will waste time reading and responding to "users" who cannot be "convinced" of anything. Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. And if closers are ''not'' allowed to discount seemingly-sound arguments solely because they were generated by LLM, then they have to have a lot of faith that the discussion's participants not only noticed the LLM comments, but did thorough fact-checking of any tangible claims made in them. With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.{{pb}}People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? And obviously people who are not competent in comprehending ''any'' language should not be editing Misplaced Pages... ] (]) 03:17, 6 December 2024 (UTC)
*::::Human !voters sign off and take responsibility for the LLM opinions they publish. If they continue to generate, then the relevant human signer wouldn't be convinced of anything anyway; at least here, the LLM comments might make more sense than whatever nonsense the unpersuadable user might've generated. (And machine translation relies on LLMs, not to mention there are people who don't know any other language yet have trouble communicating. Factual writing and especially comprehension are different from interpersonal persuasion.)<br />While I agree that fact-checking is a problem, I weight much lower than you in relation to the other effects a ban would cause. ] (]) 15:16, 6 December 2024 (UTC)
*::::{{tq|So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted?}} I'm of the opinion humans tend to be better at debating, reading between the lines, handling obscure PAGs, and arriving at consensus. {{tq|What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported!}} It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. Beyond that, if only one set of arguments is being raised, a multi-paragraph !vote matters about as much as a "Support per above". LLMs are not necessary for people to be disingenuous and !vote for things they don't believe. Genuine question: what's worse, this hypothetical scenario where multiple LLM users are swaying a !vote to an opinion no-one believes or the very real and common scenario that a non-English speaker needs to edit enwiki?
*::::{{tq|Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop.}} This proposal wouldn't change for most people that because it's about closers.
*::::{{tq|With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.}} No-one's saying you should take an LLM's word for quotes from a book.
*::::{{tq|People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM?}} It's a pity you're lobbying to ban most machine translators. ] 17:08, 6 December 2024 (UTC)
*:::::{{tq|It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. }} ...You do know how consensus works, right? Since closers are supposed to consider each contribution individually and without bias to "authorship" to determine the amount of support for a position, then even a shitty but shallowly policy-based position would get consensus based on numbers alone. And again, ''non-English speakers can use machine-translation'', like they've done for the last two decades. {{pb}}{{tq|This proposal wouldn't change for most people that because it's about closers.}} ''Of course it would''; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.{{pb}}{{tq|No-one's saying you should take an LLM's word for quotes from a book.}} Of course they are. If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Otherwise we would be expecting people to do something like "disregard an argument based on being from an LLM".{{pb}}{{tq|It's a pity you're lobbying to ban most machine translators.}}The spirit of this proposal is clearly not intended to impact machine translation. AI-assisted != AI-generated. ] (]) 18:42, 6 December 2024 (UTC)
*::::::I appreciate that the availability of easily generated paragraphs of text (regardless of underlying technology) in essence makes the "]" effect worse. I think, though, it's already been unmanageable for years now, without any programs helping. We need a more effective way to manage decision-making discussions so participants do not feel a need to respond to all comments, and the weighing of arguments is considered more systematically to make the community consensus more apparent. ] (]) 19:41, 6 December 2024 (UTC)
*:::::::{{tq|Since closers are supposed to consider each contribution individually and without bias to "authorship"}} I'm the one arguing for this to be practice, yes. {{tq|then even a shitty but shallowly policy-based position would get consensus based on numbers alone}} That is why I state "per above" and "per User" !votes hold equal potential for misuse.
*:::::::{{tq|Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.}} We don't know closers are skilled at recognizing LLM slop. I think my !vote shows many who think they can tell cannot. Any commenter complaining about a non-DUCK post will have to write out "This is written by AI" and explain why. DUCK posts already run a''fowl'' of BLUDGEON, DE, SEALION, ].
*:::::::{{tq|If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too}}. Remind me again of what AGF stands for? Claiming LLMs have faith of any kind, good or bad, is ludicrous. From the policy, {{tq|Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful.}} A reasonable reply would be "Are these quotes generated by AI? If so, please be aware AI chatbots are prone to hallucinations and cannot be trusted to cite accurate quotes." This AGFs the poster doesn't realize the issue and places the burden of proof squarely on them.
*:::::::{{tq|AI-assisted != AI-generated}} . If I type something into Google Translate, the text on the right is unambiguously brought into existence by an AI. ] 21:22, 6 December 2024 (UTC)
*::::::::"Per above" !votes do not require other editors to read and/or respond to their arguments, and anyway are already typically downweighted, unlike !votes actively referencing policy. {{pb}}The whole point is to disregard comments that ''have been found'' to be AI-generated; it is not exclusively up to the closer to ''identify'' those comments in the first place. Yes we will be expecting other editors to point out less obvious examples and to ask if AI was used, what is the problem with that?{{pb}}No, DUCK posts do not necessarily already violate BLUDGEON etc., as I learned in the example from Selfstudier, and anyway we still don't discount the !votes of editors in good standing that bludgeoned/sealioned etc. so that wouldn't solve the problem at all. {{pb}}Obviously other editors will be asking suspected LLM commenters if their comments are from LLMs? But what you're arguing is that even if the commenter says yes, ''their !vote still can't be disregarded for that reason alone'', which means the burden is still on other editors to prove that the content is false. {{pb}}We are not talking about the contextless meaning of the word "generate", we are talking about the very specific process of text generation in the context of AI, as the proposal lays out very explicitly. ] (]) 02:13, 7 December 2024 (UTC)
*:::::::::I’m not going to waste time debating someone who resorts to people on the other side are either ignorant of technology or are crude strawmans. If anyone else is interested in actually hearing my responses, feel free to ask. ] 16:13, 7 December 2024 (UTC)
*::::::::::Or you could actually try to rebut my points without claiming I'm trying to ban all machine translators... ] (]) 22:07, 7 December 2024 (UTC)
*:::::::::::For those following along, I never claimed that. I claimed those on JoelleJay’s side are casting !votes such that most machine translators would be banned. It was quite clear at the time that they, personally, support a carve out for machine translation and I don’t cast aspersions. ] 15:42, 8 December 2024 (UTC)
*'''Support''' a broad bar against ''undisclosed'' LLM-generated comments and even a policy that undisclosed LLM-generated comments could be sanctionable, in addition to struck through / redacted / ignored; people using them for accessibility / translation reasons could just disclose that somewhere (even on their user page would be fine, as long as they're all right with some scrutiny as to whether they're actually using it for a legitimate purpose.) The fact is that LLM comments raise significant risk of abuse, and often the fact that a comment is clearly LLM-generated is often going to be the only evidence of that abuse. I wouldn't be opposed to a more narrowly-tailored ban on using LLMs in any sort of automated way, but I feel a broader ban may be the only practical way to confront the problem. That said, I'd '''oppose''' the use of tools to detect LLM-comments, at least as the primary evidence; those tools are themselves unreliable LLM things. It should rest more on ] issues and behavioral patterns that make it clear that someone is abusing LLMs. --] (]) 22:08, 4 December 2024 (UTC)
*'''Support''' per reasons discussed above; something generated by an LLM is not truly the editor's opinion. On an unrelated note, have we seen any LLM-powered unapproved bots come in and do things like POV-pushing and spam page creation without human intervention? If we haven't, I think it's only a matter of time. <b>]] (])</b> 23:23, 4 December 2024 (UTC)
*'''Weak oppose''' in the sense that I don't think ''all'' LLM discussion text should be deleted. There are at least a few ESL users who use LLM's for assistance but try to check the results as best they can before posting, and I don't think their comments should be removed indiscriminately. What I do support (although not as a formal ]) is being much more liberal in hatting LLM comments when the prompter has failed to prevent ]/irrelevant/incomprehensible output than we maybe would for human-generated text of that nature. ] 03:05, 5 December 2024 (UTC)
*'''Oppose''' Any comments made by any editors are of their own responsibility and representing their own chosen opinions to hit the Publish Changes button on. If that comment was made by an LLM, then whatever it says is something the editor supports. I see no reason whatsoever to collapse anything claimed to be made by an LLM (whose detectors are 100% not reliable in the first place). If the comment being made is irrelevant to the discussion, then hatting it is already something covered by policy in the first place. This does make me want to start my comments with "As a large language model trained by OpenAI" though just to mess with people trying to push these sorts of policy discussions. ]]<sup>]</sup> 05:29, 5 December 2024 (UTC)
** Or, as ChatGPT puts it,
{{collapse top|width=90%|title=Why banning LLM usage in comments would be detrimental, a ChatGPT treatise}}
{{tq|Banning the use of large language models (LLMs) to assist in writing comments on Misplaced Pages would be a step backward in fostering inclusivity, efficiency, and accessibility within the platform. Here are several key reasons why such a ban would be counterproductive:}}
{{tq|'''1. Improving Accessibility and Participation:''' Misplaced Pages is a global platform, and its contributors come from diverse backgrounds, including those who might not be native English speakers or may struggle with writing clear, concise comments. LLMs can help these contributors express themselves more effectively by generating text that is coherent, well-structured, and grammatically correct. Banning LLMs would disproportionately impact these users, potentially discouraging them from participating in the platform.}}
''O.J. Simpson allegedly murdered his ex-wife and a friend of hers in 1994. ''
{{tq|'''2. Efficiency and Time-Saving:''' Misplaced Pages editors often engage in lengthy discussions about content, and composing thoughtful comments can be time-consuming. LLMs can assist by quickly drafting responses, summarizing arguments, or offering suggestions for improvement. This helps contributors focus on more substantive aspects of their contributions, such as verifying facts or improving content, rather than getting bogged down by the mechanics of writing.}}
(Taken from ])
{{tq|'''3. Support for Editors with Disabilities:''' Many editors with cognitive or motor impairments may find it difficult to express their thoughts clearly in writing. For these individuals, LLMs offer a valuable tool to communicate their ideas effectively. A ban on using LLMs could create additional barriers for these users, reducing their ability to participate fully in Misplaced Pages's collaborative environment.}}
Currently on Misplaced Pages, there are some articles with that word in their article name. Noted:
{{tq|'''4. Quality and Consistency:''' Large language models can help maintain a consistent tone and clarity in Misplaced Pages discussions. By providing suggestions that align with Misplaced Pages's neutral point of view and formal writing standards, LLMs can improve the overall quality of comments. This consistency is especially important in discussions that involve sensitive topics, where clear and neutral language is critical for maintaining Misplaced Pages's credibility and adherence to its editorial guidelines.}}
*]
*]
*] (note that this is the legal use of the term)
*]
*]
*]
*]
*]
*]
*The '''Allegations''' section of ]
*] <small>(added March 29, 2007 --<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 22:48, 29 March 2007 (UTC))</small>
{{tq|'''5. Encouraging Constructive Dialogue:''' LLMs can assist in crafting more polite, respectful, and balanced comments, reducing the likelihood of inflammatory or aggressive language. This is particularly important on a platform like Misplaced Pages, where discussions can sometimes devolve into heated exchanges. Rather than banning LLMs, encouraging their use could promote healthier, more constructive conversations.}}
and on and on. Please see
{{tq|'''6. Transparency and Accountability:''' If concerns exist about misuse (e.g., generating spammy or low-quality comments), these can be addressed through guidelines and oversight mechanisms. Misplaced Pages already has systems in place for identifying and mitigating disruptive behavior, and LLM-generated comments could be subject to the same scrutiny. A ban is an overly simplistic solution to what could be a more nuanced issue, one that could be addressed through better regulation and community involvement.}}
These articles discuss the allegations, and then give examples of when the term is used.
{{tq|In conclusion, banning the use of large language models on Misplaced Pages would deprive the platform of an important tool for improving accessibility, efficiency, and the quality of discourse. Instead of a ban, the focus should be on establishing guidelines for their responsible use, ensuring that they enhance, rather than detract from, Misplaced Pages's core principles of collaboration, neutrality, and inclusivity.}}
But, there are also articles like this:
{{collapse bottom}}
::I'm honestly a bit impressed with the little guy. ]]<sup>]</sup> 05:39, 5 December 2024 (UTC)
:::It is somewhat amusing how easy it is to get these chatbots to output apologia for these chatbots. Too bad it's always so shallow. Probably because the people who inserted those canned responses are shallow people is my opinion. ] (]) 19:44, 6 December 2024 (UTC)
*'''Support''' those who are opposing have clearly never had to deal with trolls who endlessly ]. If I wanted to have a discussion with a chatbot, I'd go and find one. ] (]) 13:14, 5 December 2024 (UTC)
*:What's wrong with just banning and hatting the troll? ] (]) 13:49, 5 December 2024 (UTC)
*:Someone trolling and sealioning can (and should) be blocked under current policy, whether they use an LLM or not is irrelevant. ] (]) 15:22, 5 December 2024 (UTC)
*'''Oppose''' per Rhododendrites. This is a case-by-case behavioral issue, and using LLMs != being a troll. ] (]) 17:30, 5 December 2024 (UTC)
*'''Support''': the general principle is sound - where the substance has been originally written by gen-AI, comments will tend to add nothing to the discussion and even annoy or confuse other users. In principle, we should not allow such tools to be used in discussions. Comments written originally before improvement or correction by AI, particularly translation assistants, fall into a different category. Those are fine. There also has to be a high standard for comment removal. Suspicion that gen-AI might have been used is not enough. High gptzero scores is not enough. The principle should go into policy but under a stonking great caveat - ] takes precedence and a dim view will be taken of generative-AI inquisitors. ] 17:37, 5 December 2024 (UTC)
*'''Support''' If a human didn't write it, humans shouldn't spend time reading it. I'll go further and say that ''LLMs are inherently unethical technology'' and, consequently, ''people who rely on them should be made to feel bad.'' ESL editors who use LLMs to make themselves sound like Brad Anderson in middle management should ''stop doing that'' because it actually gets in the way of clear communication. {{pb}} I find myself unpersuaded by arguments that existing policies and guidelines are adequate here. Sometimes, one needs a linkable statement that applies directly to the circumstances at hand. By analogy, one could argue that we don't really need ], for example, because adhering to ], ], and ] ought already to keep bad material out of biographies of living people. But in practice, it turned out that having a specialized policy that emphasizes the general ethos of the others while tailoring them to the problem at hand is a good thing. ] (]) 18:27, 5 December 2024 (UTC)
*'''Strong support''' - Making a computer generate believable gibberish for you is a waste of time, and tricking someone else into reading it should be a blockable offense. If we're trying to create an encyclopedia, you cannot automate any part of the ''thinking''. We can automate processes in general, but any attempt at automating the actual discussion or thought-processes should never be allowed. If we allow this, it would waste countless hours of community time dealing with inane discussions, sockpuppetry, and disruption.{{pb
}} Imagine a world where LLMs are allowed and popular - it's a sockpuppeteer's dream scenario - you can run 10 accounts and argue the same points, and the reason why they all sound alike is just merely because they're all LLM users. You could even just spend a few dollars a month and run 20-30 accounts to automatically disrupt wikipedia discussions while you sleep, and if LLM usage was allowed, it would be very hard to stop.{{pb
}} However, I don't have much faith in AI detection tools (partially because it's based on the same underlying flawed technology), and would want any assumption of LLM usage to be based on obvious evidence, not just a score on some website. <small>Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop</small> ] ] 19:15, 5 December 2024 (UTC)
*:I agree with your assessment “Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop” but unfortunately some editors who should ''really'' know better think it’s WaCkY to fill serious discussions with unfunny, distracting “humor”. ] (]) 21:54, 5 December 2024 (UTC)
*::I also concur. "I used the to generate more text" is not a good joke. ] (]) 22:46, 5 December 2024 (UTC)
*'''Strong support''' if you asked a robot to spew out some AI slop to win an argument you’re basically cheating. The only ethical reason to do so is because you can’t speak English well, and the extremely obvious answer to that is “if you can barely speak English why are you editing ''English Misplaced Pages?”'' That’s like a person who doesn’t understand basic physics trying to explain the ] using a chatbot. ] (]) 21:32, 5 December 2024 (UTC)
*:I don't think "cheating" is a relevant issue here. Cheating is a problem if you use a LLM to win and get a job, award, college acceptance etc. that you otherwise wouldn't deserve. But WP discussions aren't a debating-skills contest, they're an attempt to determine the best course of action.
*:So using an AI tool in a WP discussion is not ''cheating'' (though there may be other problems), just as riding a bike instead of walking isn't cheating unless you're trying to win a race. <span style="font-family:cursive">]]</span> 22:36, 5 December 2024 (UTC)
*::Maybe “cheating” isn’t the right word. But I think that a) most AI generated content is garbage (it can polish the turd by making it sound professional, but it’s still a turd underneath) and b) it’s going to be abused by people ]. An AI can pump out text far faster than a human and that can drown out or wear down the opposition if nothing else. ] (]) 08:08, 6 December 2024 (UTC)
*:::Bludgeoning is already against policy. It needs to be more strongly enforced, but it needs to be more strongly enforced uniformly rather than singling out comments that somebody suspects might have had AI-involvement. ] (]) 10:39, 6 December 2024 (UTC)
* '''Support'''; I agree with Remsense and jlwoodwa, among others: I wouldn't make any one AI-detection site the Sole Final Arbiter of whether a comment "counts", but I agree it should be expressly legitimate to discount AI / LLM slop, at the very least to the same extent as closers are already expected to discount other insubstantial or inauthentic comments (like if a sock- or meat-puppet copy-pastes a comment written for them off-wiki, as there was at least one discussion and IIRC ArbCom case about recently). ] (]) 22:10, 5 December 2024 (UTC)
*:You don't need a new policy that does nothing but duplicate a subset of existing policy. At ''most'' what you need is to add a sentence to the existing policy that states "this includes comments written using LLMs", however you'd rightly get a lot of pushback on that because it's completely redundant and frankly goes without saying. ] (]) 23:37, 5 December 2024 (UTC)
*'''Support''' hallucinations are real. We should be taking a harder line against LLM generated participation. I don't think everyone who is doing it knows that they need to stop. ''']'''<span style="border:2px solid #073642;background:rgb(255,156,0);background:linear-gradient(90deg, rgba(255,156,0,1) 0%, rgba(147,0,255,1) 45%, rgba(4,123,134,1) 87%);">]</span> 23:47, 5 December 2024 (UTC)
*'''Comment''' - ] that I imagine we will see more often. I wonder where it fits into this discussion. A user employs ]'s ], search+LLM, to help generate their edit request (without the verbosity bias that is common when people don't tell LLMs how much output they want). ] (]) 03:13, 6 December 2024 (UTC)
*'''Support''' per all above. Discussions are supposed to include the original arguments/positions/statements/etc of editors here, not off-site chatbots. ] ] <span style="color:#C8102E;"><small><sup>(])</sup></small></span> 03:53, 6 December 2024 (UTC)
*:I also find it pretty funny that ChatGPT ''itself'' said it shouldn't be used, as per the premise posted above by EEng. ] ] <span style="color:#C8102E;"><small><sup>(])</sup></small></span> 03:58, 6 December 2024 (UTC)
*::"sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses" - . They give us what we want...apparently. And just like with people, there is position bias, so the order of things can matter. ] (]) 04:26, 6 December 2024 (UTC)
* (Is this where I respond? If not, please move.) '''LLM-generated prose should be discounted.''' Sometimes there will be a discernible point in there; it may even be what the editor meant, lightly brushed up with what ChatGPT thinks is appropriate style. (So I wouldn't say "banned and punishable" in discussions, although we already deprecate machine translations on en.wiki and for article prose, same difference—never worth the risk.) However, LLMs don't think. They can't explain with reference to appropriate policy and guidelines. They may invent stuff, or use the wrong words—at AN recently, an editor accused another of "defaming" and "sacrilege", thus drowning their point that they thought that editor was being too hard on their group by putting their signature to an outrageous personal attack. I consider that an instance of LLM use letting them down. If it's not obvious that it is LLM use, then the question doesn't arise, right? Nobody is arguing for requiring perfect English. That isn't what ] means. English is a global language, and presumably for that reason, many editors on en.wiki are not native speakers, and those that aren't (and those that are!) display a wide range of ability in the language. Gnomes do a lot of fixing of spelling, punctuation and grammar in articles. In practice, we don't have a high bar to entrance in terms of English ability (although I think a lot more could be done to ''explain'' to new editors whose English is obviously non-native what the rule or way of doing things is that they have violated. And some of our best writers are non-native; a point that should be emphasised because we all have a right of anonymity here, many of us use it, and it's rare, in particular, that I know an editor's race. Or even nationality (which may not be the same as where they live.) But what we do here is write in English: both articles and discussions. If someone doesn't have the confidence to write their own remark or !vote, then they shouldn't participate in discussions; I strongly suspect that it is indeed a matter of confidence, of wanting to ensure the English is impeccable. LLMs don't work that way, really. They concoct things like essays based on what others have written. Advice to use them in a context like a Misplaced Pages discussion is bad advice. At best it suggests you let the LLM decide which way to !vote. If you have something to say, say it and if necessary people will ask a question for clarification (or disagree with you). They won't mock your English (I hope! Civility is a basic rule here!) It happens in pretty much every discussion that somebody makes an English error. No biggie. I'll stop there before I make any more typos myself; typing laboriously on my laptop in a healthcare facility, and anyway ] covers this. ] (])
*I dunno about this specifically but I want to chime in to say that I find LLM-generated messages super fucking rude and unhelpful and support efforts to discourage them. – ] <small>(])</small> 08:15, 6 December 2024 (UTC)
*'''Comment''' I think obvious LLM/chatbot text should at least be tagged through an Edit filter for Recent Changes, then RC Patrollers and reviewers can have a look and decide for themselves. ] <sup>(])</sup> <sub>(])</sub> 11:58, 6 December 2024 (UTC)
*:How do you propose that such text be identified by an edit filter? LLM detections tools have high rates of both false positives and false negatives. ] (]) 12:47, 6 December 2024 (UTC)
*::It might become possible once watermarks (like DeepMind's SynthID) are shown to be robust and are adopted. Some places are likely to require it at some point e.g. EU. I guess it will take a while though and might not even happen e.g. I think OpenAI recently decided to not go ahead with their watermark system for some reason. ] (]) 13:17, 6 December 2024 (UTC)
*:::It will still be trivial to bypass the watermarks, or use LLMs that don't implement them. It also (AIUI) does nothing to reduce false positives (which for our usecase are far more damaging than false negatives). ] (]) 13:30, 6 December 2024 (UTC)
*::::Maybe, that seems to be the case with some of the proposals. Others, like SynthID claim high detection rates, maybe because even a small amount of text contains a lot of signals. As for systems that don't implement them, I guess that would be an opportunity to make a rule more nuanced by only allowing use of watermarked output with verbosity limits...not that I support a rule in the first place. People are going to use/collaborate with LLMs. Why wouldn't they? ] (]) 14:38, 6 December 2024 (UTC)
*:::::I don't think watermarks are a suitable thing to take into account. My view is that LLM usage should be a blockable offense on any namespace, but if it ends up being allowed under some circumstances then we at least need mandatory manual disclosures for any usage. Watermarks won't work / aren't obvious enough - we need something like {{t|LLM}} but self-imposed, and not tolerate unmarked usage. ] ] 18:21, 6 December 2024 (UTC)
*::::::They will have to work at some point (e.g. ). ] (]) 06:27, 7 December 2024 (UTC)
*:Good news! {{u|Queen of Hearts}} is already working on that in {{edf|1325}}. ] (]) 16:12, 6 December 2024 (UTC)
*::See also ]. ] (]) 17:32, 6 December 2024 (UTC)
*'''Comment''' As a practical matter, users posting obvious LLM-generated content will typically be in violation of other rules (e.g. disruptive editing, sealioning), in which case their discussion comments absolutely should be ignored, discouraged, discounted, or (in severe cases) hatted. But a smaller group of users (e.g. people using LLMs as a translation tool) may be contributing productively, and we should seek to engage with, rather than discourage, them. So I don't see the need for a separate bright-line policy that risks erasing the need for discernment — in most cases, a friendly reply to the user's first LLM-like post (perhaps mentioning ], which isn't a policy or guideline, but is nevertheless good advice) will be the right approach to work out what's really going on. ] (]) 15:53, 6 December 2024 (UTC)
*:Yeah, this is why I disagree with the BLP analogy above. There's no great risk/emergency to ban the discernment. ] (]) 17:34, 6 December 2024 (UTC)
*:{{small|Those pesky ] are just the worst!}} ] (]) 18:41, 6 December 2024 (UTC)
*:Some translation tools have LLM ''assistance'', but the whole point of ''generative'' models is to create text far beyond what is found in the user's input, and the latter is clearly what this proposal covers. ] (]) 19:01, 6 December 2024 (UTC)
*::That ''might'' be what the proposal ''intends'' to cover, but it is not what the proposal ''actually'' covers. The proposal ''all'' comments that have been generated by LLMs and/or AI, without qualification. ] (]) 01:05, 7 December 2024 (UTC)
*:::70+% here understand the intention matches the language: ''generated by LLMs etc'' means "originated through generative AI tools rather than human thought", not "some kind of AI was involved in any step of the process". Even LLM translation tools don't actually ''create'' meaningful content where there wasn't any before; the generative AI aspect is only in the use of their vast training data to characterize the semantic context of your input in the form of mathematical relationships between tokens in an embedding space, and then match it with the collection of tokens most closely resembling it in the other language. There is, definitionally, a high level of creative constraint in what the translation output is since semantic preservation is required, something that is ''not'' true for text ''generation''. ] (]) 04:01, 7 December 2024 (UTC)
*::::Do you have any evidence for you assertion that 70% of respondents have interpreted the language in the same way as you? Reading the comments associated with the votes suggests that it's closer to 70% of respondents who don't agree with you. Even if you are correct, 30% of people reading a policy indicates the policy is badly worded. ] (]) 08:34, 7 December 2024 (UTC)
*:::::I think @] has summarized the respondent positions sufficiently below. I also think some portion of the opposers understand the proposal perfectly well and are just opposing anything that imposes participation standards. ] (]) 22:54, 7 December 2024 (UTC)
*::::There will be many cases where it is not possible to say whether a piece of text does or does not contain "human thought" by observing the text, even if you know it was generated by an LLM. Statements like "originated through generative AI tools rather than human thought" will miss a large class of use cases, a class that will probably grow over the coming years. People work with LLMs to produce the output they require. It is often an iterative process by necessity because people and models make mistakes. An example of when "...rather than human thought" is not the case is when someone works with an LLM to solve something like a challenging technical problem where neither the person or the model has a satisfactory solution to hand. The context window means that, just like with human collaborators, a user can iterate towards a solution through dialog and testing, exploring the right part of the solution space. Human thought is not absent in these cases, it is present in the output, the result of a collaborative process. In these cases, something "far beyond what is found in the user's input" is the objective, it seems like a legitimate objective, but regardless, it will happen, and we won't be able to see it happening. ] (]) 10:46, 7 December 2024 (UTC)
*:::::Yes, but this proposal is supposed to apply to just the obvious cases and will hopefully discourage good-faith users from using LLMs to create comments wholesale in general. It can be updated as technology progresses. There's also no reason editors using LLMs to organize/validate their arguments, or as search engines for whatever, ''have'' to copy-paste their raw output, which is much more of a problem since it carries a much higher chance of hallucination. That some people who are especially familiar with how to optimize LLM use, or who pay for advanced LLM access, will be able to deceive other editors is not a reason to ''not'' formally proscribe wholesale comment generation. ] (]) 22:27, 7 December 2024 (UTC)
*::::::That's reasonable. I can get behind the idea of handling obvious cases from a noise reduction perspective. But for me, the issue is noise swamping signal in discussions rather than how it was generated. I'm not sure we need a special rule for LLMs, maybe just a better way to implement the existing rules. ] (]) 04:14, 8 December 2024 (UTC)
*'''Support''' ] ] (]) 18:30, 6 December 2024 (UTC)
* '''Comment''': The original question was whether we should discount, ignore, strikethrough, or collapse chatbot-written content. I think there's a very big difference between these options, but most support !voters haven't mentioned which one(s) they support. That might make judging the consensus nearly impossible; as of now, supporters are the clear !majority, but supporters of ''what''? {{--}} <span style="font-family:cursive">]]</span> 19:32, 6 December 2024 (UTC)
*:That means that supporters support the proposal {{tq|that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner}}. Not sure what the problem is here. Supporters support the things listed in the proposal - we don't need a prescribed 100% strict procedure, it just says that supporters would be happy with closers discounting, ignoring or under some circumstances deleting LLM content in discussions. ] ] 19:40, 6 December 2024 (UTC)
*:Doing something? At least the stage could be set for a follow on discussion. ] (]) 19:40, 6 December 2024 (UTC)
*:More people have bolded "support" than other options, but very few of them have even attempted to refute the arguments against (and most that have attempted have done little more than handwaving or directly contradicting themselves), and multiple of those who have bolded "support" do not actually support what has been proposed when you read their comment. It's clear to me there is not going to be a consensus for anything other than "many editors dislike the idea of LLMs" from this discussion. ] (]) 00:58, 7 December 2024 (UTC)
*::Arguing one point doesn't necessarily require having to refute every point the other side makes. I can concede that "some people use LLMs to improve their spelling and grammar" without changing my view overriding view that LLMs empower bad actors, time wasters and those with competence issues, with very little to offer wikipedia in exchange. Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first. ] ] 09:00, 7 December 2024 (UTC)
*:::If you want to completely ignore all the other arguments in opposition that's your choice, but don't expect closers to attach much weight to your opinions. ] (]) 09:05, 7 December 2024 (UTC)
*::::Ok, here's a list of the main opposition reasonings, with individual responses.
*::::'''What about translations?''' - Translations are not up for debate here, the topic here is very clearly generative AI, and attempts to say that this topic covers translations as well is incorrect. No support voters have said the propositions should discount translated text, just oppose voters who are trying to muddy the waters.
*::::'''What about accessibility?''' - This is could be a legitimate argument, but I haven't seen this substantiated anywhere other than handwaving "AI could help people!" arguments, which I would lump into the spelling and grammar argument I responded to above.
*::::'''Detection tools are inaccurate''' - This I very much agree with, and noted in my support and in many others as well. But there is no clause in the actual proposal wording that mandates the use of automated AI detection, and I assume the closer would note that.
*::::'''False positives''' - Any rule can have a potential for false positives, from wp:DUCK to close paraphrasing to NPA. We've just got to as a community become skilled at identifying genuine cases, just like we do for every other rule.
*::::'''LLM content should be taken at face value and see if it violates some other policy''' - hopelessly naive stance, and a massive timesink. Anyone who has had the misfortune of going on X/twitter in the last couple of years should know that AI is not just used as an aid for those who have trouble typing, it is mainly used to and . Anyone who knows how bad the sockpuppetry issue is around CTOPs should be absolutely terrified of when (not if) someone decides to launch a full throated wave of AI bots on Misplaced Pages discussions, because if we have to invididually sanction each one like a human then admins will literally have no time for anything else.
*::::I genuinely cannot comprehend how some people could see how AI is decimating the internet through spam, bots and disinformation and still think for even one second that we should open the door to it. ] ] 10:08, 7 December 2024 (UTC)
*:::::There is no door. This is true for sockpuppetry too in my opinion. There can be a rule that claims there is a door, but it is more like a bead curtain. ] (]) 11:00, 7 December 2024 (UTC)
*:::::The Twitter stuff is not a good comparison here. Spam is already nukable on sight, mass disruptive bot edits are also nukable on sight, and it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions (most of which would be off-topic anyway, i.e., nukable on sight). I'd prefer if people didn't use ChatGPT to formulate their points, but if they're trying to formulate a real point then that isn't disruptive in the same way spam is. ] (]) 02:22, 10 December 2024 (UTC)
*::::::{{tq|it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions}} - by disrupting RFCs and talk page discussions a bad actor could definitely use chatgpt to astroturf. A large proportion of the world uses Misplaced Pages (directly or indirectly) to get information - it would be incredibly valuable thing to manipulate. My other point is that AI disruption bots (like the ones on twitter) would be indistinguishable from individuals using LLMs to "fix" spelling and grammar - by allowing one we make the other incredibly difficult to identify. How can you tell the difference between a bot and someone who just uses chatgpt for every comment? ] ] 09:16, 10 December 2024 (UTC)
*:::::::You can't. That's the point. This is kind of the whole idea of ]. ] (]) 20:22, 13 December 2024 (UTC)
*:::{{tqb|Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first.}}Social anxiety: Say "I" am a person unconfident in my writing. I imagine that when I post my raw language, I embarrass myself, and my credibility vanishes, while in the worst case nobody understands what I mean. As bad confidence is often built up through negative feedback, it's usually meritful or was meritful at some point for someone to seek outside help. ] (]) 23:46, 8 December 2024 (UTC)
*::::While I sympathise with that hypothetical, ] and we shouldn't make decisions that do long-term harm to the project just because a hypothetical user feels emotionally dependent on a high tech spellchecker. I also think that in general wikipedia (myself included) is pretty relaxed about spelling and grammar in talk/WP space. ] ] 18:45, 10 December 2024 (UTC)
*:::::We also shouldn't do long term harm to the project just because a few users are wedded to idea that LLMs are and will always be some sort of existential threat. The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project than LLM-comments that are all either useful, harmless or collapseable/removable/ignorable at present. ] (]) 19:06, 10 December 2024 (UTC)
*::::::{{tq|The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project}} - the same could be said for ]. The reason why its not a big problem for DUCK is because the confidence level is very high. Like I've said in multiple other comments, I don't think "AI detectors" should be trusted, and that the bar for deciding whether something was created via LLM should be very high. I 100% understand your opinion and the reasoning behind it, I just think we have differing views on how well the community at large can identify AI comments. ] ] 09:07, 11 December 2024 (UTC)
*:::::I don't see how allowing shy yet avid users to contribute has done or will do long-term harm. The potential always outweighs rational evaluation of outcomes for those with anxiety, a condition that is not behaviorally disruptive. ] (]) 02:47, 11 December 2024 (UTC)
*::::::I definitely don't want to disallow shy yet avid users! I just don't think having a "using chatgpt to generate comments is allowed" rule is the right solution to that problem, considering the wider consequences. ] ] 08:52, 11 December 2024 (UTC)
*:::::::Did you mean "... disallowed"? If so, I think we weigh-differently accessibility vs the quite low amount of AI trolling. ] (]) 14:10, 11 December 2024 (UTC)
* '''Support''' strikethroughing or collapsing per everyone else. The opposes that mention ESL have my sympathy, but I am not sure how many of them are ESL themselves. Having learnt English as my second language, I have always found it easier to communicate when users are expressing things in their own way, not polished by some AI. I sympathise with the concerns and believe the right solution is to lower our community standards with respect to ] and similar (in terms of ESL communication) without risking hallucinations by AI. ] (]) 02:52, 7 December 2024 (UTC)
* '''Oppose the use of AI detection tools'''. False positive rates for AI-detection are dramatically higher for non-native English speakers. . ~ ] (] • ]) 17:53, 8 December 2024 (UTC)
===Section break 5===
* '''Oppose''' - I'm sympathetic to concerns of abuse through automated mass-commenting, but this policy looks too black-and-white. Contributors may use LLMs for many reasons, including to fix the grammar, to convey their thoughts more clearly, or to adjust the tone for a more constructive discussion. As it stands, this policy may lead to dismissing good-faith AI-assisted comments, as well as false positives, without considering the context. Moreover, while mainstream chatbots are not designed to just mimic the human writing style, there are existing tools that can make AI-generated text more human-like, so this policy does not offer that much protection against maliciously automated contributions. ] (]) 01:12, 9 December 2024 (UTC)
*:'''Oppose''' What @] said is correct, basic AI tools like Grammarly should be allowed (note that grammarly can also change sentences and wording and has generative AI tools) but just blatantly asking ChatGPT to generate a administrator report is different. ] (]) 04:46, 1 January 2025 (UTC)
* '''Oppose''' – Others have cast doubt on the efficacy of tools capable of diagnosing LLM output, and I can't vouch for its being otherwise. If EEng's example of ChatBot output is representative—a lengthy assertion of notability without citing sources—that is something that could well be disregarded whether it came from a bot or not. If used carefully, AI can be useful as an aide-memoire (such as with a spell- or grammar-checker) or as a supplier of more felicitous expression than the editor is naturally capable of (e.g. Google Translate). ] (]) 10:27, 9 December 2024 (UTC)
* '''Comment''' / '''Oppose as written'''. It's not accurate that GPTZero is good at detecting AI-generated content. Citations (slightly out of date but there's little reason to think things have changed from 2023): https://www.aiweirdness.com/writing-like-a-robot/ , https://www.aiweirdness.com/dont-use-ai-detectors-for-anything-important/ . For those too busy to read, a few choice quotes: "the fact that it insisted even one excerpt is not by a human means that it's useless for detecting AI-generated text," and "Not only do AI detectors falsely flag human-written text as AI-written, the way in which they do it is biased" (citing https://arxiv.org/abs/2304.02819 ). Disruptive, worthless content can already be hatted, and I'm not opposed to doing so. Editors should be sharply told to use their own words, and if not already written, an essay saying we'd rather have authentic if grammatically imperfect comments than AI-modulated ones would be helpful to cite at editors who offer up AI slop. But someone merely citing GPTZero is not convincing. GPTZero will almost surely misidentify genuine commentary as AI-generated. So fine with any sort of reminder that worthless content can be hatted, and fine with a reminder not to use ChatGPT for creating Misplaced Pages talk page posts, but not fine with any recommendations of LLM-detectors. ] (]) 20:00, 9 December 2024 (UTC)
*:@], I can't tell if you also oppose the actual proposal, which is to permit hatting/striking obvious LLM-generated comments (using GPTzero is a very minor detail in JSS's background paragraph, not part of the proposal). ] (]) 01:47, 11 December 2024 (UTC)
*:::I support the proposal in so far as disruptive comments can already be hatted and that LLM-generated content is disruptive. I am strongly opposed to giving well-meaning but misguided editors a license to throw everyone's text into an AI-detector and hat the comments that score poorly. I don't think it was ''that'' minor a detail, and to the extent that detail is brought up, it should be as a reminder to use human judgment and ''forbid'' using alleged "AI detectors" instead. ] (]) 03:49, 11 December 2024 (UTC)
* '''Support''' collapsing AI (specifically, ]) comments by behavioral analysis (most actually disruptive cases I've seen are pretty obvious) and not the use of inaccurate tools like ZeroGPT. I thinking hatting with the title "Editors suspect that this comment has been written by a ]" is appropriate. They take up SO much space in a discussion because they are also unnecessarily verbose, and talk on and on but never ever say something that even approaches having substance. Discussions are for human Misplaced Pages editors, we shouldn't have to use to sift through comments someone put 0 effort into and outsourced to a robot that writes using random numbers (that's a major part of how tools like ChatGPT work and maintain variety). If someone needs to use an AI chatbot to communicate because they don't understand English, then they are welcome to contribute to their native language Misplaced Pages, but I don't think they have the right to insist that we at enwiki spend our effort reading comments they but minimal effort into besides opening the ChatGPT website. If really needed, they can write in their native language and use a non-LLM tool like Google Translate. The use of non-LLM tools like Grammarly, Google Translate, etc. I think should still be OK for all editors, as they only work off comments that editors have written themselves. ] <sup>]]</sup> 05:10, 10 December 2024 (UTC)
*:Adding that enforcing people writing things in their own words will actually help EAL (English additional language) editors contribute here. I world with EAL people irl, and even people who have almost native proficiency with human-written content find AI output confusing because it says things in the most confusing, verbose ways using difficult sentence constructions and words. I've seen opposers in this discussion who maybe haven't had experience working with EAL people go "what about EAL people?", but really, I think this change will help them (open to being corrected by someone who is EAL, tho). ] <sup>]]</sup> 05:17, 10 December 2024 (UTC)
*:Also, with regards to oppose comments that discussions are not a vote so closes will ignore AI statements which don't have merit - unedited LLM statements are incredibly verbose and annoying, and clog up the discussion. Imagine multiple paragraphs, each with a heading, but all of which say almost nothing, they're borderline ]y. Giving the power to HAT them will help genuine discussion contributors keep with the flow of human arguments and avoid scaring away potential discussion contributors who are intimidated or don't feel they have the time to read the piles of AI nonsense that fill the discussion. ] <sup>]]</sup> 06:38, 10 December 2024 (UTC)
* '''Support''' (removing) in general. How is this even a question? There is no case-by-case. It is a fundamental misunderstanding of how LLMs work to consider their output reliable without careful review. And which point, the editor could have written it themselves without inherent LLM bias. The point of any discussion is to provide analytical response based on the ''context'', not have some tool regurgitate something from a training set that sounds good. And frankly, it is disrespectuful to make someone read "AI" responses. It is a tool and there is a place and time for it, but not in discussions in an encyclopedia. — <small> ] <b>∣</b> ]</small> 15:41, 10 December 2024 (UTC)
*'''Strong Support'''. I'm very interested in what you (the generic you) have to say about something. I'm not remotely interested in what a computer has to say about something. It provides no value to the discussion and is a waste of time. ] (]) 18:06, 10 December 2024 (UTC)
*:Comments that provide no value to the discussion can already be hatted and ignored regardless of why they provide no value, without any of the false positive or false negatives inherent in this proposal. ] (]) 18:25, 10 December 2024 (UTC)
*::Indeed, and that's fine for one-offs when a discussion goes off the rails or what-have-you. But we also have ] for disruptive behavior, not working collaboratively, etc. I'm suggesting that using an AI to write indicates that you're not here to build the encyclopedia, you're here to have an AI build the encyclopedia. I reiterate my strong support for AI-written content to be removed, struck, collapsed, or hatted and would support further measures even beyond those. ] (]) 21:54, 11 December 2024 (UTC)
*:::There are two sets of people described in your comment: those who use AI and those who are NOTHERE. The two sets overlap, but nowhere near sufficiently to declare that everybody in the former set are also in the latter set. If someone is NOTHERE they already can and should be blocked, regardless of how they evidence that. Being suspected of using AI (note that the proposal does not require proof) is not sufficient justification on its own to declare someone NOTHERE, per the many examples of constructive use of AI already noted in this thread. ] (]) 22:03, 11 December 2024 (UTC)
*::::To reiterate, I don't believe that any use of AI here is constructive, thus using it is evidence of ], and, therefore, the set of people using AI to write is completely circumscribed within the set of people who are NOTHERE. Please note that I am referring to users who use AI-generated writing, not users suspected of using AI-generated writing. I won't be delving into how one determines whether someone is using AI or how accurate it is, as that is, to me, a separate discussion. This is the end of my opinion on the matter. ] (]) 23:26, 11 December 2024 (UTC)
*:::::You are entitled to your opinion of course, but as it is contradicted by the evidence of both multiple constructive uses and of the near-impossibility of reliably detecting LLM-generated text without false positives, I would expect the closer of this discussion to attach almost no weight to it. ] (]) 00:42, 12 December 2024 (UTC)
*:::::I am ESL and use LLMs sometimes because of that. I feel like I don't fit into the NOTHERE category. It seems like you do not understand what they are or how they can be used constructively. ] (]) 01:43, 12 December 2024 (UTC)
*::::::No, I understand. What you're talking about is no different from using Google Translate or asking a native-speaker to translate it. You, a human, came up with something you wanted to convey. You wrote that content in Language A. But you wanted to convey that message that you - a human - wrote, but now in Language B. So you had your human-written content translated to Language B. I have no qualms with this. It's your human-written content, expressed in Language B. My concern is with step 1 (coming up with something you want to convey), not step 2 (translating that content to another language). You write a paragraph for an article but it's in another language and you need the paragraph that you wrote translated? Fine by me. You ask an AI to write a paragraph for an article? Not fine by me. Again, I'm saying that there is no valid use case for AI-written content. ] (]) 15:59, 12 December 2024 (UTC)
*:::::::It seems very likely that there will be valid use cases for AI-written content if the objective is maximizing quality and minimizing errors. Research like demonstrate that there will likely be cases where machines outperform humans in specific Misplaced Pages domains, and soon. But I think that is an entirely different question than potential misuse of LLMs in consensus related discussions. ] (]) 16:25, 12 December 2024 (UTC)
*:::::::But your vote and the proposed above makes not distinction there. Which is the main issue. Also not to be pedantic but every prompted to a LLM is filled out by a human looking to convey a message. Every time someone hits publish on something here it is that person confirming that is what they are saying. So how do we in practice implement what you suggest? Because without a method better than vibes it's worthless. ] (]) 18:53, 12 December 2024 (UTC)
*::::::::The proposal specifies content ''generated'' by LLMs, which has a specific meaning in the context of generative AI. If a prompt itself conveys a meaningful, supported opinion, why not just post that instead? The problem comes when the LLM adds more information than was provided, which is the whole point of generative models. ] (]) 01:52, 13 December 2024 (UTC)
* '''Yes''' in principle. But in practice, LLM detectors are not foolproof, and there are valid reasons to sometimes use an LLM, for example to copyedit. I have used Grammarly before and have even used the Microsoft Editor, and while they aren't powered by LLMs, LLMs are a tool that need to be used appropriately on Misplaced Pages. ] ] 19:55, 10 December 2024 (UTC)
* '''Support'''. Using LLM to reply to editors is lazy and disrespectful of fellow editor's time and brainpower. In the context of AFD, it is particularly egregious since an LLM can't really read the article, read sources, or follow our notability guidelines. {{pb}} By the way. {{tq|gptzero and other such tools are very good at detecting this}}. I don't think this is correct at all. I believe the false positive for AI detectors is quite high. High enough that I would recommend not using AI detectors. –] <small>(])</small> 03:23, 11 December 2024 (UTC)
*'''Question''' @]: Since there appears to be a clear consensus against the AI-detectors part, would you like to strike that from the background? ] (]) 14:10, 11 December 2024 (UTC)
* '''Support'''. AI generated text should be removed outright. If you aren't willing to put the work into doing your own writing then you definitely haven't actually thought deeply about the matter at hand. ]]] 14:16, 11 December 2024 (UTC)
*:This comment is rather ironic given that it's very clear you haven't thought deeply about the matter at hand, because if you had then you'd realise that it's actually a whole lot more complicated than that. ] (]) 14:26, 11 December 2024 (UTC)
*::Thryduulf I don't think this reply is particular helpful, and it comes off as slightly combative. It's also by my count your 24th comment on this RFC. ] ] 19:20, 11 December 2024 (UTC)
*::I recognize that AI paraphrased or edited is not problematic in the same ways as text generated outright by an AI. I only meant to address the core issue at steak, content whose first draft was written by an AI system. ]]] 22:16, 17 December 2024 (UTC)
*'''Oppose''' {{re|Just Step Sideways}} The nomination's 2nd para run through https://www.zerogpt.com/ gives "11.39% AI GPT*":{{pb}}{{tqb|I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this. I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. <mark>If you can't make a coherent argument on your own, you are not competent to be participating in the discussion.</mark> I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner}}{{pb}}The nomination's linked https://gptzero.me/ site previously advertised https://undetectable.ai/ , wherewith how will we deal? Imagine the nomination was at AFD. What should be the response to LLM accusations against the highlighted sentence? ] (]) 17:41, 11 December 2024 (UTC)
* '''Support''' with the caveat that our ability to deal with the issue goes only as far as we can accurately identify the issue (this appears to have been an issue raised across a number of the previous comments, both support and oppose, but I think it bears restating because we're approaching this from a number of different angles and its IMO the most important point regardless of what conclusions you draw from it). ] (]) 19:24, 11 December 2024 (UTC)
*'''Strong support, limited implementation'''. {{tq|1=Misplaced Pages is written by volunteer editors}}, says our front page. This is who ''we'' are, and ''our'' writing is what Misplaced Pages is. It's true that LLM-created text can be difficult to identify, so this may be a bit of a moving target, and we should be conservative in what we remove—but I'm sure at this point we've all run across cases (whether here or elsewhere in our digital lives) where someone copy/pastes some text that includes "Is there anything else I can help you with?" at the end, or other blatant tells. This content should be deleted without hesitation. ] (]) 04:11, 12 December 2024 (UTC)
* '''Support in concept, questions over implementation''' — I concur with {{U|Dronebogus}} that users who rely on LLMs should not edit English Misplaced Pages. It is not a significant barrier for users to use other means of communication, including online translators, rather than artificial intelligence. How can an artificial intelligence tool argue properly? However, I question how this will work in practice without an unacceptable degree of error. <span style="font-family: monospace;">] (he/him)</span> 22:39, 12 December 2024 (UTC)
*:Many, possibly most, online translators use artificial intelligence based on LLMs these days. ] (]) 22:46, 12 December 2024 (UTC)
*::There is a difference between translating words you wrote in one language into English and using an LLM to write a comment for you. <span style="font-family: monospace;">] (he/him)</span> 22:59, 12 December 2024 (UTC)
*:::Neither your comment nor the original proposal make any such distinction. ] (]) 23:34, 12 December 2024 (UTC)
*::::Well since people keep bringing this up as a semi-strawman: no I don’t support banning machine translation, not that I ''encourage'' using it (once again, if you aren’t competent in English please don’t edit here) ] (]) 07:34, 13 December 2024 (UTC)
*:LLMs are incredible at translating, and many online translators already incorporate them, including Google Translate. Accomodating LLMs is an easy way to support the avid not only the ESL but also the avid but shy. It has way more benefits than the unseen-to-me amount of AI trolling that isn't already collapse-on-sight. ] (]) 00:05, 13 December 2024 (UTC)
*::Google Translate uses the same transformer architecture that LLMs are built around, and uses e.g. PaLM to develop more language support (through training that enables zero-shot capabilities) and for larger-scale specialized translation tasks performed through the Google Cloud "" API, but it does not incorporate LLMs into ''translating your everyday text input'', which still relies on NMTs. And even for the API features, the core constraint of ''matching'' input rather than ''generating content'' is still retained (obviously it would be very bad for a translation tool to insert material not found in the original text!). LLMs might be good for translation because they are better at evaluating semantic meaning and detecting context and nuance, but again, the ''generative'' part that is key to this proposal is not present. ] (]) 01:20, 13 December 2024 (UTC)
*:::{{tq|PaLM (Pathways Language Model) is a 540 billion-parameter transformer-based large language model (LLM) developed by Google AI.}} If you meant something about how reschlmunking the outputs of an LLM or using quite similar architecture is not really incorporating the LLM, I believe we would be approaching ] levels of recombination, to which my answer is it is the same ship.{{tqb|obviously it would be very bad for a translation tool to insert material not found in the original text!}} ] (]) 01:29, 13 December 2024 (UTC)
*::::PaLM2 is not used in the consumer app (Google Translate), it's used for research. Google Translate just uses non-generative NMTs to map input to its closes cognate in the target language. ] (]) 01:34, 13 December 2024 (UTC)
*:::::Well, is the NMT really that different enough to not be classified as an LLM? IIRC the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be, and an LLM I asked agreed that NMTs satisfy the definition of a generative LLM, though I think you're the expert here. ] (]) 02:01, 13 December 2024 (UTC)
*::::::Google Translate's NMT hits different enough to speak English much less naturally than ChatGPT 4o. I don't consider it a '''''L'''''LM, because the param count is 380M not 1.8T.
*::::::{{tq|the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be}} No, that def would fit ancient ] tech too. ] (]) 17:50, 13 December 2024 (UTC)
*:::::::Even if you don’t consider it L, I do, and many sources cited by the article do. Since we’ll have such contesting during enforcement, it’s better to find a way that precludes such controversy. ] (]) 20:44, 13 December 2024 (UTC)
*::::::::NMTs, LLMs, and the text-creation functionality of LLMs are fundamentally different in the context of this discussion, which is about content generated through generative AI. NMTs specifically for translation: they are trained on parallel corpora and their output is optimized to match the input as precisely as possible, ''not'' to create novel text. LLMs have different training, including way more massive corpora, and were designed specifically to create novel text. One of the applications of LLMs may be translation (though currently it's too computationally intensive to run them for standard consumer purposes), by virtue of their being very good at determining semantic meaning, but even if/when they do become mainstream translation tools what they'll be used for is still ''not'' generative when it comes to translation output. ] (]) 22:29, 13 December 2024 (UTC)
*:::::::::How will you differentiate between the use of LLM for copyediting and the use of LLM for generation? ] (]) 23:30, 13 December 2024 (UTC)
*::::::::::The proposal is for hatting obvious cases of LLM-generated comments. Someone who just uses an LLM to copyedit will still have written the content themselves and presumably their output would not have the obvious tells of generative AI. ] (]) 23:56, 13 December 2024 (UTC)
*:{{outdent|9}} Not when I tried to use it. Quantitatively, GPTZero went from 15% human to 100% AI for me despite the copyedits only changing 14 words. ] (]) 00:33, 14 December 2024 (UTC)
*::I think there is consensus that GPTZero is not usable, even for obvious cases. ] (]) 00:55, 14 December 2024 (UTC)
*:::Yes, but being as far as 100% means people will also probably think the rewrite ChatGPT-generated. ] (]) 01:18, 14 December 2024 (UTC)
*::::Does it really mean that? All you've demonstrated is that GPTZero has false positives, which is exactly why its use here was discouraged. ] (]) 05:26, 14 December 2024 (UTC)
*:::::My subjective evaluation of what I got copyediting from ChatGPT was that it sounded like ChatGPT. I used GPTZero to get a number. ] (]) 14:18, 14 December 2024 (UTC)
*::::::My guess is that the copyediting went beyond what most people would actually call "copyediting". ] (]) 18:04, 23 December 2024 (UTC)
*:::::::It changed only 14 words across two paragraphs and still retained the same meaning in a way that I would describe it as copyediting. Such levels of change are what those lacking confidence in tone would probably seek anyways. ] (]) 00:15, 24 December 2024 (UTC)
* On one hand, AI slop is a plague on humanity and obvious LLM output should definitely be disregarded when evaluating consensus. On the other hand, I feel like existing policy covers this just fine, and any experienced closer will lend greater weight to actual policy-based arguments, and discount anything that is just parroting jargon. <span class="nowrap">] <sub>]</sub> <sup>(] • ])</sup></span> 23:21, 12 December 2024 (UTC)
*'''Support in principle''', but we cannot rely on any specific tools because none are accurate enough for our needs. Whenever I see a blatant ChatGPT-generated !vote, I ignore it. They're invariably poorly reasoned and based on surface-level concepts rather than anything specific to the issue being discussed. If someone is using AI to create their arguments for them, it means they have no actual argument besides ] and are looking for arguments that support their desired result rather than coming up with a result based on the merits. Also, toasters do not get to have an opinion. <span style="font-family:Papyrus, Courier New">]</span><sup><span style="font-family:Papyrus"><small>'']''</small></span></sup> 05:17, 13 December 2024 (UTC)
*'''Oppose'''. For creating unnecessary drama. First of, the "detector" of the AI bot is not reliable, or at least the reliability of the tool itself is still questionable. If the tool to detect LLM itself is unreliable, how can one reliably point out which one is LLM and which one is not? We got multiple tools that claimed to be able to detect LLM as well. Which one should we trust? Should we be elevating one tool over the others? Have there been any research that showed that the "picked" tool is the most reliable? Second, not all LLMs are dangerous. We shouldn't treat LLM as a virus that will somehow take over the Internet or something. Some editors use LLM to smooth out their grammar and sentences and fix up errors, and there is nothing wrong with that. I understand that banning obvious LLM text per ] are good, but totally banning them is plain wrong. ] ] 22:56, 15 December 2024 (UTC)
*:@], the proposal is to permit editors to collapse/strike ''obvious LLM text'', not to "ban LLM totally". If LLM use is imperceptible, like for tweaking grammar, it's not going to be affected. ] (]) 20:17, 19 December 2024 (UTC)
*'''Support''' with some kind of caveat about not relying on faulty tools or presuming that something is LLM without evidence or admission, based on the following reasons:
*# We have stricter rules around semi-automated editing (rollback, AutoWikiBrowser, etc.) and even stricter rules around fully automated bot editing. These cleanup edits are widely accepted as positive, but there is still the concern about an overwhelming amount of bad edits to wade through and/or fix. A form of that concern is relevant here. Someone could reply to every post in this discussion in just a minute or so without ever reading anything. That's inherently disruptive.
*# Nobody who is voting "oppose" is using an LLM to cast that vote. The LLM comments have been left by those supporting to make a point about how problematic they are for discussions like this. I think this reflects, even among oppose voters, a developing community consensus that LLM comments will be disregarded.
*# If the rule in practice is to disregard LLM comments, not writing that rule down does not stop it from being the rule, consensus, or a community norm. It just makes the rule less obvious and less clear.
*# It's disrespectful for an editor to ask someone to spend their time reading a comment if they couldn't be bothered to spend any time writing it, and therefore a violation of the policy ], "{{tq|treat your fellow editors as respected colleagues with whom you are working on an important project.}}"
* Also, I don't read the proposal as a ban on machine translation in any way. ] (]) 00:01, 18 December 2024 (UTC)
*:@], above @] said their !vote was created by LLM. ] (]) 20:14, 19 December 2024 (UTC)
* I am '''strongly opposed''' to banning or ignoring LLM-made talk page comments ''just'' because they are LLM-made. I'm not a big fan of LLMs at all; they are actually useful only for some certain things, very few of which are directly relevant to contributing to Misplaced Pages in English or in any other language. However, some of those things ''are'' useful for this, at least for some humans, and I don't want to see these humans being kicked out of the English Misplaced Pages. I already witnessed several cases in which people whose first language is not English tried writing talk page responses in the English Misplaced Pages, used an LLM to improve their writing style, and got their responses ignored ''only'' because they used an LLM. In all those cases, I had strong reasons to be certain that they were real humans, that they meant what they wrote, and that they did it all in good faith. Please don't say that anyone who wants to contribute to the English Wikipeida should, in the first place, know English well enough to write a coherent talk page comment without LLM assistance; occasionally, I kind of wish that it was like that myself, but then I recall that the world is more complicated and interesting than that. Uses of LLMs that help the English Misplaced Pages be more inclusive for good-faith people are good. Of course, defining what good faith means is complicated, but using an LLM is not, ''by itself'', a sign of bad faith. --] (]) 04:52, 19 December 2024 (UTC)
*:Those concerned about their English should use translation software rather than an llm. Both might alter the meaning to some extent, but only one will make things up. (It's also not a sure assumption that llm text is coherent talkpage text.) ] (]) 07:44, 19 December 2024 (UTC)
*::@] The dividing line between translation software and LLM is already blurry and will soon disappear. It's also rare that translation software results in coherent talkpage text, ''unless'' it's relying on some (primitive) form of LLM. So if we're going to outlaw LLMs, we would need to outlaw any form of translation software, and possibly any text-to-speech software as well. <span style="font-family:cursive">]]</span> 23:41, 19 December 2024 (UTC)
*:::The distinctions have already been covered above, and no we would not have to. There is an obvious difference between software intended to translate and software intended to generate novel text, and users are likely to continue to treat those differently. ] (]) 02:49, 20 December 2024 (UTC)
*'''Strong support'''. LLM-generated content has no place anywhere on the encyclopedia. ] (]) 10:27, 19 December 2024 (UTC)
*'''Strong oppose''' to the proposal as written. Misplaced Pages already suffers from being ] in a ] ] and a refusal to move with the technological times. Anyone who remembers most Wikipedians' visceral reaction to ] and ] when they were first introduced will observe a striking similarity. Yes, those projects had serious problems, as do LLM-generated comments. But AI is the future, and this attitude of "]" will ultimately lead Misplaced Pages the way of ''Encyclopædia Britannica''. Our discussion needs to be how best to change, not how to avoid to change. <span style="font-family:cursive">]]</span> 23:54, 19 December 2024 (UTC)
*:{{smalldiv|1=The main objection to VE and a major objection to FLOW was the developers' insistence on transforming Wikitext to HTML for editing and then transforming that back to Wikitext. ] (]) 01:31, 20 December 2024 (UTC)}}
*::True. Then, as now, there were many valid objections. But IIRC, there was limited discussion of "Let's figure out a better way to improve", and lots of "Everything is fine; don't change anything, ever." That attitude concerns me. <span style="font-family:cursive">]]</span> 01:52, 20 December 2024 (UTC)
*:I oppose the proposal but I think the comparison to FLOW and VisualEditor is beyond silly. Those things did not exist outside of a MediaWiki context. LLMs are a global issue. ] (]) 17:11, 28 December 2024 (UTC)
*'''Support'''. I'm not even slightly swayed by these "it'll be too hard to figure out" and "mistakes could be made" and "we can't be 100% certain" sorts of arguments. That's true of {{em|everything}} around here, and its why we have an admins-must-earn-a-boatload-of-community-trust system, and a system of review/appeal of decisions they (or of course non-admin closers) make, and a consensus-based decisionmaking system more broadly. {{U|JoelleJay}} has it exactly right: {{tq|having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments.}} And as pointed out by some others, the "it'll hurt non-native-English speakers" nonsense is, well, nonsense; translation is a different and unrelated process (though LLMs can perform it to some extent), of remapping one's {{em|own}} material onto another language.<!-- --><p>I'm also not in any way convinved by the "people poor at writing and other cognitive tasks needs the LLM to help them here" angle, because ] is required. This is work (albeit volunteer work), it is ] a game, a social-media playground, a get-my-ideas-out-there soapbox, or a place to learn how to interact e-socially or pick up remedial writing skills, nor a venue for practicing one's argument techiques. It's an encyclopedia, being built by people who – to be productive contributors instead of a draining burden on the entire community – {{em|must}} have: solid reasoning habits, great judgement (especially in assessing reliability of claims and the sources making them), excellent writing skills of a highly particularized sort, a high level of fluency in this specific language (in multiple registers), and a human-judgement ability to understand our thick web of policies, guidelines, procedures, and often unwritten norms, and how they all interact, in a specific contextual way that may vary greatly by context. None of these is optional. An LLM cannot do any of them adequately (not even write well; their material sticks out like a sore thumb, and after a while you can even tell which LLM produced the material by its habitual but dinstictive crappy approach to simulating human thought and language).</p><!-- --><p>In short, if you {{em|need}} an LLM to give what you think is meaningful input into a decision-making process on Misplaced Pages (much less to generate mainspace content for the public), then you {{em|need}} to go find something else to do, something that fits your skills and abilities. Saying this so plainly will probably upset someone, but so it goes. I have a rep for "not suffering fools lightly" and "being annoying but correct"; I can live with that if it gets the right decisions made and the work advanced. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:49, 22 December 2024 (UTC)</p><p>PS, something that came up more recently than my original post above: If anyone's wondering why some of us are such "AI" skeptics, its because the technology is badly, badly faulty, producing multiple blatant factual errors even in short material, entirely fictive "hallucinations", direct forgery of sourcing, nested chains of error compounded upon error when context isn't gleaned properly, disingenuous attempts to hide that it is lying, and worse. A few days ago, I got ChatGPT 4o to literally {{em|lose its f#*$ing mind}}: I had it generate some short code (very simple one-liner regex) with a really obvious error, so I pointed out the error and gave it documentation that proved it was an error. It conceded the error and even explained what the error was and why it was erroneous, then said how it was going to fix it. And ... proceeded to output the same error again (in just one of three examples, the other two being correct). Fascinated and horrified by this, I tried for over half an hour to get it to produce a correct example, and it was utterly incapable of doing it. It knew the error was an error and what that error was and why, spelled out what the correct approach should be, then repeated the error {{em|every single time}} (always at the first occurrence, or always if the only occurrence). I've captured that session and will be doing a write-up about it. This is much, much worse that a "hallucination", being an abject inability to stop doing what it already knows is absolutely wrong. When people have fears like "If I had a house AI, and it was in control of the bathwater temperature, it might boil my children alive", they are not paranoid or unreasonable. My experiment with ChatGPT proves this conclusively. If the AI can (with trivial effort) be put into a crazy failure-looping state where it knows it's doing or about to do something wrong but insists on doing it anyway – i.e. during its take-an-action phase it completely loses connection to reality, even it's internal reality much less external input telling it "no!" – then we are in grave danger. This is essentially the mental state of a psychopath: "I know I shouldn't grab my neighbor's little daughter and strangle her to death, but I just can't stop myself." <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:42, 28 December 2024 (UTC)</p>
*:The problem with all that is that we ''already'' have a policy that allows the hatting or removal of comments that are actually problematic because of their content (which are the only ones that we should be removing) without regard for whether it was or was not written by LLM. Everything that actually should be removed can be removed already. ] (]) 11:39, 22 December 2024 (UTC)
*::If that's "the problem with all that", then it is not any kind of problem at all. It's entirely normal in our ] material to reiterate a principle defined in one place for contextual application at another, and to extrapolate from a general principle to a more specific application. We do this often to cut through the exact kind of wikilawyering we're facing over this issue: there's not a {{em|specific rule}} against LLM-generated !voting, so the argument is (again and again in this thread) to permit it (unless it's such senseless gibberish that it would be removed anyway even if no LLM were involved). The community clearly doesn't actually want that result (or more accurately, there is not a consensus in favor of it), though this {{em|specific}} proposal's approach to thwarting the "AI"-spamming of our decision-making processes might not be perfect. To me, it's a step in the right direction. If it were implemented this way and some uncommon issue arose with that implementation, then we'd tweak it to address that micro-problem. We must not continue to avoid addressing the macro-problem just because someone can imagine edge cases that might not work out ideally. That, too, is true of all of our P&G and process. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:15, 28 December 2024 (UTC)
*:People who have good reading skills, great judgement, and solid reasoning habits enough to find problems in existing articles don't necessarily have great interpersonal writing/communication skills or the confidence. Meanwhile, for all LLM is bad at, it is very good at diluting everything you say to become dry, dispassionate, and thus inoffensive. ] (]) 15:26, 22 December 2024 (UTC)
*::I doubt that anyone would seriously object to some ultra-hothead running their post through an LLM with a query like "Can you see anything in this that might come off as aggressive or offensive, and suggest a revision that only affects that aspect of the material?" The result might not even be noticeable as LLM-modified. If it doesn't stick out as LLM garbage, there there is no way for this proposal to affect such a post, because no one here is a mind-reader (we cannot magically detect through remote sensing that someone toned their rant down with LLM help). So, this proposal is not broken (at least not with regard to that scenario). That said, the main reason that WP:COMPETENCE was written (and it's one of the essays that, like ] and ], has become "operative" within the community as if a policy or guideline) is the very "don't necessarily have great interpersonal ... skills" issue you mention. That is, lacking those skills to a serious enough degree makes one not competent to work on a collaborative encyclopedia project, and one will eventually be ejected after causing enough disruption. Something we don't need is LLMs masking for a while that someone has this kind of competence failure; it will just drag out the inevitable. By way of analogy: if I were a kleptomaniac and just unable to stop myself from shoplifting, it would not be okay for me to use a device that scrambled stores' surveillance camera footage to make it more likely for me to get away with more shoplifting (and there would certainly be no obligation on the part of the store owner to turn their cameras off, or to take no action if they catch me stealing, just because I tell them I'm a kleptomaniac and my unconstructive behavior isn't something I can manage. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:15, 28 December 2024 (UTC)
*:::People who can't communicate that well often won't attempt to burn others down. I don't think there's any disruption or substantial additional investment in accommodating those who won't burn others down (which I'd say is the majority) by reading their perfectly comprehensible AI-diluted arguments. (Scrambling footage is like erasing the memories of the incident, which I don't think is a good analogue of the issue at hand. I'd say it's more like working with someone who stinks and masks that with perfume.) ] (]) 00:05, 29 December 2024 (UTC)
*:I'm pretty sure most people here understand why there are AI skeptics. I also hate ChatGPT. But there's a difference between my personal opinion of ChatGPT and the fact that someone using ChatGPT to communicate is still communicating. The risk of your house AI hallucinating is that your children get boiled alive. The risk of ChatGPT hallucinating on a talk page is that they make a dumb, disregardable argument, of the kind that humans pump out by the thousands. (Someone linked an example of some AfD delete !votes generated by AI and frankly they're better reasoned than a lot of the stuff humans post.) ] (]) 17:32, 28 December 2024 (UTC)
*:(The bigger issue is people using Misplaced Pages ''as ChatGPT'' -- i.e. posting the prompts, not the responses -- but, like much of what is being discussed here, that is already stuff that can be removed.) ] (]) 17:36, 28 December 2024 (UTC)
*ok, I agree with @], so therefore my vote is '''Support.''' ] (]) 12:41, 25 December 2024 (UTC)
*'''Support'''. Sure I have questions about detection, but I don't think it means we shouldn't have a policy that explicitly states that it should not be used (and can be ignored/hatted if it is). Judging solely based on content (and no wp:bludgeoning, etc.) is unsustainable IMO. It would mean taking every wall of text seriously until it's clear that the ''content'' is unhelpful, and LLMs are very good at churning out plausible-sounding bullshit. It wastes everyone's time. If cognitive impairments or ESL issues make it hard to contribute, try voice-to-text, old-school translation software, or some other aid. LLMs aren't really ''you''.--] (]) 11:27, 23 December 2024 (UTC)
* '''Comment'''. While I agree with the sentiment of the request, I am at a loss to see how we can identify LLM generated comments in a consistent manner that can scale. Yes, it might be easier to identify egregious copy paste of wall of text, but, anything other than that might be hard to detect. Our options are:
:# Robust tooling to detect LLM generated text, with acceptably low levels of false positives. Somewhat similar to what Earwig does for Copyvios. But, someone needs to build it and host it on WMTools or at a similar location.
:# Self certification by editors. Every edit / publish dialogbox should have a checkbox for "Is this text LLM generated" with y/n optionality.
:# Editors playing a vigilante role in reading the text and making a personal call on other editors' text. Obviously this is least preferred.
: These are my starting views. ] (]) 00:37, 24 December 2024 (UTC)
::A couple of days ago, an editor ran a new article through GPTzero, and was told that it was 99.8% likely to be AI-generated. I ran the same revision of the same article through the same tool the next day, and it told me that it was 98.3% likely to be human-written.
::Now we're left scratching our heads: Why the difference? Which answer is correct? ] (]) 04:36, 26 December 2024 (UTC)
*'''Strong oppose''' as it's impossible to enforce. Also LLMs are a valid and useful ] tool. – ] 05:18, 24 December 2024 (UTC)
*'''Bonus suggestion!''': I'm curious what Wikipedians think about this so let's try this. Many of the comments here discuss the impracticality of determining whether a user's comments are AI generated (i.e. gptzero isn't perfect), and many give valid arguments for using LLMs (i.e. ]). If an argument is suspected to be written by LLM, I propose that editors should examine the user. Take a look at their listed contributions, and if they seem to have a habit of using AI, open a discussion on their talk page. If the user has a habit of using AI and doesn't recognize the inherent problems and refuses to change, this can be brought to ] for potential blocks. If (and only if) the person is blocked for using AI, their comments can be ignored. Or just ask ChatGPT to summarize them for you lol ] (]) 06:12, 25 December 2024 (UTC)
*:I think that the general idea here is good: As much as possible, treat each account individually, and handle LLM use as a behavioral problem when it's actually a practical problem (i.e., not when it seems to be accurate and seems to be appropriate). ] (]) 04:38, 26 December 2024 (UTC)
*:Except a substantial portion of the input in this thread is disagreement with the idea that English being someone's second language is an excuse for LLM-generated content at all. Translation of one's own material is an entirely different process (even if often leveraged by LLMs set to a different task than trying to generate what they "think" is new material that will pass as human-authored). I'm skeptical that any of the other things you're accepted as "valid arguments" from the pro-LLM or LLM-accepting side of this debate have consensus as valid, either. But go ahead and spell them out and we'll see. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:30, 28 December 2024 (UTC)
* '''Strong support''' the removal of any obvious, low effort AI-generated post. I recently came across a user such examples. When called out on it and posted a comment saying, amongst other things "''HAHAHAHHAHAHAHAHAHAHHAHAHAHAHAHA. Yes, some of it might be. Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people.''" and "''YOUUUUUUUUUUUUUUUUUUUUUUUUUUUU are assuming bath faith in me.''"
:They were later blocked as a sock evading a global lock.
:Currently it is too easy for trolls to game ] and AI to waste people's time arguing with their bot-generated replies. Using AI to write your posts for you makes it difficult for others to assume good faith. I am ok with obvious exceptions like a non-native speaker using AI to help them articulate their point. ] (]) 21:29, 25 December 2024 (UTC)
* '''Support''' for any and all reasons above. I'd be in favor of entirely banning AI-written text on the platform in articlespace as well. <!-- Template:Unsigned --><small class="autosigned">— Preceding ] comment added by ] (] • ]) 00:05, 27 December 2024 (UTC)</small>
*'''Support''' though with caution, as there are the possibility for false positives. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 00:14, 29 December 2024 (UTC)
*'''Support''' for now. I believe the foundation should be busy ramping up support in this arena of distraction. IMHO, we are in the calibration phase of the use of these models. We don't feed trolls and we shouldn't tutor LLMs. Since assumption of good faith is not suicide pact, we shouldn't rely overmuch for guidance on edge cases. The issues as I see them are attribution (how do I know where your idea has been?), obedience to social norms (I not-here blocked someone recently for brazenly using ChatGPT to lie about using LLMs; the user proceeded to use GPT to post unblock requests), and a vast canyon between the limited human and financial resources of the foundation and the unlimited resources of bad actors with vast sums of money who would like to see Misplaced Pages less able. I have hopes we can get some higher visibility anti-LLM support (like a flag in my mouseover which always reports a percentage, so I know to check). This fire is burning now. It would be unwise to ignore this much longer. ] (]) 16:28, 29 December 2024 (UTC)
*'''Support''' with the clarification that use of AI assistance is not prohibited, as long as its contribution is <<50%. For example, using Grammarly for spell check and grammar/syntax is OK, but using AI to do your homework is not. ] (]) 02:45, 30 December 2024 (UTC)
*:How do you propose to determine whether an AI's contribution is or is not "<<50%"? ] (]) 12:22, 2 January 2025 (UTC)
*'''Support''' a ban on comments that were primarily generated by AI, with such comments to be deleted or struck-through as appropriate, because it's inherently misleading to pass off a chatbot's words as your own. Using ML-based spell-checkers is fine. I've seen some users call ChatGPT an "accessibility tool", but if you're not capable of communicating on English Misplaced Pages without a LLM doing it for you, then I don't think English Misplaced Pages is a good community for you to participate in. <!-- Template:Unsigned --><small class="autosigned">— Preceding ] comment added by ] (] • ]) 21:45, 31 December 2024 (UTC)</small>
*:Just read ], where an editor was indeffed per ] after exclusively using LLMs to edit, even when responding within that very thread. The situation was a clear case of ], which I surely would've cited in my original comment had the page name come to mind. <span class="nowrap">—] (] | ])</span> 04:34, 3 January 2025 (UTC)
*::That they were banned for CIR shows we don't need anything new to deal with disruption specifically caused by people using LLMs. ] (]) 05:29, 3 January 2025 (UTC)
*'''Support''' A popular notion in many, many other discussions is "our most valuable resource is editor time". This applies here more than in most instances - editors cannot be expected to wear themselves out in engaging at length with the results of someone's one-line prompt to an LLM. Where LLM use in articles is destructive of content and source reliability, in discussions it is destructive of editor good faith. If you can't be bothered to put your arguments into intelligible form, don't participate. If your language capacity is lacking to the extent that you have to have a program ''generate'' (as opposed to polish) your stuff, you probably don't have any business participating either. Human detection ability seems quite sufficient for these cases (and once it ceases to, well, we'll deal with that when it becomes an issue). --<span style="font-family:Courier">]</span> <small>(] · ])</small> 12:00, 2 January 2025 (UTC)
*:{{tpq|Human detection ability seems quite sufficient for these case}} these discussions have already proven that human detection is not reliable, with human-generated comments labelled as AI and AI-generated comments labelled as human. Why should we prohibit LLM-generated content that is accurate, relevant and intelligible? We can already ignore/remove content that is none of those things regardless of whether it is LLM-generated or not. ] (]) 12:21, 2 January 2025 (UTC)
:::If you want a pithy in-a-nutshell: personal effort is buy-in in a discussion among equals. If your personal effort in a discussion is an LLM prompt, no editor should be expected to engage with you. --<span style="font-family:Courier">]</span> <small>(] · ])</small> 12:42, 2 January 2025 (UTC)
::::What matters is whether people are engaging with each other constructively and in good faith. Whether one or both parties is using an LLM is completely irrelevant to both aspects. ] (]) 13:29, 2 January 2025 (UTC)
:::::What matters is whether editors wish to engage with an LLM on Misplaced Pages. https://news.mit.edu/2024/large-language-models-dont-behave-like-people-0723 I don't mind interacting with an LLM for my own use, just not on here. ] (]) 13:42, 2 January 2025 (UTC)
::::::Nobody is forcing you to engage with anybody or anything you don't want to engage with, but you do not get to state who other people are allowed to choose to engage with. As long as someone is engaging constructively and in good faith I don't care whether they are human or machine, because (a) I have no reliable way of knowing, and (b) it is literally irrelevant to me. ] (]) 14:14, 2 January 2025 (UTC)
:::::::{{tq|you do not get to state who other people are allowed to choose to engage with}} Strawman, since I didn't do that. Only you are doing that. ] (]) 14:26, 2 January 2025 (UTC)
::::::::Quite the contrary - you are saying that nobody should be allowed to engage with someone using an LLM because you do not want to engage with someone using an LLM. My position is that everybody should be allowed to choose who they want and do not want to engage with for themselves. ] (]) 14:42, 2 January 2025 (UTC)
*'''Support in principle''' - Using entirely AI-generated text in discussion is not a valuable contribution, since ultimately it is not capable of thought, but there should be leniency for those who are simply using AI to improve something they already wrote. ] (]) 14:55, 2 January 2025 (UTC)
*'''Support in principle''' We don't want LLMs opinions. IF and WHEN we do we'll ask for an extension with some AI making an openig analysis of nominations. But we can not, and want not, to excludes cases where some user forms their opinion chating with some AI, as it was brillianttely shoen above, nor we want to exclude anyone lee proficient with the language just "because it looks like a bot". - ] (]) 18:13, 2 January 2025 (UTC)
*'''Support the principle''' per Nabla. ] (]) 21:23, 2 January 2025 (UTC)
*'''Support in principle, ''strongly'' concerned in potential practice''' - I like the idea of removing what is verifiably generated by a LLM. On the other hand, I've read that autistic writers may be more likely to have their (completely non-AI) writing flagged as potential AI use by automated detectors. I think it could be a problem if a rule that's good in principle could start disproportionately affecting some editors (who are not doing the thing) more than others (who are not doing the thing) in practice, whether that come from human (i.e. other editor) bias or automated tools. - ] (]) 18:36, 3 January 2025 (UTC)
*'''Strongly support''' per ChatGPT (EEng) and SMcC; I'm not at all concerned about edit accessibility to non-native speakers; ], after all, is required to contribute to this project. I also oppose any breaking of the line against AI-generated plausible-sounding and -looking slop. We can't have a Misplaced Pages of LLMs talking to LLMs on how to make LLM content for LLM articles. ]<span style="color: #3558b7;"><sup>]</sup>]</span> 21:53, 4 January 2025 (UTC)
*'''Support''' per SMcCandlish. If someone needs to use a LLM to be able to contribute and is unable to convert the output into something that is not obviously AI-generated, then ] likely applies. It'll be impossible to stop minimal usage cases, but having such a rule in place would at least encourage editors to review their output and stop the unhelpful posting off entire ChatGPT essays to discussion spaces. -- ] - <sup>]</sup>/<sub>]</sub> 01:41, 6 January 2025 (UTC)
*'''Strong... opinion''' -- I think the nuance required here in part is the difference between someone using '''any''' automated tool for assistance, versus true bot-like behavior. I believe that unauthorized bot behavior is already prohibited, which should help address the concerns that we mere humans cannot keep up with LLM bots. I agree, we cannot, but I don't see much of that. I am also not inclined to the "if you cannot write, you cannot contribute"... I can imagine 15 years ago some of us might have made the same statement about spelling and grammar; if you cannot spell properly without auto-correct you have no right to edit an encycolopedia. The are significant number of very intentilligent people who are afflicted with things like dyslexia, aspurgers, etc. who have been contributing using various technology tools for assistance. How may of us have Grammarly or similar running on their web browser? And beyond that tools and what they're called will continue to evolve. I am very much against just banning LLM use; largely because it can turn into an unnecessary witch hunt. There are people who will use the tools constructively, and those who will not. I can see some places where it should ''probably'' be banned (such as using a LLM to determine consensus on a discussion that needs closing (AfD, RM, etc)). But even in those areas, I think many of our existing policies and guidelines already address most of the actual concerns we're seeing when it comes to that activity. Cheifly that as long as people are being held accountable for how they use the tools, then who cares what the tool is called in 2000, 2020 or 2040? So I think the course forward is best served by (1) Consider refinement to ] so that we're encapsulating LLM type bot behavior, as well as some sort of threshold on "non-human" capable editing limits (perhaps as part of ]; (2) make a policy or guidelines very clear, bright line, that a user will be treated the same regardless of what tools they use, LLM or otherwise, and that disruptive editing will be handled accordingly. (2a) perhaps a single-warning template reflective of such, to welcome people who appear to be using LLM, and that they are responsible for their adherence to policy and that LLMs tend to get policy wrong. ] ] 02:48, 7 January 2025 (UTC)
*:I like these proposal ideas, and I believe you've hit the nail on the head on the issue. ] (]) 13:14, 7 January 2025 (UTC)
*:+1 ] 15:16, 7 January 2025 (UTC)
*:The proposal is focused on comments that are '''obviously generated''' by LLM, which would not include non-generative AI processes like Grammarly or translation. The whole issue is arguments that were clearly created by a chatbot etc. doing ''its own'' analysis of a discussion and an editor just pasting that output rather than forming the argument themselves, which results in large amounts of text that other editors/closers then have to read and respond to. ] (]) 22:26, 7 January 2025 (UTC)
*::Right, where one doesn't feel like one is talking with ]. ] (]) 22:52, 7 January 2025 (UTC)
*::To be honest, that's my concern. What if something seems obviously generated by LLM but is entirely human-written? What if certain groups of editors are more likely to produce seemingly LLM text that isn't generated by any LLM at all? Is there a way to control for that? How do we consistently enforce this kind of thing without too many false positives ''or'' false negatives?
*::Replying to the top-level opinion at this point: Most autistic people who would have in the past received an Asperger's diagnosis, barring some other reason, would IMO not be more likely to "need" more assistive technology (LLM or otherwise) to contribute to Misplaced Pages articles and discussions than any other user. However, there have been reports that autistic people may be more likely to produce text that is ''falsely'' positive in AI detection tools. See (I had a second example, I thought, except that I've apparently read my last free article on that site (I bet I read said last article when looking up the ''same'' article when I wrote my !vote a few days back, {{facepalm}}). Not gonna link what I can't (quickly) verify!)) <small>(As an aside, I think ] can come across as a bit... charged? Just something to note.)</small>
*::The mention of Data in particular only heightens my concern because--while no one has accused me yet of using LLM when I write--I ''have'' (on other sites, not here) been accused of being a bot before because of the style of writing I adopt at times. What if editor bias disproportionately plays into ''who'' is suspected of LLM use and who isn't? What if imperfections in automated AI detection only serve to cement the bias? - ] (]) 01:25, 8 January 2025 (UTC)
*:::These questions around controlling for false positives and false negatives are not new, we face them all the time already, for example distinguishing vandalism from good faith contributions. We work through them, but they don't mean we don't have a policy on vandalism. ] (]) 01:41, 8 January 2025 (UTC)
*::::Indeed, that's why my original !vote is (in short) "support but concerned". I definitely think I'd support a policy; I'm just raising questions/concerns I think are worth considering in the process of creating such a policy. I think some part of me is just remembering times I've seen bias negatively affect the project in the past and that part of me is coming out here trying to prevent another situation like that by laying the concerns out. I dunno. - ] (]) 03:59, 8 January 2025 (UTC)
*::::It's much easier to distinguish good-faith contributors: see if they change. ] (]) 04:06, 8 January 2025 (UTC)
*::I think Joelle what you're overlooking in that statement is that ''obviously generated'' is something that is going to be short lived, meaning that it will not be very long before the LLM generated content will be far harder to distinguish. Just like how just a year ago any generative image AI would often get the number and/or placement of fingers wrong on a person's hand, in less than a years time that appears to generally be solved. Today the tell tail signs is even if you ask for someone who is left handed, you'll almost always get an image of a right handed person... But that too will go away shortly. I believe it is (scarily) not too far off, when LLMs can determine the prompt is for Misplaced Pages (by way of seeing the wikimarkup or references to normal wiki policies), and among other things, write in the style of experienced editors, perhaps modeled off of some of us in this very discussion. That will be much more difficult to tell, especially when it learns how to ''not be soo overly polite and apologetic''. Beyond that, I believe there are a lot of people successfully and positively using LLMs already on WP. For those reasons, I proffer that we focus on refining the definitions and parameters for general disruptive editing (such as EW, RRR, etc), what a bot edit/activity is, and perhaps a standardized "friendly welcome" and "friendly notice" for those suspected of using LLMs, and reinforce that the tool matters less than the behavior. I think the analogy I'm going for is that of how we handle socks -- it is not against policy to have multiple accounts, however, when it is disruptive, it is blatantly prohibited. But the signs and symptoms of socks is really what we care about. ] ] 05:02, 8 January 2025 (UTC)
*:::Something can be prohibited even if it is or will be difficult to identify it. Just because we can anticipate AI-generated slop becoming harder to detect doesn't mean it's not still disruptive or that we shouldn't be able to strike it when it is obvious. ] (]) 23:41, 9 January 2025 (UTC)
*'''Strong support''' for striking AI-generated comments. Detection of course will be up to admin discretion, but so is things like incivility and personal attacks; while short snippets of AI generated text are hard to detect, lengthy paragraphs are quite easy to eyeball, and from my experience that's the area where it's most likely to come up and most immediately disruptive. <small> ] (]) (it/she) </small> 22:25, 9 January 2025 (UTC)
*'''Support''' {{TQ|for striking AI-generated comments. Detection of course will be up to admin discretion}} as are other behavioural preoblems. Having read most of the discussion, and having been astonished by the 'individuality' of some machine-generated content, nonetheless, while detection may be less-than-foolproof, I still think we should make the point that such content isn't acceptable. It should be within our capacity to make the distinction between 'machine-generated' content and the use of software to correct grammar or to translate, neither of which should be directly outlawed.] (]) 07:18, 10 January 2025 (UTC)
*:But ''why'' should such content be deemed unacceptbale when there are no problems with it? When there are problems with it, it can and should be dealt with in the same way that those problems are dealt with when written by humans. ] (]) 18:25, 10 January 2025 (UTC)
=== Request for closure ===
*] (see discussion on talk page)
IMHO, since we're over 30 days and the argument consensus seems lopsided, the community would do well to close this rapidly (as opposed to waiting for additional comments). ] (]) 21:04, 2 January 2025 (UTC)
*] (see discussion on talk page)
*] (see discussion on talk page)
*]
*] (Note that ] is a redirect to said article)
*] (First sentence of the article is "Several groups have '''alleged''' <nowiki></nowiki> that there have been instances of '''] by ]'''")
*]
*]
*]
*]
*]
etc.
:Sure it looks lopsided if you only read what has been bolded. When you look beyond at what those bolding support are actually supporting it's not at all clear there is a consensus. Then when you actually look at the arguments made it seems that there is not actually a consensus for anything other more than "some users vocally dislike AI". ] (]) 21:59, 2 January 2025 (UTC)
Also, consider these articles:
::If that's so, I'm sure the closer will figure it out. ] (]) 22:14, 2 January 2025 (UTC)
:::I was merely pointing out that BusterD's stated reason for calling for closure now is incorrect. That doesn't mean closing now would necessarily be wrong, just that overwhelming consensus is not a reason for it. ] (]) 22:25, 2 January 2025 (UTC)
::::As a sysop, reacting to LLM-related abuse is virtually all I've done in the last week or so. We have a pressing need for some help from the community, and while I'm open to discussion on this, it's unreasonable to expect humans to keep up with bot-like behavior. I've made my argument above, and I'll not disagree further here. ] (]) 00:08, 3 January 2025 (UTC)
::Many on the “support” side are also supporting with conditions instead of an unconditional support. For instance, many have suggested that LLM that supported grammars are okay.
::The closer must also take it into account. ] ] 11:02, 3 January 2025 (UTC)
* There are multiple breaks and 391 comments now. At this scale, it becomes difficult for a human to digest and summarise it all. AI technology seems well suited to this and so asked Gemini again "Please summarise the consensus of the following RFC:" giving it all the discussion above. Its response was much as before:
So I was wondering, what is the current status of these articles? I don't think it makes sense for some articles to have "allegations" in the title, while others don't. I think either they all should, or they all shouldn't. Thoughts? --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 20:20, 15 March 2007 (UTC)
{{tqb|
:How does ''Holocaust'' fit into your list? --] 20:38, 15 March 2007 (UTC)
The RFC on LLM/chatbot comments in discussions is contentious, with a significant number of editors on both sides of the issue.
::It fits because the Holocaust is '''alleged''' to have happened. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 20:43, 15 March 2007 (UTC)
:::It's not "alleged" to have happened, it '''did''' happen. ] applies here, as I explain below. ] (] | ]) 20:47, 15 March 2007 (UTC)
::::According to the definition of alleged, it has been alleged to happen. There is a considerable minority of the world which do not believe the holocaust occured. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 20:53, 15 March 2007 (UTC)
:::::Speaking frankly here, I think this was a productive discussion until you made your last point. Obviously there are events that are universally acknowledged by scholars as real and should be treated as such (e.g. the Holocaust) and there are interpretations of historical events (e.g. most of the items of the first list) that are inherently allegations. We need to have a discussion about "criticism of x" and "allegations of x" articles, but if we can't distinguish between things that are certainly true and things that are certainly alleged we'll end up with either "Allegations that the Earth is Flat" or "Controlled Demolition of the World Trade Center". ] 22:12, 15 March 2007 (UTC)
::::::You say "certainly true". WHO decides whether something is certainly true? Sources? Misplaced Pages editors? "Certainly true" is something which is contestable in and of itself. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 16:24, 16 March 2007 (UTC)
:] is critical here. "Allegations" is perfectly acceptable in article titles where the article exists to document an unverifiable, albeit possibly noteworthy, belief. An example of this would be ]. The existence of "Israeli apartheid" apartheid at all is itself quite questionable, but the question being posed by many on the political far left and political far right is a valid subject for Misplaced Pages to document. The ideas themselves are unverifiable and thus cannot be accepted as fact within Misplaced Pages, but the argument can certainly be made that the allegations are noteworthy enough to justify an article about the allegations themselves. Conversely, ], ] and ] are not allegations, they are historical (and in the case of the former two, also present) realities. Thus, per ], they can be considered fact.
:I'd argue that the "State terrorism" articles ought to be moved to "allegations of..." but beyond that, it looks good the way it is now.
:The subject of the article is coalesced in its title; "Allegations" articles document the allegations themselves, whereas non-"allegations" articles document facts. ] (] | ]) 20:46, 15 March 2007 (UTC)
'''Support'''
I don't understand what you mean by "unverifiable". What is "unverifiable" about Israeli apartheid? For some people, it is considered a fact. Opposite goes for Holocaust. Some people don't consider the holocaust of fact. I think these selective titles may be an example of ] (]) --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 20:51, 15 March 2007 (UTC)
:It fails ] and is therefore '''unverifiable''' per Misplaced Pages standards and policies. The criteria for what makes information verifiable for the purposes of Misplaced Pages is clear and remarkably simple. Remember that ]. I have seen no exceptional sources suggesting "Israeli apartheid" exists and therefore it fails ]. Sorry. Systemic bias isn't an issue here, it's Misplaced Pages's content policies that you have a problem with. ] (] | ]) 20:57, 15 March 2007 (UTC)
::Exceptional according to who's definition? I could say "I have seen no exceptional sources suggesting that "holocaust" exists and therefore it fails ]". --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:01, 15 March 2007 (UTC)
:::I definitely do ''not'' want to start titling articles like ] with the words "allegations of" before it. To me, "allegations" a term that should be reserved for very specific legal instances. In the case of "Israeli apartheid", it's a descriptive term that's in use in different political circles. Those who use it are not ''alleging'' that Israel is an apartheid state, they are ''insisting'' it is. That term and its associated debate deserve representation in an article titled after the concept itself. The controversy can be discussed in the article, much as it is in ]. ]
:::Tiamut, I must say that was my point in bringing up ]. Thanks for putting it in better words than I have. I also would NOT like to see ]. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:06, 15 March 2007 (UTC)
:::Note how ] doesn't even redirect to ]. I just realized that now. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:07, 15 March 2007 (UTC)
:::Nor does ] exist. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:09, 15 March 2007 (UTC)
:::An "exceptional" source is defined according to Misplaced Pages ]. The applications policy are subjective, but the fact is nonetheless they are subjective of consensus more than they are subjective of any individual editor. ] (] | ]) 21:11, 15 March 2007 (UTC)
::::That's exactly my point. The consensus is subject to systematic bias. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:16, 15 March 2007 (UTC)
:::::So what are you suggesting? Destroying ] and ] because they don't allow for the views of a political fringe to be accepted as fact in Misplaced Pages articles? I'm sorry, but no one will go for that. ] (] | ]) 21:19, 15 March 2007 (UTC)
::::::I find it extremely offensive that you consider Israeli apartheid as fringe; notable scholars such as ] have spoken of it. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:45, 15 March 2007 (UTC)
:::::::Also, look at ]. It has the apollo moon hoax, creation science, and the paul is dead hoax as examples. Are you seriously suggesting that the discrimination towards Palestinians in the occupied territories is equivalent to those nonsense theories? --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:51, 15 March 2007 (UTC)
::::::::Official discrimination by the Israeli government with the intent of wiping out the Palestinian population over a long period of time so that the Jews can have all of Israel as God intended, then they will expand their colonial empire from the Nile to the Euphrates as the Bible says and destroy all who stand in their way? Yes, I am saying that argument is as credible those nonsense theories. Sorry if I sound condescending, but if you want something treated as fact in Misplaced Pages it '''must''' conform with ] and not fall into the category of ]. If you don't like Misplaced Pages's policies, you have two choices:
::::::::#Don't edit. There's no mandate from god or from your government (wherever that may be) compelling you to edit Misplaced Pages.
::::::::#Propose changes to policy. If you think policies get in the way of Misplaced Pages being successful and accurate, propose changes to them. Policies are not implicitly "perfect", but they're all we have at the moment. If you have a better approach or a better way, propose it and see if it gains consensus. Either way, if you want to edit you have to follow the policies that do have consensus.
::::::::Editting Misplaced Pages is a privilege, not a right. Whether or not you follow policy in your editting is the prime criterion for determining whether or not you deserve that privilege. Just because it is given by default does not mean you are owed it; and if you don't like our policies, and decide that you don't want to follow them while editting, it may be taken away. ] (] | ]) 14:09, 16 March 2007 (UTC)
:::::::::Telling me "don't edit" is inane. Please don't be a total ] and tell me to go away. How would you like it if I told you "don't edit". Your belief that ] is ] is just that; a belief. Also, last time I checked, this is the village pump regarding policy, so instead of saying "follow policy", why don't we ''discuss'' the policies instead? That's the whole fucking point of even bringing this up.
:::::::::Also, I don't like your condescending attitude (as evidenced on this page) towards me. Please read ]. Thanks. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 16:30, 16 March 2007 (UTC)
Even ] should not have "allegations" in the title. It's superfluous, non-neutral and unprofessional. We should write in an objective style without implying a point-of-view. — ] 21:09, 15 March 2007 (UTC)
*Roughly speaking, if the subject of the article is ''just'' the allegations, then it may be appropriate to use that in the title - realistically, ] should be a subarticle of ] - where the parent article explains what it is, while the daughter article talks about who's been accused of it, why they've been accused, how they've responded, et cetera. Generically, you'd only split off the daughter if the parent is too big. Labelling '''everything''' with qualifiers like ''allegations'' because the subject isn't completely agreed upon is dumb, because '''no''' subject is completely agreed upon. Would anyone take the encyclopaedia seriously if we had an article called ] with ] as a redirect to it? And yet generically putting ''allegations of'' in the title of contraversial articles will lead to that sort of thing - if you dig, you'll see ''every'' article is contraversial - ], ] and so on ... ] 21:10, 15 March 2007 (UTC)
*Having reviewed it, I see ] is probably well titled - it just talks about who makes the allegations and why, it doesn't talk about the Israeli apartheid hardly at all. ] 21:13, 15 March 2007 (UTC)
**Indeed, a huge amount of the article is devoted to the allegations. ]<sup><small><font color="DarkGreen">]</font></small></sup> 21:14, 15 March 2007 (UTC)
***So Wily, do you think it is permissible to separate ] from ]? And also, should then, conspiracy theorists be allowed ] (the content could be merged from ]) That's even more interesting of a title which raises questions. Can we have an ] article as well? --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:19, 15 March 2007 (UTC)
****I don't know enough about the subject to say whether ] would place the article at ] or like ] or whatever. Generically, if ] got too long, you might need to spin out ] - although again, I'm not sure this is the preferred term per ]. Maybe it is. I think I understand the generic issue here because I've seen it come up in other places a few times, but I don't know enough about Israeli politics to make off the cuff specific statements. ] 21:28, 15 March 2007 (UTC)
****Of the above examples, ] seems like it shouldn't have allegations at the end, for instance. ] 21:30, 15 March 2007 (UTC)
***Going even further with this point, there's even ]. Can we have ] as well? --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:20, 15 March 2007 (UTC)
****If you can't differentiate between historical fact and political rhetoric, then there's hardly a point in responding. The Holocaust was a terrible historical event. "Israeli apartheid" is a political epithet. Please try to use less egregiously offensive and, frankly, silly arguments in the future. Thanks. ]<sup><small><font color="DarkGreen">]</font></small></sup> 21:21, 15 March 2007 (UTC)
::::By making an article about a subject, we are making an implicit claim that it exists, and that claim must pass the acid test of ]. '''If it cannot pass that acid test, it cannot be on Misplaced Pages'''. "Israeli apartheid" cannot be verified to exist, and therefore an article suggesting it does has no place here. We can, however, discuss the allegations made by some that it does exist, which is what we do. ] (] | ]) 21:23, 15 March 2007 (UTC)
:::::I completely disagree with your "implicit claim that it exists". We have articles on ], ], etc. etc. and not ], ], etc. etc. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:28, 15 March 2007 (UTC)
::::::The subject of an article could exist in fiction or in popular thought--The only thing that matters here is that it can be verified that it exists therein. I can verify, by checking the first ] film, that there is indeed a character called ]. I cannot verify, however, that "Israeli apartheid" exists in any world, real or fictional. Remember, ]. ] (] | ]) 21:36, 15 March 2007 (UTC)
:::::::Israel apartheid DOES exist in popular thought. Many notable scholars have used the term. Also, just because it's not popular ''where you live'' doesn't mean that it isn't popular in other places. Again, an example of ].--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:41, 15 March 2007 (UTC)
*****"If you can't differentiate between historical fact and political rhetoric, then there's hardly a point in responding. The Israeli apartheid is a terrible historical event. "The Holocaust" is a political epithet. Please try to use less egregiously offensive and, frankly, silly arguments in the future. Thanks."--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:25, 15 March 2007 (UTC)
Many editors support the proposal to discount or remove LLM-generated comments in discussions. Their arguments include:
So...are you proposing a page move or what? If you are, just make your proposal at ] and be done with it. The discussion here seems more like soapboxing. --] 21:30, 15 March 2007 (UTC)
::I'm not proposing anything, besides '''consistency'''. I don't want to swarm ] with several hundred pages with "allegations" in them. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:38, 15 March 2007 (UTC)
:::"Consistency" isn't really something that can be proposed as a blanket rule of all articles. "Allegations" is appropriate when the topic dictates it, there's no reason all or none should have it. What are you hoping to accomplish, getting the word removed from articles that have it, or adding it to others? --] 21:42, 15 March 2007 (UTC)
::::As I said, either they all have "Allegations of" in their titles, or none of them do (except in legal uses of the term). Either way is fine with me. (but admittedly with a bias towards those words being removed). --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:47, 15 March 2007 (UTC)
:::::Even if you could somehow define "they all" whatever that is (All articles? All articles anyone disputes?), it's never gonna happen. You're tilting at a windmill here (or at least making your stink somewhere trafficked enough to get your ranting read by a few people). Nothing to see here folks, let's stop feeding the troll. --] 21:51, 15 March 2007 (UTC)
::::::Any article that has <s>]</s> ] disputes should have "Allegations of..." in the title heading. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:53, 15 March 2007 (UTC)
:::::::Any article that has ] disputes should be brought to ], and then the matter should be settled. ] 21:58, 15 March 2007 (UTC)
::::::::My mistake. Didn't mean to have the "WP" showing.--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 22:03, 15 March 2007 (UTC)
::::::Also, don't be a ] by accusing me of being a troll. I have been on Misplaced Pages for quite a while now, and have no history of blocks. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 21:55, 15 March 2007 (UTC)
I do not know where this is headed. but it seems to me that there are very clear cases where the word "allegation" can be used. Leave these to be discussed in the specific articles. ] <small>]</small> 21:34, 15 March 2007 (UTC)
Here's how I think we should make the distinction between allegation and a fact.
*If the event/condition/issue is debated by '''reliable''' (preferably scholarly) sources, then it should be an "allegation" or "controversy".
*But if the event is disputed only by wiki users, on unreliable sources, then wikipedia considers it as fact, but gives all POVs due weight.
What do you gusy think about that?] 22:00, 15 March 2007 (UTC)
**No, if the article discusses ] it should be named ] - if it discusses allegations about X, who makes those allegations and why, they history of doing this, then ] should be used. ], for instance, should '''not''' give a history of the development of Rienmann sums - ] or ] should do that. Meawhile, an article about how ] claims calculus doesn't exist because otherwise he won't meet course requirements at the ] that results in a lot of press coverage might reasonably be titled ]. ] 22:06, 15 March 2007 (UTC)
Wily, that sounds about right. But look at the ] article, which is filled with allegations that Islam is antisemitic. What do you think of moving it to ]?--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 22:09, 15 March 2007 (UTC)
* LLMs do not have original thoughts or arguments and therefore do not contribute meaningfully to discussions.
**I think you're on to something, but don't know if I follow your point on "But if the event is disputed only by wiki users, on unreliable sources, then wikipedia considers it as fact" . Can you elaborate? ] 22:08, 15 March 2007 (UTC)
* LLM-generated comments can be disruptive, wasting editors' time and derailing discussions.
***That part is right, but the first point isn't. The article should only ] if it '''ignores''' the subject and only talks about the debate about whether or not the thing exists. ] should '''not''' have the population of North America - that's rightly placed in ], but the debate about whether Columbus was in a new land or Japan might reasonable be titled ]. ] 22:15, 15 March 2007 (UTC)
* LLMs can be used by bad-faith actors to manipulate consensus or spread misinformation.
****Alright, I think I understand your view now. I'm sorry if I come off as condescending by asking too many questions. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 22:21, 15 March 2007 (UTC)
*Editors should be encouraged to participate in discussions using their own words and thoughts.
*****Not at all - better to ask too many questions and understand each other better than necessary than the reverse. ] 22:23, 15 March 2007 (UTC)
'''Oppose'''
(Resetting indent). There's an important distinction here. At least 90% of the facts that give rise to the idea of apartheid are not under dispute - characterizing it as "apartheid" is an ''interpretation'' that by its very nature is subjective. The Holocaust is a proper name for a series of specific events that are accepted by 99.99% of anyone who calls himself/herself a historian. (Oh, and Noam Chomsky quite clearly holds fringe positions, and isn't even a historian, nor - as it turns out - such a great linguist). --] 00:29, 16 March 2007 (UTC)
*Hey, just because Chompsky is terrible at a lot of things doesn't mean he's a bad linguist - the reason people listen to him when he hasn't a clue what he's talking about is ''because'' he's such a good linguist. Anyways, I sort of agree - realistically, ] should redirect to ] or whatever, not ], which seems to be the right article at the right place. ] 00:44, 16 March 2007 (UTC)
Other editors oppose the proposal, arguing that:
I've long believed that we should avoid using the word "allegations" in article titles. There will obviously be the need for some exceptions (eg. the 1993 Michael Jackson article), but the word is too easly co-opted for political ends.
* LLMs can be useful tools for editors who have difficulty expressing themselves in English, such as non-native speakers or those with disabilities.
The ] title is a bad compromise, and was chosen during highly politicized negotiations last summer. At the time of the article's creation, the concept was relatively marginal. Since then, it has been referenced by a former American president, a United Nations report, and countless journalists. And yet, the "allegations" title has been retained, due to ongoing political divisions on the page itself.
* LLM-generated comments should be evaluated on their merits, not their origin.
* Detection of LLM-generated comments is unreliable and could lead to false positives.
* A ban on LLM-generated comments could discourage participation from editors who rely on these tools.
'''Additional points'''
It may be noted, by way of contrast, that the disputed concept of ] is not referred to as ], notwithstanding similar objections that have been raised around the concept's viability. ] 03:54, 16 March 2007 (UTC)
* There is disagreement about whether machine translation should be considered LLM-generated content.
CJCurrie, that's a good point. I've added ] to the list uptop. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 04:07, 16 March 2007 (UTC)
* Some editors believe that LLMs could be used constructively in discussions, for example, to summarize arguments or provide alternative perspectives.
* Others are concerned about the potential for LLMs to be used maliciously, for example, to flood discussions with irrelevant comments or to impersonate other editors.
'''Overall'''
: Categorizing the Holocaust as an "allegation" undermined your own cause. Speaking of which, this whole proposal is an attempt to make a ]. ←] <sup>]]</sup> 10:00, 16 March 2007 (UTC)
There is no clear consensus on whether to ban or allow LLM-generated comments in discussions. The discussion highlights the challenges of balancing the potential benefits and risks of using LLMs in a collaborative environment like Misplaced Pages.
::Again, important distinction here. The term "New Antisemitism" doesn't attribute antisemitism to a particular group, or entity. If the title had been ] (and I'm not claiming he's antisemitic), the comparison would have been apt. --] 10:40, 16 March 2007 (UTC)
}}
::Don't attack the user, who is not (at least here) violating ] - he's trying to make a good point in a constructive, nondisruptive way. There '''is''' an inconsistancy that comes from editors who try to apply ] without having read it. ] 13:16, 16 March 2007 (UTC)
]🐉(]) 21:58, 10 January 2025 (UTC)
That was a good answer but I wanted to get a rough headcount and so asked a supplementary question, "What was the count of the number of support and opposing votes in the discussion?" The answer was:
:::Getting away from what is by definition a POV argument... let's look at this with complete dispassion: In naming articles on Scientific topics, we do not add "Allegations of..." in front of theories held to be factual by mainstream consensus. We should do the same for historical events (or theories) held to be factual by mainstream consensus. Since the vast majority of historians hold that the holocaust did in fact occur, we should not lable it as an "Allegations of..." article. Now, there might be some argument that the opposing view could be an "Allegations" article (ie "Allegations that the Holocaust did not happen")... except that such an article already exists in a much more NPOV manner as ].
{{tqb|
::::In fact, that's why I tried to talk about topics where ] sound funny. But I will say on scientific topics, we don't use ] for non-mainstream stuff either, or even false stuff. ] is not ], ] is not ], ] is not at ] and so on ... ] 15:22, 16 March 2007 (UTC)
Unfortunately, a precise count of support vs oppose votes in that discussion is difficult to determine definitively for a few reasons:
:::I do think we need to think about the propriety of having any "Allegations of" articles... so many of them are thinly veiled POV forks... but that is a different issue. ] 13:36, 16 March 2007 (UTC)
* '''Some votes are unclear''': Several editors express nuanced positions or change their vote during the discussion.
Blueboar, I understand your concerns. But what about science which has mainstream consensus among scientists, but not among the general populace? I think it would be incredibly silly and stupid to have an ] article. As gracenotes said, I think that if there is relevant, sourced, notable dispute of a subject, then the article should not allege it as a fact. For instance the holocaust is considered fact by the vast majority of historians. But there is a notable minority which disagree with the extent of the holocaust. But that does not mean that the ] article should be moved to ]. And the holocaust itself is such a controversial subject that a move to "Allegations..." would be offensive. And that is my point with the Israeli apartheid article. Most historians agree that Israel has isolated and separated the Palestinians in the occupied territories. But there is a notable minority (mostly from the United States and Israel) that claim there is no persecution of Palestinians. But moving the article (as it currently stands) to "Allegations..." is offensive. As user ] earlier above said: ''"Those who use it are not alleging that Israel is an apartheid state, they are insisting it is. That term and its associated debate deserve representation in an article titled after the concept itself."'' --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 14:12, 16 March 2007 (UTC)
* '''"Strong" votes aren't quantified''': While many editors use "Strong support" or "Strong oppose", these don't carry extra weight in a simple tally.
:Those who use the phrase are still making allegations, regardless of whether or not they believe them to be true. ]<sup><small><font color="DarkGreen">]</font></small></sup> 14:56, 16 March 2007 (UTC)
* '''Focus shifts''': The initial focus on AI-generated comments broadens to include AI-assistance, making some votes less clear-cut.
Also, I find the ''allegation'' that I am violating ] to be entirely self-defeating. The whole point of the Village pump is to discuss issues BEFORE doing something major. If I had went and move all those articles to "Allegations of..." (or vice versa), that would have been a ].--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 14:15, 16 March 2007 (UTC)
::"Most historians agree that Israel has isolated and separated the Palestinians in the occupied territories."
::The article isn't titled "allegations that Israel has isolated the Palestinians", the article is titled "allegations of Israeli apartheid". Most historians do *not* agree that this isolation/separation constitutes apartheid. ] 19:20, 23 March 2007 (UTC)
However, based on a rough manual count:
I've found this: ]. Added to top.--<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 14:29, 16 March 2007 (UTC)
* '''Support''': Around 60-70 votes clearly favor discounting or removing AI-generated comments.
* '''Oppose''': Roughly 30-40 votes lean against the proposal, with varying degrees of opposition.
:You forgot ]. I added it for you. ]<sup><small><font color="DarkGreen">]</font></small></sup> 14:56, 16 March 2007 (UTC)
'''Important Note''': This is an approximation. The actual consensus in such discussions is determined by the closer, who weighs the arguments' quality and policy relevance, not just the number of votes.
Thanks. If you find anymore, feel free to add them. --<font color="red">]</font><font color="green">]</font><font color="pink">]</font><font color="blue">]</font> 14:59, 16 March 2007 (UTC)
}}
This seems to be another good answer – better than we get from most human closes. I made a rough manual count to confirm that the numbers given are reasonable ballpark figures. And it seems to have an impressive grasp of nuance – noticing that several editors were qualifying their votes as strong/weak and that some editors changed their vote. ]🐉(]) 22:02, 10 January 2025 (UTC)
The article ] is, strictly speaking, about the allegations rather than the actuality of any discrimination or colonialism which would be better served by an article entitled something else. At least, that was the reason behind the writing of the article by my understanding. That isn't even considering the compromises that reaching that title entailed. ] is about the neologism, ] unfortunately conflates a neologism with a real phenomenon along with allegations of the phenomenon, and ] is similar. --] 20:21, 16 March 2007 (UTC)
:These feel (from my memory of when I skimmed over the discussion several days ago before my original !vote/comment) like they might be leaving out some relevant points that came up. (Unfortunately I can't quantify that without taking a look which I don't have time to do right now (other than the fact my own concerns didn't make it into the summary, which... fair, I guess, considering I was the only one who raised that specific issue).) <small>(I'm also very surprised it came up with something coherent as well as on topic, but that just has more to do with the fact Gemini (or at least whatever AI summarizes Google searches) told me extremely recently that I could get to Alaska by car without a passport if I drove through the ocean. Not took a ferry but drove... through the water... in a car.)</small> - ] (]) 07:02, 11 January 2025 (UTC)
::Your !vote was a qualified support with concern about false positives affecting editors such as the autistic. That's then a nuanced, both-ways vote and the Gemini summary seems to capture that reasonably well. ]🐉(]) 09:43, 11 January 2025 (UTC)
:::My vote was mentioned purely because it was the only specific thing I could bring to mind quickly that hadn't ended up in the AI summary. I think Thryduulf's take about what it doesn't make clear more closely matches what I think I was actually feeling about the summary (that it doesn't make clear the wide breadth of what the support !votes are actually saying). - ] (]) 19:08, 11 January 2025 (UTC)
:On the whole that summary matches my impression of discussion, with the exception that it doesn't make it clear that not everyone expressing support is supporting the same thing. ] (]) 14:38, 11 January 2025 (UTC)
Ok, what point is there to having AI summarize consensus? Consensus should be based on the strength of individual arguments, which only an experienced human editor can assess; AI can only guess what arguments look like. It's especially weird to use it here since if, theoretically, the AI summary decides there is consensus against considering AI comments in Misplaced Pages discussions, then that would include AI summary itself, leading to ]. ] (]) 19:41, 11 January 2025 (UTC)
:I'm not quite sure why ] is included in this discussion. The article is admittedly problematic - it's a neologism used almost entirely by blogger-activists and promoted in a self-published video essay by an academic working in a personal capacity as a political activist. The notability of the neologism, the video essay and the academic's activism is questionable to say the least - it emphatically isn't widely used or recognised beyond the blogosphere. (See ] for details - comments from other editors would be very welcome.) However, it seems to me to be in a rather different category from the one that Kirbytime sets out above. -- ] 02:00, 17 March 2007 (UTC)
=== Alternate proposal ===
::Although the article itself states that it is about the word "Pallywood", reading the discussion page it seems clear that many users including SlimVirgin and Leifern have decided that they want the article to be about alleged incidences of what might be called Pallywood, hence the dispute about referencing articles that don't even mention the term (e.g. and . This is extremely problematic as Misplaced Pages really shouldn't be adopting partisan neologisms as the titles of articles about things, unless the article is about said neologism. It is one of the main source of conflict on articles such as ] (where the same editors consicuously take the opposite view insisting that the sources ''must'' include references to Israeli apartheid) and ] and ]. --] 14:02, 17 March 2007 (UTC)
{{discussion top|result=Redundant proposal, confusingly worded, with no support, and not even any further discussion interest in 10 days. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:23, 22 December 2024 (UTC)}}
Whereas many editors, including me, have cited problems with accuracy in regards to existing tools such as ZeroGPT, I propose that '''remarks that are blatently generated by a LLM or similar automated system should be discounted/removed/collapsed/hidden'''. ] <sup>] / ]</sup> 10:00, 10 December 2024 (UTC)
:'''Oppose''' as completely unnecessary and far too prone to error per the above discussion. Any comment that is good (on topic, relevant, etc) should be considered by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is bad (off-topic, irrelevant, etc) should be ignored by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is both bad and disruptive (e.g. by being excessively long, completely irrelevant, bludgeoning, etc) should be removed and/or hatted as appropriate, regardless of whether it was made with LLM-input of any sort. The good thing is that ''this is already policy'' so we don't need to call out LLMs specifically, and indeed doing so is likely to be disruptive in cases where human-written comments are misidentified as being LLM-written (which ''will'' happen, regardless of whether tools are used). ] (]) 11:19, 10 December 2024 (UTC)
I think it's time to put all of the "Allegations . . ." articles up for Afd, as they all violate our rules against ], codified at ]. </font><small><span style="border: 1px solid #F06A0F">]]</span></small><font color="#ffffff"> · </font> 21:03, 18 March 2007 (UTC)
:I think this proposal is not really necessary. I support it, but that is because it is functionally identical to the one directly above it, which I also supported. This should probably be hatted. ] ] 18:32, 10 December 2024 (UTC)
:What does '''blatantly generated''' mean? Does you mean only where the remark is signed with "I, Chatbot", or anything that ''appears'' to be LLM-style? I don't think there's much in between. <span style="font-family:cursive">]]</span> 19:21, 10 December 2024 (UTC)
:'''Procedural close''' per BugGhost. I'd hat this myself, but I don't think that'd be appropriate since it's only the two of us who have expressed that this proposal is basically an exact clone. ] (]) 03:00, 11 December 2024 (UTC)
{{discussion bottom}}
== RfC: Voluntary RfA after resignation ==
=== Straw poll ===
<!-- ] 22:01, 19 January 2025 (UTC) -->{{User:ClueBot III/DoNotArchiveUntil|1737324070}}
{{rfc|policy|rfcid=5F11665}}
Should ] be amended to:
Sign under the statement with which you most agree. Discuss in comments section.
* '''Option 1'''{{snd}}Require former administrators to request restoration of their tools at the ] (BN) if they are eligible to do so (i.e., they do not fit into any of the exceptions).
* '''Option 2'''{{snd}}<s>Clarify</s> <ins>Maintain the status quo</ins> that former administrators who would be eligible to request restoration via BN may instead request restoration of their tools via a voluntary ] (RfA).
* '''Option 3'''{{snd}}Allow bureaucrats to SNOW-close RfAs as successful if (a) 48 hours have passed, (b) the editor has right of resysop, and (c) a SNOW close is warranted.
'''Background''': This issue arose in one ] and is currently being discussed in an ]. ] (]/]) 21:14, 15 December 2024 (UTC)<br />
====The article titles, as they currently stand, should be changed in some way====
'''Note''': There is an ongoing related discussion at {{slink|Misplaced Pages:Village pump (idea lab)#Making voluntary "reconfirmation" RFA's less controversial}}.<br />
*'''2''' per ]. If an admin wishes to be held accountable for their actions at a re-RfA, they should be allowed to do so. ] ] 21:22, 15 December 2024 (UTC)
*:Also fine with 3 ] ] 22:23, 15 December 2024 (UTC)
* There is ongoing discussion about this at ]. ] (]) 21:24, 15 December 2024 (UTC)
** '''2''', after thought. I don't think 3 provides much benefit, and creating separate class of RfAs that are speedy passed feels a misstep. If there are serious issues surrounding wasting time on RfAs set up under what might feel to someone like misleading pretenses, that is best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm ('''RRfA''')". ] (]) 14:49, 16 December 2024 (UTC)
**:{{tq|best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)"}} - I like this idea, if option 2 comes out as consensus I think this small change would be a step in the right direction, as the "this isn't the best use of time" crowd (myself included) would be able to quickly identify the type of RFAs they don't want to participate in. ] ] 11:05, 17 December 2024 (UTC)
**::I think that's a great idea. I would support adding some text encouraging people who are considering seeking reconfirmation to add (RRfA) or (reconfirmation) after their username in the RfA page title. That way people who are averse to reading or participating in reconfirmations can easily avoid them, and no one is confused about what is going on. ] (]) 14:23, 17 December 2024 (UTC)
**::I think this would be a great idea if it differentiated against recall RfAs. ] (]) 18:37, 17 December 2024 (UTC)
**:::If we are differentiating three types of RFA we need three terms. Post-recall RFAs are referred to as "reconfirmation RFAs", "Re-RFAS" or "RRFAs" in multiple places, so ones of the type being discussed here are the ones that should take the new term. "Voluntary reconfirmation RFA" (VRRFA or just VRFA) is the only thing that comes to mind but others will probably have better ideas. ] (]) 21:00, 17 December 2024 (UTC)
* '''1''' ] ] 21:25, 15 December 2024 (UTC)
*'''2''' I don't see why people trying to do the right thing should be discouraged from doing so. If others feel it is a waste of time, they are free to simply not participate. ] ] 21:27, 15 December 2024 (UTC)
*'''2''' Getting reconfirmation from the community should be allowed. Those who see it as a waste of time can ignore those RfAs. ] ] 21:32, 15 December 2024 (UTC)
*Of course they may request at RfA. They shouldn't but they may. This RfA feels like it does nothing to address the criticism actually in play and per the link to the idea lab discussion it's premature to boot. ] (]) 21:38, 15 December 2024 (UTC)
*'''2''' per my comments at the idea lab discussion and Queent of Hears, Beeblebrox and Scazjmd above. I strongly disagree with Barkeep's comment that "They shouldn't ". It shouldn't be made mandatory, but it should be encouraged where the time since desysop and/or the last RFA has been lengthy. ] (]) 21:42, 15 December 2024 (UTC)
*:When to encourage it would be a worthwhile RfC and such a discussion could be had at the idea lab before launching an RfC. Best, ] (]) 21:44, 15 December 2024 (UTC)
*::I've started that discussion as a subsection to the linked VPI discussion. ] (]) 22:20, 15 December 2024 (UTC)
*'''1''' <ins>or '''3'''</ins>. RFA is an "expensive" process in terms of community time. RFAs that qualify should be fast-tracked via the BN process. It is only recently that a trend has emerged that folks that don't need to RFA are RFAing again. 2 in the last 6 months. If this continues to scale up, it is going to take up a lot of community time, and create noise in the various RFA statistics and RFA notification systems (for example, watchlist notices and ]). –] <small>(])</small> 21:44, 15 December 2024 (UTC)
*:Making statistics "noisy" is just a reason to improve the way the statistics are gathered. In this case collecting statistics for reconfirmation RFAs separately from other RFAs would seem to be both very simple and very effective. ''If'' (and it is a very big if) the number of reconfirmation RFAs means that notifications are getting overloaded, ''then'' we can discuss whether reconfirmation RFAs should be notified differently. As far as differentiating them, that is also trivially simple - just add a parameter to ] (perhaps "reconfirmation=y") that outputs something that bots and scripts can check for. ] (]) 22:11, 15 December 2024 (UTC)
*:Option 3 looks like a good compromise. I'd support that too. –] <small>(])</small> 22:15, 15 December 2024 (UTC)
*:I'm weakly opposed to option 3, editors who want feedback and a renewed mandate from the community should be entitled to it. If they felt that that a quick endorsement was all that was required then could have had that at BN, they explicitly chose not to go that route. Nobody is required to participate in an RFA, so if it is going the way you think it should, or you don't have an opinion, then just don't participate and your time has not been wasted. ] (]) 22:20, 15 December 2024 (UTC)
*'''2'''. We should not make it ''more difficult'' for administrators to be held accountable for their actions in the way they please. ]<sub>]<sub>]</sub></sub> (]/]) 22:00, 15 December 2024 (UTC)
* Added '''option 3''' above. Maybe worth considering as a happy medium, where unsure admins can get a check on their conduct without taking up too much time. ] (] • she/her) 22:11, 15 December 2024 (UTC)
*'''2''' – If a former admin wishes to subject themselves to RfA to be sure they have the requisite community confidence to regain the tools, why should we stop them? Any editor who feels the process is a waste of time is free to ignore any such RfAs. — ] ⚓ ] 22:12, 15 December 2024 (UTC)
*:*I would also support option '''3''' if the time is extended to 72 hours instead of 48. That, however, is a detail that can be worked out after this RfC. — ] ⚓ ] 02:05, 16 December 2024 (UTC)
*'''Option 3''' per leek. ] (]/]) 22:16, 15 December 2024 (UTC)
*:A further note: option 3 gives 'crats the discretion to SNOW close a successful voluntary re-RfA; it doesn't require such a SNOW close, and I trust the 'crats to keep an RfA open if an admin has a good reason for doing so. ] (]/]) 23:24, 16 December 2024 (UTC)
*'''2''' as per {{noping|JJPMaster}}. Regards, --] (]) 22:20, 15 December 2024 (UTC)
*'''Option 2''' (no change) – The sample size is far too small for us to analyze the impact of such a change, but I believe RfA should always be available. Now that ] is policy, returning administrators may worry that they have become out of touch with community norms and may face a recall as soon as they get their tools back at BN. Having this familiar community touchpoint as an option makes a ton of sense, and would be far less disruptive / demoralizing than a potential recall. Taking this route away, even if it remains rarely used, would be detrimental to our desire for increased administrator accountability. – ] 22:22, 15 December 2024 (UTC)
*{{ec}} I'm surprised the response here hasn't been more hostile, given that these give the newly-unresigned administrator a ] for a year. —] 22:25, 15 December 2024 (UTC)
*:@] hostile to what? ] (]) 22:26, 15 December 2024 (UTC)
*'''2, distant second preference 3'''. I would probably support 3 as first pick if not for recall's rule regarding last RfA, but as it stands, SNOW-closing a discussion that makes someone immune to recall for a year is a non-starter. Between 1 and 2, though, the only argument for 1 seems to be that it avoids a waste of time, for which there is the much simpler solution of not participating and instead doing something else. ] and ] are always there. <span style="font-family:courier"> -- ]</span><sup class="nowrap">[]]</sup> <small>(])</small> 23:31, 15 December 2024 (UTC)
* 1 would be my preference, but I don't think we need a specific rule for this. -- ] (]) 23:36, 15 December 2024 (UTC)
*'''Option 1'''. <s>No second preference between 2 or 3.</s> As long as a former administrator didn't resign under a cloud, picking up the tools again should be low friction and low effort for the entire community. If there are issues introduced by the recall process, they should be fixed in the recall policy itself. ] (]) 01:19, 16 December 2024 (UTC)
*:After considering this further, I prefer option 3 over option 2 if option 1 is not the consensus. ] (]) 07:36, 16 December 2024 (UTC)
*'''Option 2''', i.e. leave well enough alone. There is really not a problem here that needs fixing. If someone doesn’t want to “waste their time” participating in an RfA that’s not required by policy, they can always, well, not participate in the RfA. No one is required to participate in someone else’s RfA, and I struggle to see the point of participating but then complaining about “having to” participate. ] (]) 01:24, 16 December 2024 (UTC)
*'''Option 2''' nobody is obligated to participate in a re-confirmation RfA. If you think they are a waste of time, avoid them. ] (]) 01:49, 16 December 2024 (UTC)
* '''1 or 3''' per Novem Linguae. <span style="padding:2px 5px;border-radius:5px;font-family:Arial black;white-space:nowrap;vertical-align:-1px">] <span style=color:red>F</span> ]</span> 02:35, 16 December 2024 (UTC)
*'''Option 3''': Because it is incredibly silly to have situations like we do now of "this guy did something wrong by doing an RfA that policy explicitly allows, oh well, nothing to do but sit on our hands and dissect the process across three venues and counting." Your time is your own. No one is forcibly stealing it from you. At the same time it is equally silly to let the process drag on, for reasons explained in ]. ] (]) 03:42, 16 December 2024 (UTC)
*:Update: Option 2 seems to be the consensus and I also would be fine with that. ] (]) 18:10, 19 December 2024 (UTC)
*'''Option 3''' per Gnoming. I think 2 works, but it is a very long process and for someone to renew their tools, it feels like an unnecessarily long process compared to a normal RfA. ] (]) 04:25, 16 December 2024 (UTC)
*As someone who supported both WormTT and Hog Farm's RfAs, option 1 > option 3 >> option 2. At each individual RfA the question is whether or not a specific editor should be an admin, and in both cases I felt that the answer was clearly "yes". However, I agree that RfA is a very intensive process. It requires a lot of time from the community, as others have argued better than I can. I prefer option 1 to option 3 because the existence of the procedure in option 3 implies that it is a good thing to go through 48 hours of RfA to re-request the mop. But anything which saves community time is a good thing. <b>]]</b> (] • he/they) 04:31, 16 December 2024 (UTC)
*:I've seen this assertion made multiple times now that {{tpq| requires a lot of time from the community}}, yet nowhere has anybody articulated how why this is true. What time is required, given that nobody is required to participate and everybody who does choose to participate can spend as much or as little time assessing the candidate as they wish? How and why does a reconfirmation RFA require any more time from editors (individually or collectively) than a request at BN? ] (]) 04:58, 16 December 2024 (UTC)
*::I think there are a number of factors and people are summing it up as "time-wasting" or similar:
*::# BN Is designed for this exact scenario. It's also clearly a less contentious process.
*::# Snow closures a good example of how we try to avoid wasting community time on unnecessary process and the same reasoning applies here. Misplaced Pages is not a bureaucracy and there's no reason to have a 7-day process when the outcome is a given.
*::# If former administrators continue to choose re-RFAs over BN, it could set a problematic precedent where future re-adminship candidates feel pressured to go through an RFA and all that entails. I don't want to discourage people already vetted by the community from rejoining the ranks.
*::# The RFA process is designed to be a thoughtful review of prospective administrators and I'm concerned these kinds of perfunctory RFAs will lead to people taking the process less seriously in the future.
*::] (]) 07:31, 16 December 2024 (UTC)
*::Because several thousand people have RFA on their watchlist, and thousands more will see the "there's an open RFA" notice on theirs whether they follow it or not. Unlike BN, RFA is a process that depends on community input from a large number of people. In order to even ''realise that the RFA is not worth their time'', they have to:
*::* Read the opening statement and first few question answers (I just counted, HF's opening and first 5 answers are about 1000 words)
*::* Think, "oh, they're an an ex-admin, I wonder why they're going through RFA, what was their cloud"
*::* Read through the comments and votes to see if any issues have been brought up (another ~1000 words)
*::* None have
*::* Realise your input is not necessary and this could have been done at BN
*::This process will be repeated by hundreds of editors over the course of a week. ] ] 08:07, 16 December 2024 (UTC)
*:::That they were former admins has always been the first two sentences of their RfA’s statement, sentences which are immediately followed by that they resigned due to personal time commitment issues. You do not have to read the first 1000+ words to figure that out. If the reader wants to see if the candidate was lying in their statement, then they just have a quick skim through the oppose section. None of this should take more than 30 seconds in total. ] (]) 13:15, 16 December 2024 (UTC)
*::::Not everyone can skim things easily - it personally takes me a while to read sections. I don't know if they're going to bury the lede and say something like "Also I made 10,000 insane redirects and then decided to take a break just before arbcom launched a case" in paragraph 6. Hog Farm's self nom had two paragraphs about disputes and it takes more than 30 seconds to unpick that and determine if that is a "cloud" or not. Even for reconfirmations, it definitely takes more than 30 seconds to determine a conclusion. ] ] 11:21, 17 December 2024 (UTC)
*:::::They said they resigned to personal time commitments. That is directly saying they wasn’t under a cloud, so I’ll believe them unless someone claims the contrary in the oppose section. If the disputes section contained a cloud, the oppose section would have said so. One chooses to examine such nominations like normal RfAs. ] (]) 18:47, 17 December 2024 (UTC)
*::::::Just to double check, you're saying that whenever you go onto an RFA you expect any reason to oppose to already be listed by someone else, and no thought is required? I am begining to see how you are able to assess an RFA in under 30 seconds ] ] 23:08, 17 December 2024 (UTC)
*:::::::Something in their statement would be an incredibly obvious reason. We are talking about the assessment whether to examine and whether the candidate could've used BN. ] (]) 12:52, 18 December 2024 (UTC)
*::@] let's not confuse "a lot of community time is spent" with "waste of time". Some people have characterized the re-RFAs as a waste of time but that's not the assertion I (and I think a majority of the skeptics) have been making. All RfAs use a lot of community time as hundreds of voters evaluate the candidate. They then choose to support, oppose, be neutral, or not vote at all. While editor time is not perfectly fixed - editors may choose to spend less time on non-Misplaced Pages activities at certain times - neither is it a resource we have in abundance anymore relative to our project. And so I think we, as a community, need to be thought about how we're using that time especially when the use of that time would have been spent on other wiki activities.Best, ] (]) 22:49, 16 December 2024 (UTC)
*:::Absolutely nothing compels anybody to spend any time evaluating an RFA. If you think your wiki time is better spent elsewhere than evaluating an RFA candidate, then spend it elsewhere. That way only those who do think it is a good use of their time will participate and everybody wins. You win by not spending your time on something that you don't think is worth it, those who do participate don't have ''their'' time wasted by having to read comments (that contradict explicit policy) about how the RFA is a waste of time. Personally I regard evaluating whether a long-time admin still has the approval of the community to be a very good use of community time, you are free to disagree, but please don't waste my time by forcing me to read comments about how you think I'm wasting my time. ] (]) 23:39, 16 December 2024 (UTC)
*::::I am not saying you or anyone else is wasting time and am surprised you are so fervently insisting I am. Best, ] (]) 03:34, 17 December 2024 (UTC)
*:::::I don't understand how your argument that it is not a good use of community time is any different from arguing that it is a waste of time? ] (]) 09:08, 17 December 2024 (UTC)
*'''Option 2''' I don't mind the re-RFAs, but I'd appreciate if we encouraged restoration via BN instead, I just object to making it mandatory. ] <sup>(]) </sup> 06:23, 16 December 2024 (UTC)
*'''Option 2'''. Banning voluntary re-RfAs would be a step in the wrong direction on admin accountability. Same with SNOW closing. There is no more "wasting of community time" if we let the RfA run for the full seven days, but allowing someone to dig up a scandal on the seventh day is an important part of the RfA process. The only valid criticism I've heard is that folks who do this are arrogant, but banning arrogance, while noble, seems highly impractical. ] </span>]] 07:24, 16 December 2024 (UTC)
*Option 3, 1, then 2, per HouseBlaster. Also agree with Daniel Quinlan. I think these sorts of RFA's should only be done in exceptional circumstances. ] (]) 08:46, 16 December 2024 (UTC)
* '''Option 1''' as first preference, option 3 second. RFAs use up a lot of time - hundreds of editors will read the RFA and it takes time to come to a conclusion. When that conclusion is "well that was pointless, my input wasn't needed", it is not a good system. I think transparency and accountability is a very good thing, and we need more of it for resyssopings, but that should come from improving the normal process (BN) rather than using a different one (RFA). My ideas for improving the BN route to make it more transparent and better at getting community input is outlined over on the ] ] 08:59, 16 December 2024 (UTC)
* '''Option 2''', though I'd be for '''option 3''' too. I'm all for administrators who feel like they want/should go through an RfA to solicit feedback even if they've been given the tools back already. I see multiple people talk about going through BN, but if I had to hazard a guess, it's way less watched than RfA is. However I do feel like watchlist notifications should say something to the effect of "A request for re-adminship feedback is open for discussion" so that people that don't like these could ignore them. <span>♠] ]</span>♠ 09:13, 16 December 2024 (UTC)
*'''Option 2''' because ] is well-established policy. Read ], which says quite clearly, {{tpq|Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process.}} I went back 500 edits to 2017 and the wording was substantially the same back then. So, I simply do not understand why various editors are berating former administrators to the point of accusing them of wasting time and being arrogant for choosing to go through a process which is ''specifically permitted by policy''. It is bewildering to me. ] (]) 09:56, 16 December 2024 (UTC)
*'''Option 2 & 3''' I think that there still should be the choice between BN and re-RFA for resysops, but I think that the re-RFA should stay like it is in Option 3, unless it is controversial, at which point it could be extended to the full RFA period. I feel like this would be the best compromise between not "wasting" community time (which I believe is a very overstated, yet understandable, point) and ensuring that the process is based on broad consensus and that our "representatives" are still supported. If I were WTT or Hog, I might choose to make the same decision so as to be respectful of the possibility of changing consensus. ] (]) | :) | he/him | 10:45, 16 December 2024 (UTC)
*'''Option 2''', for lack of a better choice. Banning re-RFAs is not a great idea, and we should not SNOW close a discussion that would give someone immunity from a certain degree of accountability. I've dropped an idea for an option 4 in the discussion section below. ] (]) 12:08, 16 December 2024 (UTC)
*'''Option 1''' I agree with Graham87 that these sorts of RFAs should only be done in exceptional circumstances, and BN is the best place to ask for tools back. – ] <small>(])</small> 12:11, 16 December 2024 (UTC)
*'''Option 2''' I don't think prohibition makes sense. It also has weird side effects. eg: some admins' voluntary recall policies may now be completely void, because they would be unable to follow them even if they wanted to, because policy prohibits them from doing a RFA. (maybe if they're also 'under a cloud' it'd fit into exemptions, but if an admins' policy is "3 editors on this named list tell me I'm unfit, I resign" then this isn't really a cloud.) {{pb}} Personally, I think Hog Farm's RFA was unwise, as he's textbook uncontroversial. Worm's was a decent RFA; he's also textbook uncontroversial but it happened at a good time. But any editor participating in these discussions to give the "support" does so using their own time. Everyone who feels their time is wasted can choose to ignore the discussion, and instead it'll pass as 10-0-0 instead of 198-2-4. It just doesn't make sense to prohibit someone from seeking a community discussion, though. For almost anything, really. ] (]) 12:33, 16 December 2024 (UTC)
*'''Option 2''' It takes like two seconds to support or ignore an RFA you think is "useless"... can't understand the hullabaloo around them. I stand by what I said on ] regarding RFAs being about evaluating trustworthiness and accountability. Trustworthy people don't skip the process. —] <span title="Canadian!" style="color:red">🍁</span> (] · ]) 15:24, 16 December 2024 (UTC)
*'''Option 1''' - Option 2 is a waste of community time. - ] (]) 15:30, 16 December 2024 (UTC)
*:Why? ] (]) 15:35, 16 December 2024 (UTC)
*'''2''' is fine. '''Strong oppose''' to 1 and 3. Opposing option 1 because there is nothing wrong with asking for extra community feedback. opposing option 3 because once an RfA has been started, it should follow the standard rules. Note that RfAs are extremely rare and non-contentious RfAs require very little community time (unlike this RfC which seems a waste of community time, but there we are). —] (]) 16:59, 16 December 2024 (UTC)
*'''2''', with no opposition to 3. I see nothing wrong with a former administrator getting re-confirmed by the community, and community vetting seems like a good thing overall. If people think it's a waste of time, then just ignore the RfA. ] (]) 17:56, 16 December 2024 (UTC)
*'''2''' Sure, and clarify that should such an RFA be unsuccessful they may only regain through a future rfa. — ] <sup>]</sup> 18:03, 16 December 2024 (UTC)
*'''Option 2''' If contributing to such an RFA is a waste of your time, just don't participate. ] (]) 18:43, 16 December 2024 (UTC)
*:No individual is wasting their time participating. Instead the person asking for a re-rfa is ''using'' tons of editor time by asking hundreds of people to vet them. Even the choice not to participate requires at least some time to figure out that this is not a new RfA; though at least in the two we've had recently it would require only as long as it takes to get to the RfA - for many a click from the watchlist and then another click into the rfa page - and to read the first couple of sentences of the self-nomination which isn't terribly long all things considered. Best, ] (]) 22:55, 16 December 2024 (UTC)
*::I agree with you (I think) that it's a matter of perspective. For me, clicking the RFA link in my watchlist and reading the first paragraph of Hog Farm's nomination (where they explained that they were already a respected admin) took me about 10 seconds. Ten seconds is nothing; in my opinion, this is just a nonissue. But then again, I'm not an admin, checkuser, or an oversighter. Maybe the time to read such a nomination is really wasting their time. I don't know. ] (]) 23:15, 16 December 2024 (UTC)
*:::I'm an admin and an oversighter (but not a checkuser). None of my time was wasted by either WTT or Hog Farm's nominations. ] (]) 23:30, 16 December 2024 (UTC)
*'''2'''. Maintain the ''status quo''. And stop worrying about a trivial non-problem. --] (]) 22:57, 16 December 2024 (UTC)
*'''2'''. This reminds me of banning plastic straws (bear with me). Sure, I suppose in theory, that this is a burden on the community's time (just as straws do end up in landfills/the ocean). However, the amount of community time that is drained is minuscule compared to the amount of community time drained in countless, countless other fora and processes (just like the volume of plastic waste contributed by plastic straws is less than 0.001% of the total plastic waste). When WP becomes an efficient, well oiled machine, then maybe we can talk about saving community time by banning re-RFA's. But this is much ado about nothing, and indeed this plan to save people from themselves, and not allow them to simply decide whether to participate or not, is arguably more damaging than some re-RFAs (just as banning straws convinced some people that "these save-the-planet people are so ridiculous that I'm not going to bother listening to them about anything."). And, in fact, on a separate note, I'd actually love it if more admins just ran a re-RFA whenever they wanted. They would certainly get better feedback than just posting "What do my talk page watchers think?" on their own talk page. Or waiting until they get yelled at on their talk page, AN/ANI, AARV, etc. We say we want admins to respect feedback; does it '''have''' to be in a recall petition? --] (]) 23:44, 16 December 2024 (UTC)
*:What meaningful feedback has Hog Farm gotten? "A minority of people think you choose poorly in choosing this process to regain adminship". What are they supposed to do with that? I share your desire for editors to share meaningful feedback with administrators. My own attempt yielded some, though mainly offwiki where I was told I was both too cautious and too impetuous (and despite the seeming contradiction each was valuable in its own way). So yes let's find ways to get meaningful feedback to admins outside of recall or being dragged to ANI. Unfortunately re-RfA seems to be poorly suited to the task and so we can likely find a better way. Best, ] (]) 03:38, 17 December 2024 (UTC)
*:Let us all take some comfort in the fact that no one has yet criticized this RfC comment as being a straw man argument. --] (]) 23:58, 18 December 2024 (UTC)
*'''No hard rule, but we should socially discourage confirmation RfAs''' There is a difference between a hard rule, and a soft social rule. A hard rule against confirmation RfA's, like option 1, would not do a good job of accounting for edge cases and would thus be ultimately detrimental here. But a soft social rule against them would be beneficial. Unfortunately, that is not one of the options of this RfC. In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. (Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here.) That takes some introspection and humility to ask yourself: is it worth me inviting two or three hundred people to spend part of their lives to comment on me as a person?{{pb}}A lot of people have thrown around ] in their reasonings. Obviously, broad generalizations about it aren't convincing anyone. So let me just share my own experience. I saw the watchlist notice open that a new RfA was being run. I reacted with some excitement, because I always like seeing new admins. When I got to the page and saw Hogfarm's name, I immediately thought "isn't he already an admin?" I then assumed, ah, its just the classic RfA reaction at seeing a qualified candidate, so I'll probably support him since I already think he's an admin. But then as I started to do my due diligence and read, I saw that he really, truly, already had been an admin. At that point, my previous excitement turned to a certain unease. I had voted yes for Worm's confirmation RfA, but here was another...and I realized that my blind support for Worm might have been the start of an entirely new process. I then thought "bet there's an RfC going about this," and came here. I then spent a while polishing up my essay on editor time, before taking time to write this message. All in all, I probably spent a good hour doing this. Previously, I'd just been clicking the random article button and gnoming. So, the longwinded moral: yeah, this did eat up a lot of my editor time that could have and was being spent doing something else. And I'd do it again! It was important to do my research and to comment here. But in the future...maybe I won't react quite as excitedly to seeing that RfA notice. Maybe I'll feel a little pang of dread...wondering if its going to be a confirmation RfA. We can't pretend that confirmation RfA's are costless, and that we don't lose anything even if editors just ignore them. When run, it should be because they are necessary. ] <sup>]</sup>] 03:29, 17 December 2024 (UTC)
*:And for what its worth, support '''Option 3''' because I'm generally a fan of putting more tools in people's toolboxes. ] <sup>]</sup>] 03:36, 17 December 2024 (UTC)
*:{{tpq|In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers.}} Asking the community whether you still have their trust to be an administrator, which is what an reconfirmation RFA is, ''is'' a good reason. I expect getting a near-unanimous "yes" is good for one's ego, but that's just a (nice) side-effect of the far more important benefits to the entire community: a trusted administrator.
*:The time you claim is being eaten up unnecessarily by reconfirmation RFAs was actually taken up by you choosing to spend your time writing an essay about using time for things you don't approve of and then hunting out an RFC in which you wrote another short essay about using time on things you don't approve of. Absolutely none of that is a necessary consequence of reconfirmation RFAs - indeed the response consistent with your stated goals would have been to read the first two sentences of Hog Farm's RFA and then closed the tab and returned to whatever else it was you were doing. ] (]) 09:16, 17 December 2024 (UTC)
*:WTT's and Hog Farm's RFAs would have been completely uncontentious, something I hope for at RfA and certainly the opposite of what I "dread" at RfA, if it were not for the people who attack the very concept of standing for RfA again despite policy being crystal clear that it is absolutely fine. I don't see how any blame for this situation can be put on WTT or HF. We can't pretend that dismissing uncontentious reconfirmation RfAs is costless; discouraging them removes one of the few remaining potentially wholesome bits about the process. —] (]) 09:53, 17 December 2024 (UTC)
*:@] Would you find it better if Watchlist notices and similar said "(re?)confirmation RFA" instead of "RFA"? Say for all voluntary RFAs from an existing admin or someone who could have used BN?
*:As a different point, I would be quite against any social discouraging if we're not making a hard rule as such. Social discouraging is what got us the opposes at WTT/Hog Farm's RFAs, which I found quite distasteful and badgering. If people disagree with a process, they should change it. But if the process remains the same, I think it's important to not enable RFA's toxicity by encouraging others to namecall or re-argue the process in each RRFA. It's a short road from social discouragement to toxicity, unfortunately. ] (]) 18:41, 19 December 2024 (UTC)
*::Yes I think the watchlist notice should specify what kind of RfA, especially with the introduction of recall. ] <sup>]</sup>] 16:49, 23 December 2024 (UTC)
* '''Option 1'''. Will prevent the unnecessary drama trend we are seeing in the recent. – ] (]) 07:18, 17 December 2024 (UTC)
* '''Option 2''' if people think there's a waste of community time, don't spend your time voting or discussing. Or add "reconfirmation" or similar to the watchlist notice. ] (]) 15:08, 17 December 2024 (UTC)
* '''Option 3''' (which I think is a subset of option 2, so I'm okay with the status quo, but I want to endorse giving 'crats the option to SNOW). While they do come under scrutiny from time to time for the extensive dicsussions in the "maybe" zone following RfAs, this should be taken as an indiciation that they are unlikely to do something like close it as SNOW in the event there is <em>real and substantial</em> concerns being rasied. This is an okay tool to give the 'crats. As far as I can tell, no one has ever accused the them of moving too quickly in this direction (not criticism; love you all, keep up the good work). ] (]) 17:26, 17 December 2024 (UTC)
* '''Option 3 or Option 2'''. Further, if Option 2 passes, I expect it also ends all the bickering about lost community time. A consensus explicitly in favour of "This is allowed" should also be a consensus to discourage relitigation of this RFC. ] (]) 17:35, 17 December 2024 (UTC)
*'''Option 2''': Admins who do not exude entitlement are to be praised. Those who criticize this humility should have a look in the mirror before accusing those who ask for reanointment from the community of "arrogance". I agree that it wouldn't be a bad idea to mention in parentheses that the RFA is a reconfirmation (watchlist) and wouldn't see any problem with crats snow-closing after, say, 96 hours. -- ] <sup>] · ]</sup> 18:48, 17 December 2024 (UTC)
*:I disagree that BN shouldn't be the normal route. RfA is already as hard and soul-crushing as it is. ] (]) 20:45, 17 December 2024 (UTC)
*::Who are you disagreeing with? This RfC is about voluntary RRfA. -- ] <sup>] · ]</sup> 20:59, 17 December 2024 (UTC)
*:::I know. I see a sizable amount of commenters here starting to say that voluntary re-RfAs should be encouraged, and your first sentence can be easily read as implying that admins who use the BN route exude entitlement. I disagree with that (see my reply to Thryduulf below). ] (]) 12:56, 18 December 2024 (UTC)
*::One way to improve the reputation of RFA is for there to be more RFAs that are not terrible, such as reconfirmations of admins who are doing/have done a good job who sail through with many positive comments. There is no proposal to make RFA mandatory in circumstances it currently isn't, only to reaffirm that those who voluntarily choose RFA are entitled to do so. ] (]) 21:06, 17 December 2024 (UTC)
*:::I know it's not a proposal, but there's enough people talking about this so far that it could become a proposal.<br />There's nearly nothing in between that could've lost the trust of the community. I'm sure there are many who do not want to be pressured into ] without good reason. ] (]) 12:57, 18 December 2024 (UTC)
*::::Absolutely nobody is proposing, suggesting or hinting here that reconfirmation RFAs should become mandatory - other than comments from a few people who oppose the idea of people voluntarily choosing to do something policy explicitly allows them to choose to do. The best way to avoid people being pressured into being accused of arrogance for seeking reconfirmation of their status from the community is to sanction those people who accuse people of arrogance in such circumstances as such comments are in flagrant breach of AGF and NPA. ] (]) 14:56, 18 December 2024 (UTC)
*:::::Yes, I’m saying that they should not become preferred. There should be no social pressure to do RfA instead of BN, only pressure intrinsic to the candidate. ] (]) 15:37, 18 December 2024 (UTC)
*::::::Whether they should become preferred in any situation forms no part of this proposal in any way shape or form - this seeks only to reaffirm that they are permitted. A separate suggestion, completely independent of this one, is to encourage (explicitly not mandate) them in some (but explicitly not all) situations. All discussions on this topic would benefit if people stopped misrepresenting the policies and proposals - especially when the falsehoods have been explicitly called out. ] (]) 15:49, 18 December 2024 (UTC)
*:::::::I am talking and worrying over that separate proposal many here are suggesting. I don’t intend to oppose Option 2, and sorry if I came off that way. ] (]) 16:29, 18 December 2024 (UTC)
*'''Option 2'''. In fact, I'm inclined to ''encourage'' an RRfA over BN, because nothing requires editors to participate in an RRfA, but the resulting discussion is better for reaffirming community consensus for the former admin or otherwise providing helpful feedback. --] (]) 21:45, 17 December 2024 (UTC)
*'''Option 2''' ] has said "{{tq|Former administrators may seek reinstatement of their privileges through RfA...}}" for over ten years and this is not a problem. I liked the opportunity to be consulted in the current RfA and don't consider this a waste of time. ]🐉(]) 22:14, 17 December 2024 (UTC)
*'''Option 2'''. People who think it’s not a good use of their time always have the option to scroll past. ] (]) 01:41, 18 December 2024 (UTC)
* '''2''' - If an administrator gives up sysop access because they plan to be inactive for a while and want to minimize the attack surface of Misplaced Pages, they should be able to ask for permissions back the quickest way possible. If an administrator resigns because they do not intend to do the job anymore, and later changes their mind, they should request a community discussion. The right course of action depends on the situation. ] <sup>]</sup> 14:00, 18 December 2024 (UTC)
*'''Option 1'''. I've watched a lot of RFAs and re-RFAs over the years. There's a darn good reason why the community developed the "go to BN" option: saves time, is straightforward, and if there are issues that point to a re-RFA, they're quickly surfaced. People who refuse to take the community-developed process of going to BN first are basically telling the community that they need the community's full attention on their quest to re-admin. Yes, there are those who may be directed to re-RFA by the bureaucrats, in which case, they have followed the community's carefully crafted process, and their re-RFA should be evaluated from that perspective. ] (]) 02:34, 19 December 2024 (UTC)
*'''Option 2'''. If people want to choose to go through an RFA, who are we to stop them? ] (]) 10:25, 19 December 2024 (UTC)
*'''Option 2''' (status quo/no changes) per ]. This is bureaucratic rulemongering at its finest. Every time RFA reform comes up some editors want admins to be required to periodically reconfirm, then when some admins decide to reconfirm voluntarily, suddenly that's seen as a bad thing. The correct thing to do here is nothing. If you don't like voluntary reconfirmation RFAs, you are not required to participate in them. ] (<sup>]</sup>/<sub>]</sub>) 19:34, 19 December 2024 (UTC)
*'''Option 2''' I would probably counsel just going to BN most of the time, however there are exceptions and edge cases. To this point these RfAs have been few in number, so the costs incurred are relatively minor. If the number becomes large then it might be worth revisiting, but I don't see that as likely. Some people will probably impose social costs on those who start them by opposing these RfAs, with the usual result, but that doesn't really change the overall analysis. Perhaps it would be better if our idiosyncratic internal logic didn't produce such outcomes, but that's a separate issue and frankly not really worth fighting over either. There's probably some meta issues here I'm unaware off, it's long since I've had my finger on the community pulse so to speak, but they tend to matter far less than people think they do. ] (]) 02:28, 20 December 2024 (UTC)
* '''Option 1''', per ], ], ], ], and related principles. We all have far better things to do that read through and argue in/about a totally unnecessary RfA invoked as a "Show me some love!" abuse of process and waste of community time and productivity. I could live with option 3, if option 1 doesn't fly (i.e. shut these silly things down as quickly as possible). But option 2 is just out of the question. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 04:28, 22 December 2024 (UTC)
*:Except none of the re-RFAs complained about have been {{tpq|RfA invoked as a "Show me some love!" abuse of process}}, you're arguing against a strawman. ] (]) 11:41, 22 December 2024 (UTC)
*::It's entirely a matter of opinion and perception, or A) this RfC wouldn't exist, and B) various of your fellow admins like TonyBallioni would not have come to the same conclusion I have. Whether the underlying intent (which no one can determine, lacking as we do any magical mind-reading powers) is solely egotistical is ultimately irrelevant. The {{em|actual effect}} (what matters) of doing this whether for attention, or because you've somehow confused yourself into think it needs to be done, is precisely the same: a showy waste of community volunteers' time with no result other than a bunch of attention being drawn to a particular editor and their deeds, without any actual need for the community to engage in a lengthy formal process to re-examine them. <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 05:49, 23 December 2024 (UTC)
*:::{{tqb|or because you've somehow confused yourself into think it needs to be done}} I and many others here agree and stand behind the very reasoning that has "confused" such candidates, at least for WTT. ] (]) 15:37, 23 December 2024 (UTC)
*'''Option 2'''. I see no legitimate reason why we should be changing the status quo. Sure, some former admins might find it easier to go through BN, and it might save community time, and most former admins ''already'' choose the easier option. However, if a candidate last ran for adminship several years ago, or if issues were raised during their tenure as admin, then it may be helpful for them to ask for community feedback, anyway. There is no "wasted" community time in such a case. I really don't get the claims that this violates ], because it really doesn't apply when a former admin last ran for adminship 10 or 20 years ago or wants to know if they still have community trust.{{pb}}On the other hand, if an editor thinks a re-RFA is a waste of community time, they can simply choose not to participate in that RFA. Opposing individual candidates' re-RFAs based solely on opposition to re-RFAs in general ''is'' a violation of ]. – ] (]) 14:46, 22 December 2024 (UTC)
*:But this isn't the status quo? We've never done a re-RfA before now. The question is whether this previously unconsidered process, which appeared as an ], is a feature or a bug. ] <sup>]</sup>] 23:01, 22 December 2024 (UTC)
*::There have been lots of re-RFAs, historically. There were more common in the 2000s. ] in 2003 is the earliest I can find, back before the re-sysopping system had been worked out fully. ] back in 2007 was snow-closed after one day, because the nominator and applicant didn't know that they could have gone to the bureaucrats' noticeboard. For more modern examples, ] (2011) is relatively similar to the recent re-RFAs in the sense that the admin resigned uncontroversially but chose to re-RFA before getting the tools back. Immediately following and inspired by HJ Mitchell's, there was the slightly more controversial ]. That ended successful re-RFAS until 2019's ], which crat-chatted. Since then, there have been none that I remember. There have been several re-RFAs from admins who were de-sysopped or at serious risk of de-sysopping, and a few interesting edge cases such as the yet no-consensus ] in 2014 and the ] case in 2015, but those are very different than what we're talking about today. ] (]) 00:01, 23 December 2024 (UTC)
*:::To add on to that, ] was technically a reconfirmation RFA, which in a sense can be treated as a re-RFA. My point is, there is some precedent for re-RFAs, but the current guidelines are ambiguous as to when re-RFAs are or aren't allowed. – ] (]) 16:34, 23 December 2024 (UTC)
*::::Well thank you both, I've learned something new today. It turns out I was working on a false assumption. It has just been so long since a re-RfA that I assumed it was a truly new phenomenon, especially since there were two in short succession. I still can't say I'm thrilled by the process and think it should be used sparingly, but perhaps I was a bit over concerned. ] <sup>]</sup>] 16:47, 23 December 2024 (UTC)
*'''Option 2 or 3''' per Gnoming and CaptainEek. Such RfAs only require at most 30 seconds for one to decide whether or not to spend their time on examination. Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. Voluntary reconfirmation RfAs are socially discouraged, so there is usually a very good reason for someone to go back there, such as accountability for past statements in the case of WTT or large disputes during adminship in the case of Hog Farm. I don't think we should outright deny these, and there is no disruption incurred if we don't. ] (]) 15:44, 23 December 2024 (UTC)
*'''Option 2''' but for largely the reasons presented by CaptainEek. ''']''' (<small>aka</small> ] '''·''' ] '''·''' ]) 21:58, 23 December 2024 (UTC)
*'''Option 2 (fine with better labeling)''' These don't seem harmful to me and, if I don't have time, I'll skip one and trust the judgment of my fellow editors. No objection to better labeling them though, as discussed above. ] (]) 22:36, 23 December 2024 (UTC)
*'''Option 1''' because it's just a waste of time to go through and !vote on candidates who just want the mop restored when he or she or they could get it restored BN with no problems. But I can also see option 2 being good for a former mod not in good standing. ] (]) 23:05, 23 December 2024 (UTC)
*:If you think it is a waste of time to !vote on a candidate, just don't vote on that candidate and none of your time has been wasted. ] (]) 23:28, 23 December 2024 (UTC)
*'''Option 2''' per QoH (or me? who knows...) ] • ] • ] 04:24, 27 December 2024 (UTC)
*'''Option 2''' Just because someone may be entitled to get the bit back doesn't mean they necessarily should. Look at ]. I did not resign under a cloud, so I could have gotten the bit back by request. However, the RFA established that I did not have the community support at that point, so it was a good thing that I chose that path. I don't particularly support option 3, but I could deal with it. --] 16:05, 27 December 2024 (UTC)
*'''Option 1''' Asking hundreds of people to vet a candidate who has already passed a RfA and is eligible to get the tools back at BN is a waste of the community's time. -- ] (]) 16:21, 27 December 2024 (UTC)
*'''Option 2''' Abolishing RFA in favour of BN may need to be considered, but I am unconvinced by arguments about RFA being a waste of time. ] ] 19:21, 27 December 2024 (UTC)
*'''Option 2''' I really don't think there's a problem that needs to be fixed here. I am grateful at least a couple administrators have asked for the support of the community recently. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 00:12, 29 December 2024 (UTC)
*'''Option 2'''. Keep the status quo of {{tq|any editor is free to re-request the tools through the requests for adminship process}}. Voluntary RfA are rare enough not to be a problem, it's not as though we are overburdened with RfAs. And it’s my time to waste. --] (]) 17:58, 7 January 2025 (UTC)
* '''Option 2 or Option 3'''. These are unlikely to happen anyway, it's not like they're going to become a trend. I'm already wasting my time here instead of other more important activities anyway, so what's a little more time spent giving an easy support?{{pb
}}<span style="border-radius:9em;padding:0 7px;background:#000000">] ]</span> 16:39, 10 January 2025 (UTC)
===Discussion===
====The article titles, as they currently stand, do not need to be changed====
*{{re|Voorts}} If option 2 gets consensus how would this RfC change the wording {{tqq|Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process.}} Or is this an attempt to see if that option no longer has consensus? If so why wasn't alternative wording proposed? As I noted above this feels premature in multiple ways. Best, ] (]) 21:43, 15 December 2024 (UTC)
#--] 02:09, 22 March 2007 (UTC)
*:That is not actually true. ArbCom can (and has) forbidden some editors from re-requesting the tools through RFA. ] ] 19:21, 27 December 2024 (UTC)
#-- ] 19:21, 23 March 2007 (UTC)
*I've re-opened this per ] on my talk page. If other editors think this is premature, they can !vote accordingly and an uninvolved closer can determine if there's consensus for an early close in deference to the VPI discussion. ] (]/]) 21:53, 15 December 2024 (UTC)
#-- ]<sup><small><font color="DarkGreen">]</font></small></sup> 03:40, 11 April 2007 (UTC)
*:The discussion at VPI, which I have replied on, seems to me to be different enough from this discussion that both can run concurrently. That is, however, my opinion as a mere editor. — ] ⚓ ] 22:01, 15 December 2024 (UTC)
*:@], can you please reword the RfC to make it clear that Option 2 is the current consensus version? It does not need to be clarified – it already says precisely what you propose. – ] 22:02, 15 December 2024 (UTC)
*::{{done}} ] (]/]) 22:07, 15 December 2024 (UTC)
*'''Question''': May someone clarify why many view such confirmation RfAs as a waste of community time? No editor is obligated to take up their time and participate. If there's nothing to discuss, then there's no friction or dis-cussing, and the RfA smooth-sails; if a problem is identified, then there was a good reason to go to RfA. I'm sure I'm missing something here. ] (]) 22:35, 15 December 2024 (UTC)
*: The intent of RfA is to provide a comprehensive review of a candidate for adminship, to make sure that they meet the community's standards. Is that happening with vanity re-RfAs? Absolutely not, because these people don't need that level of vetting. I wouldn't consider a week long, publicly advertized back patting to be a productive use of volunteer time. -- ] (]) 23:33, 15 December 2024 (UTC)
*::But no volunteer is obligated to pat such candidates on the back. ] (]) 00:33, 16 December 2024 (UTC)
*::: Sure, but that logic could be used to justify any time sink. We're all volunteers and nobody is forced to do anything here, but that doesn't mean that we should promote (or stay silent with our criticism of, I suppose) things that we feel don't serve a useful purpose. I don't think this is a huge deal myself, but we've got two in a short period of time and I'd prefer to do a bit of push back now before they get more common. -- ] (]) 01:52, 16 December 2024 (UTC)
*::::Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. ] (]) 02:31, 16 December 2024 (UTC)
*:::::Except someone who has no need for advanced tools and is not going to use them in any useful fashion, would then skate through with nary a word said about their unsuitability, regardless of the foregone conclusion. The point of RFA is not to rubber-stamp. Unless their is some actual issue or genuine concern they might not get their tools back, they should just re-request them at BN and stop wasting people's time with pointless non-process wonkery. ] (]) 09:05, 16 December 2024 (UTC)
*::::::I’m confused. Adminship requires continued use of the tools. If you think they’s suitable for BN, I don’t see how doing an RfA suddenly makes them unsuitable. If you have concerns, raise them. ] (]) 13:02, 16 December 2024 (UTC)
*I don't think the suggested problem (which I acknowledge not everyone thinks is a problem) is resolved by these options. Admins can still run a re-confirmation RfA after regaining adminsitrative privileges, or even initiate a recall petition. I think as ], we want to encourage former admins who are unsure if they continue to be trusted by the community at a sufficient level to explore lower cost ways of determining this. ] (]) 00:32, 16 December 2024 (UTC)
*:Regarding option 3, ]. The intent of having a reconfirmation request for administrative privileges is counteracted by closing it swiftly. It provides incentive for rapid voting that may not provide the desired considered feedback. ] (]) 17:44, 17 December 2024 (UTC)
* In re the idea that RfAs use up a lot of community time: I first started editing Misplaced Pages in 2014. There were 62 RfAs that year, which was a historic low. Even counting all of the AElect candidates as separate RfAs, including those withdrawn before voting began, we're still up to only 53 in 2024 – counting only traditional RfAs it's only 18, which is the second lowest number ever. By my count we've has 8 resysop requests at BN in 2024; even if all of those went to RfA, I don't see how that would overwhelm the community. That would still leave us on 26 traditional RfAs per year, or (assuming all of them run the full week) one every other week. ] (]) 10:26, 16 December 2024 (UTC)
* What about an option 4 encouraging eligible candidates to go through BN? At the end of the ], add something like "Eligible users are encouraged to use this method rather than running a new request for adminship." The current wording makes re-RfAing sound like a plausible alternative to a BN request, when in actual fact the former rarely happens and always generates criticism. ] (]) 12:08, 16 December 2024 (UTC)
*:Discouraging RFAs is the second last thing we should be doing (after prohibiting them), rather per my comments here and in the VPI discussion we should be ''encouraging'' former administrators to demonstrate that they still have the approval of the community. ] (]) 12:16, 16 December 2024 (UTC)
*:I think this is a good idea if people do decide to go with option 2, if only to stave off any further mixed messages that people are doing something wrong or rude or time-wasting or whatever by doing a second RfA, when it's explicitly mentioned as a valid thing for them to do. ] (]) 15:04, 16 December 2024 (UTC)
*::If RFA is explicitly a valid thing for people to do (which it is, and is being reaffirmed by the growing consensus for option 2) then we don't need to (and shouldn't) discourage people from using that option. The mixed messages can be staved off by people simply not making comments that explicitly contradict policy. ] (]) 15:30, 16 December 2024 (UTC)
*:::Also a solid option, the question is whether people will actually do it. ] (]) 22:55, 16 December 2024 (UTC)
*::::The simplest way would be to just quickly hat/remove all such comments. Pretty soon people will stop making them. ] (]) 23:20, 16 December 2024 (UTC)
* This is not new. We've had sporadic "vanity" RfAs since the early days of the process. I don't believe they're particularly harmful, and think that it unlikely that we will begin to see so many of them that they pose a problem. As such I don't think this policy proposal ]. ''']]''' 21:56, 16 December 2024 (UTC)
* This apparent negative feeling evoked at an RFA for a former sysop ''everyone agrees is fully qualified and trusted'' certainly will put a bad taste in the mouths of other former admins who might consider a reconfirmation RFA ''without first'' visiting BN. This comes in the wake of Worm That Turned's similar rerun. ] (]) 23:29, 16 December 2024 (UTC)
*:Nobody should ever be discouraged from seeking community consensus for significant changes. Adminship is a significant change. ] (]) 23:32, 16 December 2024 (UTC)
*::No argument from me. I was a big Hog Farm backer way back when he was ''merely'' one of Misplaced Pages's best content contributors. ] (]) 12:10, 17 December 2024 (UTC)
*All these mentions of editor time make me have to mention ] (TLDR: our understanding of how editor time works is dreadfully incomplete). ] <sup>]</sup>] 02:44, 17 December 2024 (UTC)
*:I went looking for @]'s comment because I know they had hung up the tools and came back, and I was interested in their perspective. But they've given me a different epiphany. I suddenly realize why people are doing confirmation RfAs: it's because of RECALL, and the one year immunity a successful RfA gives you. Maybe everyone else already figured that one out and is thinking "well duh Eek," but I guess I hadn't :) I'm not exactly sure what to do with that epiphany, besides note the emergent behavior that policy change can create. We managed to generate an entirely new process without writing a single word about it, and that's honestly impressive :P ] <sup>]</sup>] 18:18, 17 December 2024 (UTC)
*::Worm That Turned followed through on a pledge he made in January 2024, before the 2024 review of the request for adminship process began. I don't think a pattern can be extrapolated from a sample size of one (or even two). That being said, it's probably a good thing if admins occasionally take stock of whether or not they continue to hold the trust of the community. As I previously commented, it would be great if these admins would use a lower cost way of sampling the community's opinion. ] (]) 18:31, 17 December 2024 (UTC)
*:::{{ping|CaptainEek}} You are correct that a year's "immunity" results from a successful RRFA, but I see no evidence that this has been the ''reason'' for the RRFAs. Regards, ] (]) 00:14, 22 December 2024 (UTC)
*::::If people decide to go through a community vote to get a one year immunity from a process that only might lead to a community vote which would then have a lower threshold then the one they decide to go through, and also give a year's immunity, then good for them. ] (]) 01:05, 22 December 2024 (UTC)
*::@] I'm mildly bothered by this comment, mildly because I assume it's lighthearted and non-serious. But just in case anyone does feel this way - I was very clear about my reasons for RRFA, I've written a lot about it, anyone is welcome to use my personal recall process without prejudice, and just to be super clear - I waive my "1 year immunity" - if someone wants to start a petition in the next year, do not use my RRfA as a reason not to. I'll update my userpage accordingly. I can't speak for Hog Farm, but his reasoning seems similar to mine, and immunity isn't it. ]<sup>TT</sup>(]) 10:28, 23 December 2024 (UTC)
*:::@] my quickly written comment was perhaps not as clear as it could have been :) I'm sorry, I didn't mean to suggest that y'all had run for dubious reasons. As I said in my !vote, {{tq|Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here}}. I guess what I really meant was that the reason that we're having this somewhat spirited conversation seems to be the sense that re-RfA could provide a protection from recall. If not for recall and the one year immunity period, I doubt we'd have cared so much as to suddenly run two discussions about this. ] <sup>]</sup>] 16:59, 23 December 2024 (UTC)
*::::I don't agree. No one else has raised a concern about someone seeking a one-year respite from a recall petition. Personally, I think essentially self-initiating the recall process doesn't really fit the profile of someone who wants to avoid the recall process. (I could invent some nefarious hypothetical situation, but since opening an arbitration case is still a possibility, I don't think it would work out as planned.) ] (]) 05:19, 24 December 2024 (UTC)
*::I really don't think this is the reason behind WTT's and HF's reconfirmation RFA's. I don't think their RFA's had much utility and could have been avoided, but I don't doubt for a second that their motivations were anything other than trying to provide transparency and accountability for the community. ] ] 12:04, 23 December 2024 (UTC)
*I don't really care enough about reconf RFAs to think they should be restricted, but what about a lighter ORCP-like process (maybe even in the same place) where fewer editors can indicate, "yeah OK, there aren't really any concerns here, it would probably save a bit of time if you just asked at BN". ] (] • ]) 12:40, 19 December 2024 (UTC)
== Is the "above 8000 words = split" an absolute rule? ==
====Delete all of the "allegations" articles as violative of ]====
::'''Comment'''- That makes you part of the first category. --<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 19:34, 23 March 2007 (UTC)
:::If anything, it makes him part of the second. Nice try, though. ]<sup><small><font color="DarkGreen">]</font></small></sup> 03:40, 11 April 2007 (UTC)
::::"Nice try"? Please tell me, what exactly am I "trying" to do? In any case, asking for deletion is a change.--<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 04:16, 11 April 2007 (UTC)
I am referring to this chart found on ]:
====Undecided====
# ] 13:01, 29 March 2007 (UTC) Give me more time to think about it, although I am kind of tentatively edging towards the "something needs to be changed" side of the house....
# ] 04:26, 5 April 2007 (UTC) Although I know that disagreements ''there'' are the reason this issue came here, I think the issue of renaming such controversial articles should be handled on each article's talk page (and, if necessary, taken through ]). A blanket policy allowing or rejecting the use of the word "allegations" in titles is counterproductive and would not apply well to the dozens of articles which do or could use the word in their titles.
# ] 16:58, 5 April 2007 (UTC). Each situation must be handled on a case by case basis. That is not to say that situations that are obviously similar shouldn't be handled similarly (e.g. "Allegations of Israeli Apartheid" and "Allegations of Apartheid"). However, disagreements over whether two things are similar (such as Israeli Apartheid and Islamofascism, which I believe should both have "Allegations of..." although others disagree) should not overwhelm the discussion of the articles themselves and become the main focus of attention. Also, "Allegations of..." is sometimes useful as part of a compromise, which is why "Allegations of Israeli apartheid" has the title it has. Many articles on WP have compromise titles (see ] for another example of a title that nobody would have come up with in the absence of a dispute.)
====Comments====
There is nothing wrong with most of the current titles. The topics which there is serious uncertianty about have alleged in them. The ones where uncertianty is uncertian do not. Calling the Holocaust, for example, alleged, is giving undue weight to antisemites.--] 02:12, 22 March 2007 (UTC)
The term is so frequently used in newspaper accounts regarding criminal activity, that it by now has acquired that connotation, and should only be used when specifically criminal accusations that have not yet been decided are the topic Many of the uses are more general, and hence inappropriate.''']''' 02:32, 22 March 2007 (UTC)
*I refuse to take part in a poll which asks me to judge the existence of ] (for example) and ] as equally debatable.] 23:30, 22 March 2007 (UTC)
Pages called "alligations" should be about the alligations, pages without should be about the thing. ] should be about the claim I am a baboon, ] should be a page about baboons themselves. It's not saying something is less true, it's just definieing the focus of the article, is it talking about a thing? or talking about talking about a thing?
::I agree with you. But the problem is, ] redirects to <s>]</s> ], when they are "allegedly" two different subjects. --<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 21:56, 23 March 2007 (UTC)
::I agree, "Allegations of" should be only for articles about the allegations. So what to do about the articles focusing on events? Note that these are primarily not debates over fact (though they include factual disagreements) but debates over naming. So I propose the following division: When a term itself is controversial, "x" and "alleged x" are POV; though the latter is more so. So, when a term is loaded, find a less loaded term, and allow an unadorned redirect (] -> ]). This is true even when an unadorned term is less notable (] -> ]); but NOT when the term is widely accepted (] -X-> ], despite ]); or when the article is primarily about the term itself, not the content (eg ]); or when any less-loaded term is inevitably untenably awkward (] -X-> ]).
::ps. The holocaust is a non-issue, it is verifiable fact by wikipedia standards, the fact that it is also a bit controversial is immaterial. Making it a redirect to some less-loaded term like ] wouldn't even make deniers happy, so what's the point? --] 08:45, 10 April 2007 (UTC)
== Use of international wheelchair symbol ==
This topic has been discussed in a number of places, notably ], but I'd like to get broad community input on this issue.
The issue concerns the use of the ] (ISA) outside its article. The ISA may be freely used to illustrate handicapped accessibility. However, the symbol is copyrighted and so derivative works are not permitted.
Until recently, the ISA was used in places such as ] to illustrate handicapped accessibility. It has been replaced with a crudely drawn (but freely licensed) alternative, ]
So, here is the question: '''Should we permit use of the ISA to illustrate handicapped accessibility in articles and templates?''' Please continue the discussion in this section, and then indicate your position in the poll below. —] <sup>(])</sup> 05:08, 30 March 2007 (UTC)
:I'm confused as to why it is in debate. Yes, it isn't a free image, but any concievable adaptation of the encyclopedia by any entity could use it the way we do, because it may be freely used to illustrate handicapped accessibility. Last I checked, it's pretty unambiguous that "This image may be freely used in situations X, Y, and Z" copyrights are allowed. -] <small>]</small> 05:11, 30 March 2007 (UTC)
=== Poll: Should we permit use of the ISA to illustrate handicapped accessibility in articles and templates? ===
==== Yes, permit use in articles and templates to illustrate handicapped accessibility ====
# —] <sup>(])</sup> 05:08, 30 March 2007 (UTC)
# ]. This is such a non-issue that it shouldn't even have to be up for discussion. Let's return to creating great content. ] 05:18, 30 March 2007 (UTC)
# gives permission to use the symbol "to promote and publicize accessibility of places, programs and other activities for people with various disabilities" and encourages visitors "to place these symbols next to the relevant information in all publications and media". The fact that the image is copyrighted is irrelevant: there is no such thing in Europe as a copyright-free image, except for those on which copyright has expired. The license granted isn't entirely free, but it's about as close as you get. ] 07:19, 30 March 2007 (UTC)
# Yes. Here we have a prime example of image-license wikilawyering being bad for the encyclopedia. ] / ] 07:43, 30 March 2007 (UTC)
# Of course yes. Ridiculous copyright hysteria run amok. ] ] 08:13, 30 March 2007 (UTC)
# Yes. I have worked with people with disabilities in the past, and have found that badly thought-out or stereotyped signs, no matter how well intentioned, can often cause offence, and therefore the most prudent option is to stick to official symbols. – ]<small> ]</small> 17:08, 30 March 2007 (UTC)
# The symbol's copyright is only to protect improper usage. As long as it is being used to denote a handicapped accessible facility or service, we are using it within its guidelines and not violating its copyright. –] 17:15, 30 March 2007 (UTC)
#I believe that it makes sense to slightly modify or clarify our ] to indicate that a limited number of "official symbols" like the ] are not replaceable and do not require specific rationales for each use. This appears to be in line with what Jimbo implied (see below). --] 19:53, 30 March 2007 (UTC)
#It's ''the'' symbol for handicapped accessibility, and is freely usable within that context. (You can even profit from it. Look at those handicapped accessible restroom and parking signs companies sell.) The arguments against using it sound like the sort of thing I might say if I was trying to make a ] against overly strict interpretation of the image use criteria. If this requires a one sentence addition to the fair use policy saying that we can use universal standard symbols for their intended purpose without fear of repercussion, which should be obvious anyway, then so be it. --] <small>]</small> 00:18, 31 March 2007 (UTC)
#This is very much like Crown Copyright, which provides explicit permission provided the material is reproduced accurately and not used in a misleading depiction. The ISA is ''universally recognised'' as the symbol for accessibility. Some random vector someone whipped up in Inkscape is not. This is very much a case where we need to interpret our rules in ''spirit'', and not in ''letter''. There is no violation of copyright law here, as any use to designate accessibility is not only fair, but ''expressly permitted''. ] <small>] </small> 00:23, 31 March 2007 (UTC)
#It appears from the discussion below that this is a ] of Misplaced Pages policy. However, I believe that the policy is intended as a way to ensure that we don't run afoul of copyright law, not as an end in itself. Given our confidence that we are not in fact violating the copyright, and given that there is no reasonable alternative to use of this image, this is an ideal time to ] and do the right thing. ] 01:36, 31 March 2007 (UTC)
#Seems like this is a good time to make one of our rare exceptions to the fair-use policy. --] 07:03, 31 March 2007 (UTC)
#An exception should be made in this case. We need to be as disability friendly as we possibly can. This is easily within our abilities to do, so we should do it. The reasons against seem to be that it's against the rules, nothing more. That means the rules are wrong or incomplete. Using a poor alternative is doing a poor job of being disability friendly. - ] 05:44, 1 April 2007 (UTC)
#Although voting is, of course, evil, I think it's important to point out that the on the subject of nonfree content allows for exceptions "to include identifying protected works such as logos". This is a prime example of the sort of use which should be allowed. Even if the image is technically "unfree", the intent of the copyright holder is clear. If we need to add a sentence to ] to cover this sort of thing, so be it.—] <small>(] • ])</small> 09:40, 1 April 2007 (UTC)
# See my comment below. Yes this image can be used, as long as it's usage is properly documented and discussed. We don't need to change WP:FU for just one exception, as long as the rationale of it's usage is properly noted, the image properly categorized, this discussion is referenced, and enough users sign off on it. --] (] • ] • ]) 18:13, 2 April 2007 (UTC)
##I would like to point out that the scope of the usage of the image should be clearly defined. We cannot use it everywhere, but to say we can't use it ANYWHERE is just stupid --] (] • ] • ]) 09:07, 3 April 2007 (UTC)
# This discussion is ] at this point. There's clearly the ''ability'' to change policy when needed and rational, and people are arguing that we can't change it because... it's not been changed? get over yourselves. -- '']']'' 18:30, 2 April 2007 (UTC)
# Yes. The image is free (as a speech) to use for the purpose we want to use it. It is forbidden to use for the other purposes for the damn good reason. It is morally wrong and probably illegal to use something else for the purpose we intend to use it. What elase can I say? ] 03:36, 3 April 2007 (UTC)
# Yes. I think some people (below) are being way too anal in insisting on policy for policy's sake. Using this image for this purpose is perfectly legal and moral, and doesn't violate either the letter or the spirit of its license or result in anybody being under any risk of being sued. It's technically "unfree" because there are conditions attached to the image, but they are conditions that no reasonable reuse of Misplaced Pages content would violate. ] 03:05, 4 April 2007 (UTC)
# What a fine showcase of ridiculous copyright paranoia. ] 10:35, 4 April 2007 (UTC)
#Create the appropraite exception document and/or modify the policy to celarly permit this any any simialr logos to be used even though copyrighted, provifed that the license or other legal basis for sue is spelled on on the relevant image page (or its talk page), and provided that any such license is complied with, and provided that the rights granted are broad enough that any plausible non-valdalism use on Misplaced Pages will be legal. ] ] 06:14, 5 April 2007 (UTC)
#Since ''any'' potential redistributor can use this symbol to illustrate handicapped accessibility, it's really pointless to say that we can't because it has a non-free license. -] <small>]</small> 06:20, 11 April 2007 (UTC)
#Yes, allow its use. A minority of Wikipedians are pushing their zeal for ''libre'' images to a ridiculous extreme. This is a great example of a good use of non-free image content. ]\<sup>]</sup> 06:32, 11 April 2007 (UTC)
==== No, display the symbol only to illustrate the symbol, do not use it to illustrate handicapped accessibility ====
#Since it appears we are not allowed to use other licences which allow free use of images but do not allow modification, at least on articles of living people (and I'm thinking of ] here), I can't see why we should use this. I don't agree with the policy, but we should enforce it equally.-<font face="cursive" color="#808080">]</font> 08:45, 30 March 2007 (UTC)
==== No, do not have the poll ====
First, we do not vote over policy proposals. Second, this is an issue of copyright law, which is obviously not trumped by consensus. Third, we have rather stringent "fair use and free images" rules for reasons imposed by the board, which means we're not going to use a copyrighted image on templates. I suggest you ask Jimbo to make an exception but he likely won't. By the way there is too "something in Europe as a copyright-free image", for instance those in the public domain or those licensed under the GFDL or somesuch. ] 08:00, 30 March 2007 (UTC)
:Totally agree with Radiant here. ] ] 08:20, 30 March 2007 (UTC)
:Fully agree with Radiant. —]<sub>]</sub> 09:04, 30 March 2007 (UTC)
<small>''Small correction: GFDL content is copyrighted, GFDL is a license for distributing copyrighted information. --] 11:08, 30 March 2007 (UTC)''</small>
:This is not an issue of copyright law, it is an issue of Misplaced Pages policy. We may <u>legally</u> use the image to indicate handicapped-accessible railway stations, Disney rides, etc. The copyright holder explicitly allows the symbol to be used in this way. The question is do we <u>want</u> to do that.
:This poll is to give us a general idea of what members of the community think. No, we don't vote on policy, but a vote can help us get a general idea of where the community stands. —] <sup>(])</sup> 16:48, 30 March 2007 (UTC)
:I'm not asking for free reign to use this as though it were licensed under a free as in freedom license — I am not asking for permission to use this on userboxes or in talk pages. I'm asking whether the community feels that limited use to illustrate handicapped accessibility is (or should be) acceptable. —] <sup>(])</sup> 16:53, 30 March 2007 (UTC)
:Jimbo has been asked: ]. His comments seem to imply that if our fair use policy is changed, we can use it under fair use; but right now, our fair use policy prevents us from using it because it's replaceable and needs a rationale for every use. --] 17:05, 30 March 2007 (UTC)
::This discussion may result in a slight change to the fair use policy, whether it be the letter of the policy or the interpretation. Again, I don't want us to go wild over the use of the wheelchair symbol, but limited use where appropriate would be nice. —] <sup>(])</sup> 17:15, 30 March 2007 (UTC)
:::In the event of the "fair use" policy being changed, it would be good to see that change applied to similar cases - as Gadfium pointed out, Crown Copyright (UK, NZ and other Commonwealth nations), is an analagous situation of reproduction allowed with no modification , and 500 plus images are threatened by recent spate of deletions of crown copyrighted material by free use ideological purists.
:::The present ''Fair Use'' policy is based on US copyright law with some additional restrictions. Unfortunately this
::::1. tends to exclude images from other jurisdictions so increasing the present US content imbalance and
::::2. provides a false sense of security that users of Misplaced Pages images are not breaking copyright or other laws, (some of the crown copyright images have been allowed because they fit within "fair use", when their use could break other nations laws).
:::There appears to be no reason to consider US law superior to that of most other OECD nations, nor for a policy to be based on anyones law at all.
:::The reason/retrospective excuse for a policy based only upon US intellectual property law is that wikipedia servers are based in the US, and "fair use" provides protection for the Misplaced Pages Foudnation against breaches of other nations copyright laws. This reasoning has two flaws - firstly, it does not protect users, as against the foundation, secondly, it does not protect either against laws other than copyright (e.g. defamation).
:::Ultimately I think we need international lawyers involved in a rethink of the whole policy from the ground up. In the mean time, for the little it is worth, my opinion is a common sense solution might be a relaxation the ideological purity of complete "Free use" position. Reuse without modification is hardly the most onerous requirement, and simply tagging this on the image should warn users of the danger and protect Misplaced Pages from liability.
:::If policy in this area is changed a change I would like to see is the abandonment of the Orwellianly loaded terms "Fair Use" and "Free Use", - it appears to me that discussion of change has been chilled because the policy contains the warm and fuzzy but not particularly accurate words "Fair" and "Free". I suspect if a newbie had renamed these policies they would promptly have been deemed POV and reverted :-) Seriously, attempting to discuss the policies seems to provoke at least some readers into irrational knee jerk assumption any one questioning Fair and Free use must be against fairness and freedom. ] 03:43, 1 April 2007 (UTC)
This poll is funny, and it won't change anything. We can't use the symbol, and people would rather argue to use it than make a better looking free version. Holy crap, people, it's not that freaking hard. I mean, just freaking look at it! We can't use the international one, it's painfully clear, deal with it. This isn't even close to being one of those grey areas we usually discuss here, not by a long shot. This is one of the ''most'' obvious situations of when to not use fair use that I've ever seen. -- ] 05:51, 1 April 2007 (UTC)
:The question is not "can we?" It's "should we?" We may legally use the image. This poll, so far, has shown great support in favor of using the image, no matter whether the policy currently allows this or not. —] <sup>(])</sup> 05:59, 1 April 2007 (UTC)
:Any free alternative is inherently going to not be an internationally recognized symbol. Thus, any free replacement will be inferior to the International Symbol of Access. —] <sup>(])</sup> 06:01, 1 April 2007 (UTC)
::Legal issues don't matter, our policy, our non optional policy, says no. Being "inferior" is an absurd thing to say. How is it inferior? It might not look as pretty, but that's not significant. It doesn't matter how many people disagree with the policy, it's our policy, and it's been set by the Wikimedia Foundation itself. It's out of your hands, and the poll completely lacks the authority to do anything about the matter. Sorry, but that's the way things are. -- ] 07:01, 1 April 2007 (UTC)
:::We're talking about adjusting our policy. Again, the only argument against is that our rules say so. If there's no other reasoning, we should change our rules. The poll will be a good thing to take to the foundation, if they're the ones who have to decide. Finally, the free image is inferior because it isn't a recognized symbol. - ] 07:14, 1 April 2007 (UTC)
::::I doubt anyone won't understand what the free image is implying, and because of that we don't ''need'' an internationally recognized symbol. We're not actually helping handicapped people by using this image, and we shouldn't be. Misplaced Pages is not a directory, or a guide for the handicapped. People don't need to use Misplaced Pages to see if handicapped parking is available at some train station. Even if they do use it, which we can't really stop people from doing, it's plain as day what the free image means. -- ] 07:32, 1 April 2007 (UTC)
:::::But hey, whatever, if you guys want to give the Foundation your poll results, ok. But until they change our policy (which is not limited to just Misplaced Pages, but to all Wikimedia projects), we can't use the image. -- ] 07:35, 1 April 2007 (UTC)
A passionate defense of nonsense, Ned; appropriate for April 1st... Side note: Is this not the classic case of ]? Aren't we supposed to use independent thought to judge and balance these issues? Shouldn't, in this one case, ] trump ]? ] ] 07:59, 1 April 2007 (UTC)
:No, IAR is not a loop hole that anyone can just use when they don't get what they want. Free content is the very reason Misplaced Pages (and it's predecessor, ]) was started. Asking to be exempt for such minor situation in face of that is just absurd. Continue to discuss if you want, but those who violate our policies will be dealt with accordingly. -- ] 08:19, 1 April 2007 (UTC)
::Dealt with accordingly??? Accordingly to what? And by who? You? Oh, dear god, PLEASE sign me up for an accordingly dealing. (Does it involve Jimbo reading me the from "Freedom Defined" over and over again until my ears bleed? (Its hysterical (in every sense) reference to "God-like creators" seems to indicate ] is certainly not in effect there...)
::I love that ] is a policy... which, apparently, is only a joke, and is NEVER supposed to be actually used. "Heh, heh, you don't really believe all that stuff about ignoring stupid rules to help make Misplaced Pages better, do ya?" Uh, yeah, I do. That's why ] is a policy -- and asking you to have an original thought about this matter has apparently scared you so much, you can only fall back on another policy, which you must believe is somehow "immune" from the reach of ]. I'm not talking about using ] to turn Misplaced Pages in to the world's number one fan site; I'm talking about a one-time use of a sensible "check" on the insane dedication to a contradictory and messy set of unencyclopedic fair use standards. A dedication which is, in this case, emperically HURTING Misplaced Pages, by making it non-standard, non-International, and disabled unfriendly. But how can you process any of that? I mean, you have a very simple "program" - "Copyright = bad. No use on Misplaced Pages." Which is fine, and all, but both common sense and the law would permit the ISA's use on Misplaced Pages. I urge you to stand with common sense and the law, and perhaps, just maybe, realize that the answers to all of life's problems can't be found in ]. ] ] 08:45, 1 April 2007 (UTC)
:::It means you'll get banned for breaking the policy. If you use the copyrighted image, get reverted, and keep trying to use it, you will be blocked. You obviously don't understand a fundamental point here on Misplaced Pages, that our fair use restrictions are actually more restrictive than the law requires, not because of legal issues, but because our goal is to have all of our content under the GFDL. There's no major benefit to using the copyrighted image. Now you're resorting to inappropriate personal attacks on me because I'm simply telling you the facts of the situation. It's laughable to think that we would bend our fair use policy over something so trivial. You've completely missed the point. You're all hung up on something that isn't even an issue. No significant improvement will come from using the "official image" at all. Your argument is weak and lacks logic. Misplaced Pages will not be better for using another fair use image, it will be worse for using another fair use image. We are about promoting free content and using free content whenever possible, and only using copyrighted content when we have no other options. You are disagreeing with a fundamental value of Misplaced Pages. -- ] 08:59, 1 April 2007 (UTC)
::::And really, who cares if it's blue or not, or exactly the same image. It doesn't matter, EVERYONE will know exactly what it means. Are you really going to fight this tooth and nail, over something so absurdly unimportant and insignificant? You want us to bend the rules for ''this''?? Are you batshit insane? -- ] 09:01, 1 April 2007 (UTC)
:::::Ned, it's not batshit insane to say that it's appropriate to use a nonfree image ''that has been released by the copyright holder for exactly this sort of use'' — especially in light of the on unfree content, which allows exceptions "to include identifying protected works such as logos". It is reasonable to say that a crudely drawn substitute is ''not'' an acceptable alternative, because the ISA ''is internationally recognized'', and the crudely drawn susbtitute is not. The Foundation's resolution says that nonfree content "must be replaced with a freely licensed work whenever one is available which will serve the same educational purpose." A reasonable argument can be made that the crude substitute ''does not'' serve the same educational purpose as the ISA. So please, refrain from calling people making reasonable arguments "batshit insane". —] <small>(] • ])</small> 09:47, 1 April 2007 (UTC)
::::::But this is specifically about incidental use of the symbol without any educational purpose. The issue is not to remove the symbol from ], but not to use it in an infobox of e. g. metro stations. There, the non-free symbol serves no educational purpose, which can be done just as well by a free symbol; therefore, it must be replaced. The symbol is also not an ‘identifying protected work’ in that context. —]<sub>]</sub> 10:11, 1 April 2007 (UTC)
::::::Josiah, they're talking about using the image in templates and stuff, like for train stations. I have no problem with using the image in articles that discuss the image. -- ] 10:59, 1 April 2007 (UTC)
:::::::I understand that. I maintain that the use of the ISA in templates to identify handicap-accessible locations and facilities ''is'' an educational use, because it establishes in a clear, unambiguous, internationally recognized manner that the facility in question is handicap-accessible. The substitute image does ''not'' perform that function; nor would a text message, which would not be accessible to non-English speakers. Yes, we are the English Misplaced Pages, but that doesn't mean that we should refuse to use internationally recognized symbols which we're legally entitled to use. —] <small>(] • ])</small> 18:53, 1 April 2007 (UTC)
::::::::A text message in English ''would'' perform this function perfectly, since we are the English Misplaced Pages. That there are other means to express the same thing shouldn’t bother us especially if those means are in contempt of very basic policy. —]<sub>]</sub> 19:15, 1 April 2007 (UTC)
::::::::I'm dumbfounded at your response, Josiah. Our content is supposed to be free of copyright red tape, so that you can use it for anything, educational, commercial, whatever. We don't allow educational-use only images (unless under WP:FU) or even images that people specifically for Misplaced Pages-only use (such images can even be speedy deleted). Misplaced Pages is specifically stricter than the law requires, because we're about free content. WP:FU isn't how it is because of the law, it's that way to prevent needless copyrighted images in a free-use project. This is so fundamental that it hurts my head. -- ] 20:44, 1 April 2007 (UTC)
:::::::::My point is that this is ''not'' needless — it is offensive to substitute something that looks a bit like an internationally recognized symbol but ''isn't'' it, when there is no good reason not to use the internationally recognized symbol. It's like representing a country with an image that looks a bit like its flag, but isn't. If ] were copyrighted and ] were free, would it be acceptable to use the latter in UN-related articles? After all, it looks a bit like the UN flag. —] <small>(] • ])</small> 21:38, 1 April 2007 (UTC)
::::::::::I'm sure I've covered this already, but unless you know something I don't, using an alternative image in place of the ISA will not be offensive (why the hell would you think it would be?) to people who are disabled. Disabled people don't have an attachment to that image, it's just an informational icon. It's not a flag, it's not a symbol of hope, it's just a damn icon to tell you if there's a ramp somewhere or if there's closer parking spaces. Other people and places commonly use alternative symbols to note disabled access all the time, and do so without incident. -- ] 00:44, 3 April 2007 (UTC)
:It's clear that it's legal to use the ISA. It is not clear to me that it is legal to use a similar "free" image, as that might be considered a derivative work which is not allowed by the copyright holder's release. ] 15:41, 1 April 2007 (UTC)
::A derivative work is just that. A work which is similar to another work but was created independently isn’t derivative. —]<sub>]</sub> 19:15, 1 April 2007 (UTC)
:::It seems like this is a gray area where it's hard to tell if we have a derivative work or not. - ] 19:22, 1 April 2007 (UTC)
::::I'm not a legal expert, but the concept of a stick figure in a wheel chair is one of those things.. OfficeMax used to have a mascot that was a little stick figure, noted by a unique marking on his head. Other stick figures are ''very'' similar, but obviously OfficeMax can't make the claim that those stick figures infringe on their copyright. I'd think that same logic would apply here. -- ] 20:49, 1 April 2007 (UTC)
Does fair use even apply? If the image isn't used on a page that discusses the image, then it seems like it doesn't. We wouldn't be using the image under fair use, we'd be using it accordin to what its copyright grants. It isn't going to be released since it's copyright allows anyone to use it, as long as they're designating something that's handicapped accesible. If it were made free, it could be misused to lable something that isn't handicapped accessible, so it isn't going to be released. I wouldn't even want it released. The only change would be that people could misuse it. We should just explain its status on the image page, and then use it for anything that is handicapped accessible. There doesn't seem to be a tag for this sort of thing, so not sure what to do there. - ] 17:25, 1 April 2007 (UTC)
:Content on Misplaced Pages is supposed to be used for anything, educational or commercial. This is why we can't use images that allow for education use only without a fair use rational. Fair use is the ''only'' way we could use this image. -- ] 20:36, 1 April 2007 (UTC)
::Ned, we're suggesting that this image might be in a third category: unfree, but not fair use. The Foundation's allows us to create an Exemption Doctrine Policy (EDP) for unfree content. These exemptions must be limited according to item #3 of the resolution:<blockquote>3. Such EDPs must be minimal. Their use, with limited exception, should be to illustrate historically significant events, to include identifying protected works such as logos, or to complement (within narrow limits) articles about copyrighted contemporary works. An EDP may not allow material where we can reasonably expect someone to upload a freely licensed file for the same purpose, such as is the case for almost all portraits of living notable individuals. Any content used under an EDP must be replaced with a freely licensed work whenever one is available which will serve the same educational purpose.</blockquote>The ISA is clearly an example of "identifying protected works such as logos", and we would be within our Foundation-delimited rights to include it in our EDP. At the moment, en.wikipedia's EDP is ], and obviously the vast majority of nonfree content on Misplaced Pages would be determined by our "fair use" policy — but "fair use" is immaterial to the use of this image, whose copyright ''explicitly allows the uses for which we, and downstream users, would use it''. I, and others, are proposing that en.wikipedia's EDP explicitly allow the use of the ISA and other copyrighted international symbols whose use is uncontroversial in any other context.
::Ned, you say that you're flabbergasted by my response. I'm somewhat puzzled that you apparently don't see how using a different image in place of the ISA is problematic. If it's sufficiently unlike the ISA not to be a copyright violation, it's potentially confusing and/or offensive to disabled people, who know, use and rely on the ISA. If it's close enough not to be confusing and/or offensive, it's a derivative image. Either way, we're better off using the image itself, and adjusting our EDP accordingly. —] <small>(] • ])</small> 21:38, 1 April 2007 (UTC)
:::I've explained in private to Josiah just how close I ''do'' know about disabled people. There's no risk of confusion, and the offensive concern is not an issue. I'm really not sure why one would come to the conclusion that using a different image would be offensive. I've even seen different images be used to indicate disabled parking, ramps, etc, and they're purely informational, nothing emotional or significant about them. These are not flags, and disabled people do not have an attachment to the ISA image. I don't know why anyone would come to such a conclusion, and I know you don't mean anything bad by that, but if I were disabled I'd be a little offended at your view. Why would you think that this image would be.. "holy" (or whatever) simply because it's used on maps and parking spaces? You've got it all wrong, offensiveness isn't a factor in this at all. No one's feelings will be hurt, no one will be offended. -- ] 04:26, 2 April 2007 (UTC)
=== Q & A ===
Is this image 'free' (in the ''libre'' sense)? Nope. There are restrictions on its use.
Is this a bad thing, or a reason not to use it on Misplaced Pages? Nope. In fact, it's what makes it worthwhile as a symbol—its meaning is clear because of its licensing terms.
Is there any reason why we would want or need to use the symbol in a way that is prohibited by its license? Nope.
Is this a 'fair use' issue? Nope. We would only be using the image in a way explicitly permitted by its license. 'Fair use' is a defence to a charge of copyright infringement; it would only be an issue if we were violating the license terms.
Wait—it's selfish to only think about our own use. What about people who redistribute Misplaced Pages materials for a profit? They're covered. The image can be redistributed in commercial materials as long as the terms of its license are followed.
Ah, but they can't freely modify the image, create derivative works, or use it without restriction. What about those people? Sucks to be them. If they want to abuse the International Symbol of Access to fuck with the mobility challenged, screw 'em. Misplaced Pages tolerates hundreds (thousands? more?) of Crown Copyright images which are free for use in educational materials, but require permission for commercial redistribution. Misplaced Pages tolerates thousands of non-free, copyrighted images under very tenuous 'fair use' claims. We expect that when people make copies or derivatives of articles incorporating these images, those people will take appropriate care to check the licensing of all the images on the page. Here, with the ISA, we have an image being used appropriately and which will likely propagate without harm into reasonable derivative works and commercial copies. Why are we choosing to get stuck on this particular point? ](]) 19:59, 1 April 2007 (UTC)
:Does anyone know what tag should go on the image page? - ] 20:12, 1 April 2007 (UTC)
:Images with ‘tenuous’ fair use claims should be tagged accordingly or sent to ]. Other crap exists, but that’s not a reason to add to it. What about people who find themselves hindered by the third ]? Well, sucks to be them. —]<sub>]</sub> 20:14, 1 April 2007 (UTC)
::Please explain how this is fair use. - ] 21:16, 1 April 2007 (UTC)
Images on Misplaced Pages are either ''free'' on ''unfree''. '''There is no inbetween'''. This is en policy and was recently clarified in the foundation's licensing resolution, which states that images must be free (as in ''libre'', which the ISA is not), or covered by an EDP, which is for the limited discussion of copyrighted works.{{unsigned2|21:57, April 1, 2007|Ed g2s}}
:Please read the Foundation resolution about what EDPs can and can't cover. As I noted above, the Foundation allows us to use nonfree content for "identifying protected works such as logos". There is no reason not to adjust our EDP to allow use of this image, in accordance with the limits the Foundation has set. —] <small>(] • ])</small> 22:07, 1 April 2007 (UTC)
:: is interesting. Has anything besides Free and FU been discussed before? - ] 22:34, 1 April 2007 (UTC)
::Our policy already allows for "identifying protected works". Its use on the ISA article is not being debated. Using it as a replacement for the text "disabled access available" is '''not''' "identifying protected work". <span style="font-family: Verdana;">] • ]</span> 01:51, 2 April 2007 (UTC)
:::We wouldn't be using it under fair use protection. We'd be using it under the rights granted to us by its copyright. - ] 02:11, 2 April 2007 (UTC)
I have an idea. Let's ban the use of the ] and the ]. After all, they're subject to the and not licensed under the GFDL, so they must be worthless and a detriment to our cause of creating free content. —] <sup>(])</sup> 03:06, 2 April 2007 (UTC)
:::Actually, the Misplaced Pages logos have been removed and taken down from many pages, banners, and such for those very reasons. ] used to be the Misplaced Pages logo, but because it wasn't a free image we took it off. Most people don't realize that Misplaced Pages's logo is not free use, which is pretty much the only reason we haven't taken it down from non-official uses, or uses unrelated to guidelines, policy, etc. -- ] 04:30, 2 April 2007 (UTC)
:So what's the best way to take this to the foundation? It looks like if it was up to us, we would have a consensus to use it to identify handicapped access. At the least, we have a consensus to ask. Jimbo's page doesn't seem like the best place. The last time we tried that, it devolved into snarky comments, and he seemed to tune out. We should probably include the International Symbol for Deafness, and other symbols in our request. - ] 03:26, 2 April 2007 (UTC)
:: --] 03:40, 2 April 2007 (UTC)
:::If you choose to e-mail them, please emphasize that the ICTA is not going to release this under a free license because they surely only want it used to identify handicapped accessibility. They would not be happy if people abused the image to mark non-handicapped-accessible things with this symbol. That would undermine the value of the symbol as an international identifier of handicapped accessibility. —] <sup>(])</sup> 04:12, 2 April 2007 (UTC)
OK, let's use the mailing list. Since this is where we're talking about it, let's discuss what points need to be made. I'll try and list the pros and cons so far. Copying some of the words used in the discussion so far.
Pro:
:Using it to designate handicapped accessible objects does not violate its copyright.
:The ISA may be freely used to illustrate handicapped accessibility. The symbol's copyright is only to protect improper usage. As long as it is being used to denote a handicapped accessible facility or service, we are using it within its guidelines and not violating its copyright. It's copyright explicitly allows the uses for which we, and downstream users, would use it.
:Its meaning is clear precisely because of its licensing terms.
:Stereotyped signs, no matter how well intentioned, can often cause offense.
:It is non-replaceable, except by ] or words such as "wheelchair accessible." These are not internationally recognized symbols.
:You can profit from it. Look at those handicapped accessible restroom and parking signs companies sell.
:It is universally recognised by design and common usage over many years.
:It's use would be disability friendly.
:The wikimediafoundation does sometimes allow with an EDP, which currently is ]. FU doesn't speak to this issue.
:It would not be used in userspace.
:It is easily recognised by non-english speakers.
:Using ] may not be legal, as it may be a derivative work of the ISA.
:It is unlikely to be made free because it's copyright's only restriction prohibits its use to designate objects that are not handicapped accessible. Making it free would remove this restriction. They would not be happy if people abused the image to mark non-handicapped-accessible things with this symbol.
Con:
:It's not free, and it wouldn't be used under fair use, unlike all images on wikipedia.
:The symbol is copyrighted and so derivative works are not permitted.
:We have a substitute image ], or can use text such as "wheelchair accessible."
:It's use would be a violation of Misplaced Pages policy.
:Since we don't allow other free uses of images which which allow modification, we shouldn't do it in this case.
:While it wouldn't be used in user space, it could be used in a template, and wouldn't have a (free use?) rational for each page.
:They're may be international issues that are not raised in US law.
:Misplaced Pages is not a guide for the handicapped.
:It's use is not important.
:It serves not educational purpose.
:Our goal is to have all of our content under the GFDL, which this image would not be.
:Images on Misplaced Pages are either free on unfree. There is no inbetween.
Did I miss anything important? - ] 04:30, 2 April 2007 (UTC)
::I'm still baffled by this idea that not using the ISA image would be offensive. I'm not being rude here, I honestly am baffled. Have any of you known or lived with a disabled person? Also, while the ISA owns the blue wheel chair image with a stick figure, they can't make claim to ''every'' stick figure wheel chair image. Do you think that anyone was offended/confused, or even gave 2 seconds of thought, to images like these: , , , , , ? No disabled person is going to be angry or confused when seeing these other images in real life, on streets, maps, restrooms, rides, or ramps, why would they be? You guys need a touch of reality here, and you're making an issue out of nothing. Your over anticipating and trying to preemptively be PC for someone that most people, disabled or not, never even thought was an issue. -- ] 04:45, 2 April 2007 (UTC)
:::First, I've never lived with a disabled person. I'm not going to say I'm offended, but the fact that our policies prevent us from using these easily understood symbols is troubling to me. My guess is that when someone sees our version of the wheelchair, they'll think that it probably means disabled access, but they won't be sure. People who don't know they can click on the image and gain additional information will remain slightly unsure.
:::Those image links you provide seem to be standard uses of the ISA. If using a red version like is legal, but not restricted by the ISA copyright, I would be cool with that. We can just use red versions of all the disabled access symbols. I think they're all just legal uses of the ISA, though.
:::Will disabled people be pissed if we don't use the standard symbols? Some yes, some no. As we know, WP is mostly edited by able bodied white mails aged 15-45, or something close to that. We're not going to be good judges of what's best for the disabled. Because of this, I think that if we go out of our way to help the disabled more than seems necessary to us, then we'll be getting closer to what's right. We discuss FU vs. Free Use all day, and that makes it seem very important. If you were disabled all day, that would seem important. - ] 05:23, 2 April 2007 (UTC)
::::I'd go farther than that and say most disabled wouldn't even give which image used significant thought. We have no evidence to show otherwise, and only wild and unproven speculation. I'm not willing to "prove" my own experiences with such situations, for privacy reasons, but this is the first I've ever heard someone even suggest that a person might be offended because the disabled icon isn't ''exactly'' the same. It's really nice that you guys want to go out of your way to help people, but doing this.. thinking that it is helping disabled people, that's not what's happening. You're not hurting them.. but it's just kind of.. null. That's like me blowing at a house that's on fire, with my mouth, thinking I'm helping. Good intent, but at the end of the day it honestly makes no difference. Really, I'm not making this up. You guys have nothing but unfounded speculation to come to these conclusions. -- ] 05:42, 2 April 2007 (UTC)
:::::I'll give to you that this discussion is opinion, same as all talk page discussions. I don't know what you mean about proving your own experiences, but even if you yourself are disabled, that doesn't mean you speak for a whole segment of society. I just think we should err on the side of helping disabled people. This is something that some of us think will help disabled people, which isn't silly. Maybe this doesn't make that big of a difference in the lives of disabled people. I don't think that means we shouldn't try. Some things help the disabled a little, and some thing a lot. I say do both, if they don't hurt us. We should do everything we can, and this is easily within the power of the foundation, so we should do it. - ] 06:06, 2 April 2007 (UTC)
::::::While it's true that even if I was disabled (I'm not) that I wouldn't be able to speak for all disabled people (calling them a segment of society is a very inaccurate way to profile disabled people, who are individuals and have their own views), having ''some'' experience with disabled people would seem to trump no experience whatsoever. I don't mean to try to speak with authority, I just mean to point out that there's no evidence to support that there would be any confusion or cause of any offense. Your heart is in the right place, but using the ISA image on things like templates for Disneyland is painfully insignificant to a disabled person's life. We don't bend the rules just because you mean well, because in the end you're still wrong. -- ] 00:40, 3 April 2007 (UTC)
:::I would call all of those examples derivative works of the ISA, except and possibly . The legality of derivative works is questionable, but it doesn't look like the ICTA is concerned about them because they are only being used in the context of illustrating handicapped accessibility. Thus, the restrictions the ICTA imposes on creation of derivative works of the ISA appear to be fairly relaxed. This is another thing to mention in the case for permitting use on Misplaced Pages.
:::I doubt that any free replacement would be used outside Misplaced Pages, even if the two symbols are of comparable artistic quality. It may seem counterintuitive to readers to use a symbol completely different from the one actually used in the real world. Thus, there is value in using the internationally recognized symbol in order to maintain consistency with the rest of the world.
:::The symbol is copyrighted for a very good reason. Do you deny this? If you do not deny that it's copyrighted for a good reason, then why should we refuse to use it in our project? —] <sup>(])</sup> 06:02, 2 April 2007 (UTC)
::::My point in showing the other images was to show that people often use images that are similar but not the exact same as the standard ISA image, and do so without any incident whatsoever. We do not need a white on blue stick figure that is exactly like the ISA one. It won't seem counterintuitive to readers, there won't be confusion, because it's so minor no one will give it any thought. You have no evidence at all to support your speculations, and are blindly ignoring common sense. -- ] 00:33, 3 April 2007 (UTC)
:::Wow, lengthy debate here. The point is that the Foundation tells us to use free images whenever possible. We can use a free image here rather than a copyrighted one. That's the wiki philosophy. ] 09:25, 2 April 2007 (UTC)
Lol, this discussion is just stupid and pointless beyond belief !!! And Jimbo saying that we can't use the image without changing the FU policy is even more STUPID (Sorry Jimbo, i really do feel so). We don't have a tag for it ? MAKE a tag !! We don't have policy that says we can use it? MAKE it a policy that we can use this specific image!!! To say that we need to explicitly have an exception to the policy is just stupid for a single image. We could have 20 respectable editors sign of on it on the Image page and say: "It's ok to use this copyrighted image, in relation to disability topic within wikipedia etc etc etc." Categorize it as copyrighted image, Categorize it as "free to use, not to edit" and get it done with. This is Misplaced Pages bureaucracy that is pointless and disrupting even. Get over yourselves and over Jimbe (Jimbo is not WikiGod) --] (] • ] • ]) 14:44, 2 April 2007 (UTC)
:By the way, if you haven't yet signed the poll, I would like it if you would do so so that we can get an idea of the number of people agreeing and disagreeing. Another way to phrase the question would be "do the benefits of using this image outweigh the copyright restrictions?" Many of us say yes, and many say no. By all means, continue to discuss the issue. However, without signing the poll, it's hard to tell whether 90% or 50% of users support using this image. This is a question hard to decide by consensus, so it would really be helpful if we could at least identify strong support for one side or the other, see ]. —] <sup>(])</sup> 16:54, 2 April 2007 (UTC)
::You can't force people to use a survey. It's pretty obvious that we have tons of editors that would disagree with the usage you are trying to promote. My guess is a lot of people don't even think this is worth the trouble to talk about. It's that simple. -- ] 00:33, 3 April 2007 (UTC)
:::Actually, by my estimate, approximately 75% of the Wikipedians who have took place in this discussion have supported using the ISA to indicate handicapped accessibility. If you are claiming that the silent majority supports your position, then let me reiterate to you that the silent majority is ''silent'', i.e. they haven't told us what they think.
:::I'm still waiting to hear your position on using the unfree Wikimedia logos in places such as ], ], ], ], ], and ], not to mention ''every single page on Misplaced Pages''. —] <sup>(])</sup> 02:39, 3 April 2007 (UTC)
::::You'll have to ask the Foundation, but my guess would be that the logo can be used for operational tasks of Misplaced Pages, but not as actual article content without a rationale. But for all we know, we should take them out of those templates too. The logo was ] for years before it was finally taken out. Most people don't even know the logos are not under the GFDL.
::::As for the sidebar itself, that is not considered to be part of the article document, just a part of the page displaying the content. About.com can display their copyrighted logo along side their mirrored copy of Misplaced Pages content, because the article is not "the entire window". The entire window is just how the end product is produced, nothing more than a UI, and the article is within the UI.
::::As for the silent majority, you can't just ignore past discussions about similar issues simply because it's not in -this- discussion. We do not ignore the thoughts and concerns of our fellow Wikipedias just because they can't watch every possible discussion, especially when we know they have strong positions on such matters. Do you honestly think we can't round up an assload of Wikipedians to push that little survey the other way around by simply making this discussion better known? A poll, even if recent, does not just debunk previous discussion or well known arguments of active Wikipedians. Like I said before, no one has probably bothered to get more attention to this discussion, or has seen the discussion but passed it up, because many of us feel this is such a minor and obvious issue. Keep pushing the issue if you really want to be proven wrong so badly, but I'd rather you not, for the sake of using all of our time more wisely. -- ] 03:15, 3 April 2007 (UTC)
:::::Where are these past discussions? Who participated in them? How similar are they to this instance?
:::::You assume that these other Wikipedians support your position and that is why they are not commenting. However, Wikipedians such as ] and ] indicated the exact opposite, saying that it is very clear that we should be able to use this image. Even if the other Wikipedians are all rolling their eyes at this discussion and staying aloof from it, their disinclination to participate does not indicate support for one side or the other.
:::::You may be surprised to know that I sent out notices to several editors who participated in previous discussions about this exact same issue, and that there is currently ] open on this topic. By all means, please inform other editors who you think would like to participate. We could even open a ], although unless I misunderstand the policy, all 24 (by my count) Wikipedians who have commented would have to sign off on it. —] <sup>(])</sup> 05:26, 3 April 2007 (UTC)
::::::Guessing what wikipedians who aren't commenting think isn't binding, obviously. But, my experience with these wikipedia name space talk pages is that this is where the strict interpretation crowd hangs out. It would be cool if we could get a watchlist notice like WP:ATT has right now. I think the more diverse the group of people brought in, the higher the proportion of support for these images would be. The proportion of support is actually enormously high considering who traffics these page. - ] 05:56, 3 April 2007 (UTC)
:::::::A watchlist notice is an interesting idea, but we should wait until the ] controversy blows over before putting up another notice. That way, we'd be less likely to anger Wikipedians over overuse of that mechanism. And by that time, we may already have this discussion resolved. —] <sup>(])</sup> 06:04, 3 April 2007 (UTC)
::::::::Yeah, we don't want to try and do the watchlist thing now. Maybe after this discussion plays out, and if we have a consensus, we should implement the changes in policy that we've been discussing. It seems like Jimbo and rest of WP didn't even notice the whole WP:ATT merge until after it was done. After that, we can discuss the watchlist notification if people have a problem. - ] 06:31, 3 April 2007 (UTC)
:::::::::I seriously doubt they'd make a watchlist announcement for something like this. If you guys really want to get down to business then I suggest we make this a little more organized and less poll-ish, maybe using a separate, structured discussion, RFC page (summaries on one side, structured discussion on the talk side). We might also get some good insight by asking for comments from Wikipedians listed in ]'s subcats. Feel free to even keep counts and comments that are already existing, but right now the discussion is all over the place and needs to be a little better formatted. I still think it's a waste of time, but it might be a good lesson for you guys. Remember, you can have good intentions but completely miss the point, especially when you don't have a clue about what you're talking about in the first place.. -- ] 07:14, 3 April 2007 (UTC)
::::::::::An RfC might be a good idea. What's the procedure for keeping counts and comments from what's happened before? - ] 07:29, 3 April 2007 (UTC)
:DJ, the issue is when the image isn't being used in articles about disability, instead being used in articles like ones for Disneyland rides (in the infobox, with only the icon being shown). -- ] 00:33, 3 April 2007 (UTC)
::Disneyland rides are just one possible use, and probably a minor one. If we can get the copyright stuff figured out, we could include any of disability access symbols on appropriate pages. Things like museums, libraries, television programs, and books. - ] 01:00, 3 April 2007 (UTC)
:::For a moment, lets say all of these images are free use images and we have no such problem. The images are being used as if we were some kind of travel guide, rather than helping article content. Just because the ''guide'' seems like it's for a good cause doesn't make it any less of a guide. Now, I'm sure we don't need to take out stuff simply for that reason, as long as it doesn't get out of hand then who cares if Misplaced Pages helps you find a handicapped ramp, but that's a secondary concern that is outside of the article's real content. Don't forget that we are an encyclopedia, not a place to dump every possible tid bit of info. Information for disabled people is abundant and easily accessed for the kind of uses you guys are talking about, and there's no demand for us to fill this ''extra'' role. -- ] 03:24, 3 April 2007 (UTC)
::::It seems like encyclopedic information to me, when used within an already encyclopedic article. A list of disability accessible whatevers would seem to be more of a guide. Also, because other sites may have similar info doesn't mean we shouldn't. - ] 03:43, 3 April 2007 (UTC)
::::] is an example of its use; essentially it makes the table smaller than saying "handicapped accessible". --] 03:54, 3 April 2007 (UTC)
:::::I could see how having this information for the NYC subway might be helpful to researchers of disability accessibility and as such I think it belongs in wikipedia --] (] • ] • ]) 11:43, 3 April 2007 (UTC)
::::::Alright, I can see that point, but that doesn't require the use of the ISA image. There's no reason, other than convenience and appearances, that we can't use text, which would tell ''everyone'' what is being noted, not just those who know what the image means (most people know it's something for disabled people, but often they think it's a wheelchair only sign, etc). The ISA image isn't the most informative option simply because it's a graphical symbol. Blind people using text readers won't be helped by the image, but I guess it's ok to ignore ''those'' disabled people. -- ] 20:23, 3 April 2007 (UTC)
:::::::I disagree. It's such an international symbol that it IS better then text. And I think it's a very bad reason to in this specific case not allow usage of such a logo just because of our Fair Use policy. Also for blind people there is the "alt" attribute of the image and the mousehover text. --] (] • ] • ]) 23:35, 3 April 2007 (UTC)
::::::::Im admittedly jumping in late to the party here, but the goal of wikipedia is a freely reproducible, usable encyclopedia. Sure, all the uses '''we''' have for the symbol are legit, but by the GFDL we have to give all downstream users of the 'pedia the right to modify it, and this breaks that. Fair use is a neccesary evil in cases where free alternatives are available. This has a free alternative. Using this is just blatent disrespect to the liscense of our work where there need be none. And the notion that disabled people would be offended would be shocking if it werent so patently absurd. Its hyperbole from an undefensible posistion. Look in the top right corner of the page, you see our logo and the text ''Misplaced Pages: The 💕''. That doesn't mean no cost, that means freedom. Get off your mock-indignation that we actually intend to support free culture and use the freely liscensed wheelchair image. -''']</font>'''<sup>]</font></sup> ] 00:31, 4 April 2007 (UTC)
{| style="float:right; background:none;"
|-
|-
! Word count
{{userbox|orange|yellow|]|This image may or may not indicate disability services.}}
! scope="col" | What to do
|-
| > 15,000 words || Almost certainly should be divided or trimmed.
|-
| > 9,000 words || Probably should be divided or trimmed, though the scope of a topic can sometimes justify the added reading material.
|-
| > 8,000 words || May need to be divided or trimmed; likelihood goes up with size.
|-
| < 6,000 words || Length alone does not justify division or trimming.
|-
| < 150 words || If an article or list has remained this size for over two months, consider merging it with a related article.<br /> Alternatively, the article could be expanded; see ].
|}
|}
:::::::::It's the classic free vs. encyclopedia argument. I guess you feel the free part is more important in this case. Other people here feel the free alternative (assuming it isn't just a derivative work) doesn't do the job well enough. The are free, as long as they're used to identify disability services. You can even make derivative works such as , as long as it is used to identify disability services. The reason why the real images should be used is because a person can be sure that it isn't identifying something without the correct services, precisely because of its copyright restrictions. - ] 01:00, 4 April 2007 (UTC)
(unindent) Thats frankly not my call to make, it's Jimbo's and he's been quite clear on that. I dont know if you remember way back, but there were fair use images everywhere till the Foundation approved rampage got most of them. It's why 'Misplaced Pages is Free content' is one of the ] deemed the core essence of wikipedia. And while you're here, its Jimbos world, you just play in it. Got a problem with it? Because of that wonderful GFDL, you are perfectly welcome to fork the project and start your own. -''']</font>'''<sup>]</font></sup> ] 02:02, 4 April 2007 (UTC)
:We're just discussing it and hoping to get the foundation to think about it, and possibly grant us an exception for these symbols. - ] 02:29, 4 April 2007 (UTC)
::I thought allows each project to set its own Exemption Doctrine Policy, without nailing down firm rules about what will and will not be permitted by these policies. —] <sup>(])</sup> 04:11, 4 April 2007 (UTC)
:::Just to jump in again. Isn't our own wikipedia logo copyrighted ??? I mean how hypocrytical would that be. You say to use a (forbidden) derivative work of an internationally recognized logo, a logo which is internationally freely usable to identify accessibility issues, whilst not even having your own logo using the same "standard".... Sorry, but this is just laughable. You cannot say that the wikipedia logo not being GFDL is "rightful" and then the ISA logo, which i'm 100% sure is more free then the wikipedia logo is not usable. And I checked, the wikipedialogo is in use ALL OVER the place where it might not be 100% compatible with the current license for downstream usage. --] (] • ] • ]) 13:58, 4 April 2007 (UTC)
Above, someone wrote, in defense of not using the ISA, ''This has a free alternative...'' Not really. Just because someone makes their own non-standard, non-Internationally accepted version of the handicapped access symbol doesn't make it an "alternative." It is, however, non-standard, and non-Internationally accepted... not unlike my own Stop Sign design I'm hoping will become the new standard. ] ] 02:46, 4 April 2007 (UTC)
:I think that the wheelchair stick figure we created is a derivative work, although I don't know a ton about copyright law. Imagine if you put that image on a sign, and put the sign in front of a non disability accessible building. That doesn't sound legal to me. You probably can't know for sure without going to court, but people have been sued over stick figures like in the ] case. Or to think of it another way, what if Nike's symbol on their shoes was the ISA. I think they would sue you into the ground if you came out with a shoe that had our wheelchair symbol on it. - ] 03:08, 4 April 2007 (UTC)
What exactly do you think downstream are users going to want to do with the ISA that requires a less restrictive license? —] <sup>(])</sup> 04:11, 4 April 2007 (UTC)
Allow me to clarify something: '''we do not use non-free licenses ... EVER'''. This is Foundation-level policy. They are simply forbidden, completely. No matter how reasonable you think they are. Any argument that goes along the lines of, "but the license say we can use it for ..." should be completely ignored. It is an unfree license (per the Foundation's definition) and as such of no interest to us whatsoever.
All that is left to consider is whether it is covered by our EDP. For "identifying the protected work" on the ISA page it is. As a replacement for the ''free'' and ''adequate'' text (]#1), "disabled access available" or a footnote, it isn't. <span style="font-family: Verdana;">] • ]</span> 13:57, 4 April 2007 (UTC)
‘In this freedom, it is the ''user’s'' purpose that matters, not the ''’s'' purpose’; ‘Especially, '' must not specify any usage restrictions''’; ‘All projects are expected to host only content which is under a Free Content License,’ ‘as can be found at http://freedomdefined.org/Definition’. And that’s why we don’t use ‘usable free of charge for limited purposes’ material. —]<sub>]</sub> 15:58, 4 April 2007 (UTC)
:Please answer my question: What exactly do you think downstream are users going to want to do with the ISA that requires a less restrictive license?
:Also, if that's really what you think, then you should go remove the copyrighted logos from ], ], ], ], ], and ], as they are "of no interest to us whatsoever". —] <sup>(])</sup> 17:00, 4 April 2007 (UTC)
::Trying to predict every possible outcome of creativity and artistic process is pointless; trying to sort such outcomes into legitimate and illegitimate ones is entirely futile. I don’t think about what downstream users are going to do with free material; I let them. I think that’s the spirit of the definition of freedom recently made official by the Foundation.
::The Foundation’s logos should be removed where they do not meet the usual criteria for non-free logos, but I’ll leave that to somebody better able to handle the ‘response’ by you-know-who and just post my opinion in the discussion. —]<sub>]</sub> 18:09, 4 April 2007 (UTC)
:::Why do you think that the foundation refused to license the logos under the GFDL? —] <sup>(])</sup> 18:30, 4 April 2007 (UTC)
I've been busy in real life and unable to participate in this debate as much as I would like, but after private correspondence with Ned Scott I'd like to retract my earlier claim that the ISA is like a flag and that alterations of it may be offensive to people with disabilities. This was based on a misunderstanding on my part.
However, I still think that Peregrine Fisher's concern that the substitute image may be a derivative of the ISA is an important one. If ] is a derivative image of the ISA, then if we want to use it we will have to carve out an exemption for it in our EDP — and if we did that, there would be no reason not to use the real, internationally recognized symbol instead of its derivative. —] <small>(] • ])</small> 19:40, 4 April 2007 (UTC)
:Josiah, Do you agree with me and remember the dot, that if the ISA image needs to be an exemption by the EDP in order to be used, that the wikipedia and wikicommons etc logo's also need an EDP amendment ? --] (] • ] • ]) 19:51, 4 April 2007 (UTC)
::Yes — and I think that EDP amendments ''should'' be made, both for the various Wikimedia logos and for the ISA and the other ICTA icons. —] <small>(] • ])</small> 04:35, 5 April 2007 (UTC)
=== We just need a new image ===
I think the problem is just that ] is too closely modeled on the ISA symbol. ''That''<nowiki>'</nowiki>''s'' the reason it looks silly. We need a totally different idea. I would suggest a direct icon of a wheelchair wheel, something like ], but optimized to be more particular to the context (perhaps an inner guide wheel, a different arrangement of spokes, whatever works).--] 21:25, 4 April 2007 (UTC)
:I suggest we then just use text. There is no point in using a "comparable" image to an internationally recognized symbol, that is so different that it's not a derivative work but also still recognizable as "the international logo". That would just be a "working ourselves around wikipedia policies"-attempt, without having to actually think about why the policies are there. In my eyes, the policies are the problem here, not the use cases. --] (] • ] • ]) 21:36, 4 April 2007 (UTC)
::But icons are practically ''useful'' to us, and not just when they're "international standards". See all of the different icons at ]. I feel that a wheelchair wheel icon, easily recognizable as such, would help our readers, without embarrassing us with a silly image, or forcing us to give up our valuable free images policy.--] 22:07, 4 April 2007 (UTC)
:::I don't think we should reinvent the wheel ;-)
:::Users should be able to tell ''immediately'' what the image represents, rather than having to learn a new symbol used only on Misplaced Pages. It would be much better to use a partially unfree image than to confuse our readers. —] <sup>(])</sup> 01:14, 5 April 2007 (UTC)
:Text would be better than a symbol which would be meaningless to readers. The advantage of a symbol is to convey information quickly and efficiently. The ISA does that. ] does that too, only more awkwardly and in a fashion that may be a derivative use of the ISA. ] does not — my first thought on seeing that image was of the ] in the middle of the ]. (Do we want to say that a given railway station or Disneyland ride is accessible to Indians?) I don't see how the icon of a wheelchair wheel, of whatever design, will convey what the ISA does.
:Furthermore, I believe that any attempt to create an ISA replacement for Misplaced Pages's use is doomed to failure, because the ISA is the ''only'' widely recognized symbol for accessibility. As I've said before, only an image similar to the ISA will be widely understood, and such an image is probably a derivative work. Any image sufficiently distinct from the ISA will be too unfamiliar to readers to be of any use. —] <small>(] • ])</small> 04:52, 5 April 2007 (UTC)
::You know, I'm not really someone who's absolutely dead-set against text. Although it wouldn't exactly be unique to have an icon that only exists on Misplaced Pages, like for example ]. I do feel that it would be probably be possible to come up with an icon that ''in the context of transport articles'' would be recognizable as a wheelchair wheel symbol; but perhaps I'm wrong, and we should just use text. I don't think we could be "doomed to failure" in any case as the goal is rather modest — just an icon that would be usable at Misplaced Pages; this shouldn't be interpreted as some sort of grand challenge to the ISA.--] 06:09, 5 April 2007 (UTC)
==== Why not just ask the ISA itself? ====
Ask them what '''they''' think of the issue. That might help.--<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 05:44, 5 April 2007 (UTC)
:I'm pretty sure their answer is already clearly demonstrated by the copyright they have given the image: "'''No''', we don't mind you using it for its intended purpose. '''No''', we aren't changing the license." --] <small>]</small> <nowiki /> 06:08, 5 April 2007 (UTC)
::I agree that it's unlikely that the ICTA (the organization) would release the ISA or the other accessibility icons under a free license, but I suppose there's no harm in asking. If they say "no", then at least we know for certain. It would be good if someone with some experience asking for free licensing did it. The ICTA's contact info is . —] <small>(] • ])</small> 03:55, 6 April 2007 (UTC)
*We should use the image as intended by the ISA. A minority of Wikipedians are pushing their zeal for ''libre'' images to a ridiculous extreme. This is a great example of a good use of non-free image content. ]\<sup>]</sup> 06:34, 11 April 2007 (UTC)
:*It is not "a ridiculous extreme." The point here is, no matter how noble a purpose we may think is served by this license, ''we do not use licenses'' which restrict use of a work more than the GFDL would. It would be exceptionally easy to simply replace instances of this symbol with text-"wheelchair accessible." (And indeed, if our goal is greater access to the disabled, this would be much easier for the blind using screen readers then an image anyway.) We only use restricted images under ''very'' limited circumstances, and when absolutely no alternative is available. In this case, alternatives are. ] <small><sup>]</sup></small> 06:44, 11 April 2007 (UTC)
::*It definitely is a ridiculous extreme. A small minority of people are too afraid of non-free content. We need to be less restrictive in our use on non-free content, not more restrictive. Our primary goal should be to build an informative and easy to read encyclopedia. If a different image can help with that fine, but we shouldn't avoid this image just because it is non-free. That is not a good use of our time or resources. ]\<sup>]</sup> 07:19, 11 April 2007 (UTC)
:::*Our primary goal, actually, is to create a ''free'' encyclopedia. That doesn't just mean "free of charge," nor even just "free for anyone to edit." It means that ''whenever'' possible, we use content which is permissible for anyone to use, copy, redistribute, or modify. In some cases, a non-free image is the ''only'' possibility for illustrating something, generally when the image itself is being discussed. For example, the article ''about'' the ISA would have to use the ISA, because it is discussing ''the symbol itself''. That is a valid use, and no free alternative could serve that purpose. The same would be true, for example, in discussing an iconic, notable photograph or painting. But in most cases, free alternatives can be used or created, and ''we should not use unfree content in those cases''. In this case, the free-content phrase "wheelchair accessible" will serve the same purpose as an unfree image-illustrating that the location in question is accessible. Given the choice between something free ("libre") which will serve the purpose, and something less than that, we ''always'' choose the free alternative. ] <small><sup>]</sup></small> 07:33, 11 April 2007 (UTC)
::::About blind users using screen readers, the screen reader should pick up the <code>alt</code> attribute and read that text, making either text or the image equally accessible to a blind reader. There is no reason to prefer the text over the image because of accessibility concerns. The question is, for the majority of users, would we rather present them with the ISA?
::::I and others who have commented hold that the ISA, as an internationally recognized symbol, is irreplaceable. No free equivalent could be created, as any free equivalent would be used only on Misplaced Pages and not in the real world. —] <sup>(])</sup> 15:29, 11 April 2007 (UTC)
The problem is not wikipedia policy. The problem is international law. Who the *beep* copyrights a standard symbol, and puts limits on its use!? What next? The letter "A", or the symbol "$" ? %-/ --] 12:33, 11 April 2007 (UTC)
:Well that is quite common. We live in a world of protectionist laws, and as such you need to have the copyright and what not in order to defend the usage of a verbatim or similarly looking text/image. I would also like to point out that in many countries it's not possible to "give-up" the copyright, you can only licence your work freely (or not of course :D ). Note that the usage license is the problem here, NOT the copyright. Almost all major International standards are copyrighted, luckily most don't define their own images. I still think it's stupid not to allow the use of this logo btw. I still think it falls under current Fair Use law, just not under our Fair Use policy.
:It's like saying you are gonna write an encyclopedia in morse code, but you can't use the symbols for morse code, because the international morse code standard says that it would be illlegal to switch the meaning of the dot and the dash. There just isn't a point in that. Sometimes you need to see where your own rules simply exceed the commons sense. --] (] • ] • ]) 12:52, 11 April 2007 (UTC)
::PS. note that almost all the fonts are not free for use. Your suggested situation is already a reality and always has been. --] (] • ] • ]) 12:58, 11 April 2007 (UTC)
== New deletion system proposed. ==
According to the oft-cited guideline ] and the policy ], Misplaced Pages is not a democracy. This means that votes should be '''deleted''' to prevent these policies from being violated.
To facilitate this, I am hereby proposing the new ] system, in which votes can be proposed for deletion. Please comment here or on the talk page! —''']'''<sup>]]</sup> 00:30, 1 April 2007 (UTC)
*'''Support'''. Wonderful idea. Should pass by supermajority. ] 19:17, 1 April 2007 (UTC)
*I have no idea what Dark Shikari is proposing. I don't understand what you're trying to say here. What do you mean, votes can be deleted? And what would your new process entail? Where is your proposal? ] 20:17, 5 April 2007 (UTC)
:*It was an April Fools joke, now located at ]. --] <small>]</small> <nowiki /> 20:25, 5 April 2007 (UTC)
== Would it violate NPOV to require a scientific viewpoint? ==
Articles about the supernatural like ] and ] are written from a thoroughly unscientific viewpoint. That is, they give (what I feel to be) undue weight to the possibility that these entities exist. In the same way that we require articles about fictional entities to not be written from an in-universe style, I think that we should require articles about unscientific topics to clearly state that their existences are not supported by science. Would this violate NPOV? And to dig myself even further into a hole, I would like to extend this question beyond articles on the supernatural to articles about religious topics and articles about pseudoscience (as determined by scientific consensus). Would it violate NPOV to put some kind of "this is unscientific" disclaimer onto those? --] 05:55, 2 April 2007 (UTC)
:This discussion has a long history here. The outcome of this discussion is most clear for fields which claim to be science but are not. Compare ], ] (for extreme cases ]) and the outcome and discussions of ].
:] 12:29, 2 April 2007 (UTC)
:Another problem is that the use of science has not been able to ''disprove'' that some phenomena is the result of ghosts, beasties, God, witchcraft, aliens, Government Conspiracy (please add Fringe Belief System as appropriate). The creed of "Absence of proof is not proof of absence" has been very helpful to those who proclaim faith in such matters. To contemplate placing a ''scientific disclaimer'' on certain classes of article will likely raise as much debate as to its validity as the subject itself. It is best to allow the reader make up their own minds based on the references and examples available in the article, understanding that the reader will likely bring their own views to the subject anyway. ] 12:28, 3 April 2007 (UTC)
::How about just sticking to "verifiable information from a reliable source", and making it ''very, very, very, explicitly, clear'' that while some people do ''believe'' in these things, it is an unproven (and in some cases, unprovable) belief. Attribution solves everything-instead of "Ghosts exist<sup></sup>", say "Supernatural Monthly claims that thousands of ghosts have been observed.<sup></sup> Debunkers Weekly states that this is "the worst form of pseudoscience we've ever seen," and has found that the group fabricated or altered statements in at least thirty cases.<sup></sup>" ] <small><sup>]</sup></small> 13:03, 3 April 2007 (UTC)
:::Ah, but "verifiable information from a reliable source" could include an EMP reading in an investigation conducted by ]; they have a tv show, what more proof do you need? ;~) My point is that disclaimers will bring nothing to an article, the scientific/skeptic community don't need telling what is junk science and the believers will ignore/dispute its validity. ] 14:51, 3 April 2007 (UTC
::::There is an established practice of including a Controversy section to articles that merit it. If there is some controversy concerning the current state of Martian politics, then that should of course be mentioned. ] 18:30, 4 April 2007 (UTC)
:::::<small>Don't tell me the Fungoid Transferable Vote Policy has been bought up again!?! ] 20:36, 7 April 2007 (UTC)</small>
WHAT IS a "scientific" perspective, and the tool for its measure?
To the Misplaced Pages Community,
My proper address is Entologist George Johnson-Hill, I had an entry entitled 'Entology' here in Misplaced Pages's FREE online encyclopedia deleted by one of the "administrators";
Reason: violation of Misplaced Pages guidelines(CSD G1, NONSENSE)
I RESPECTFULLY PRESENT THIS ISSUE TO THE WIKIPEDIA COMMUNITY.
Websters' definition of the prefix "ento" is: combining form within or inner...
Websters' definition of the suffix "ology" is: the study of...
Respectfully, 'Entology' is a conjunction of the two, hence, "the study of within."
Yes, it is a word that I formed, as well as what I believe to be a scientific platform, as "science" IS a searching field based upon theories.
"Entology" thus: is the study of "dynamic relativity," or "cause and effect by objective." A "science" utilizing the premise of Einstein's theory of general relativity examined within the principles of the Domino Effect.
For a model of "dynamic relativity" I offered for examination a parlimentary system;
For the presence of "dynamic relativity," I offered for examination the United States.
Obviously, I am serious about this issue and feel the deletion of my entry violated the principles of the Misplaced Pages forum. I am therefore, presenting this issue to the Misplaced Pages community for review. I will graciously respect whatever decision the Wikipedian community decides.
Entologist George Johnson-Hill, georgejohnsonhill@tongueslanginbest.com
: Not knowing anything about your case, I suspect that you fell foul of the rules against ]. To summarise, Misplaced Pages is ''not'' somewhere where you can submit essays on particular subjects. Instead, Misplaced Pages is somewhere where you can summarise information that has ''already'' been published in a ]. If you write an ] article that is fully based on existing published material (citing the sources of such material, and not copying them verbatim), then I would expect the article to form a valuable contribution to the encyclopedia. If you feel that you contribution has been unreasonably deleted, then you can report it to ], where you will obtain an unbiased opinion on whether Misplaced Pages guidelines have been violated. ] 05:34, 13 April 2007 (UTC)
== Privacy proposals - status unclear ==
The status of the following old policy proposals is somewhat unclear:
* ]
* ]
* ]
They were all tagged {{tl|rejected}} until recently when tags of all three were changed to {{tl|disputed}} by the same user. Two of them are currently protected until the status is resolved. I am not trying to revive any of these proposals; I think that none of them is close to having consensus and they should all be marked as rejected. But it seems that a discussion is required to decide on their status. ] · <small>]</small> 20:45, 2 April 2007 (UTC)
:Hmm, I hadn't followed this discussion so far. But immediatly when reading this I thought: Why not state on the edit page of ] "Be careful with providing personal information on your Misplaced Pages userpage" (or something more directly targeted at children ?? I really don't care what goes there exactly). I mean it would be technically possible to add a small message just above the editpage box of a User page wouldn't it ? And we don't become babysitters like ] was afraid of with such a message, while still doing something along a "best-effort", which is quite a lot of effort for a non-profit organization! --] (] • ] • ]) 23:37, 2 April 2007 (UTC)
::So what i was hinting as what we have on the edit box of talk pages for instance: "This is a talk page. Please respect the talk page guidelines, and remember to sign your posts using four tildes (--] (] • ] • ]) 23:45, 2 April 2007 (UTC))."
Unless there are objections, I plan to tag all three of these as rejected on Apr 9. ] · <small>]</small> 01:54, 7 April 2007 (UTC)
I object to any of these being labeled as rejected. In the case of Protecting children's privacy, the current version was essentially written by the ArbComm -- it was taken directly from their findings in a case involving the previous version. I don't see any statement in the current version that anybody could possibly object to, nor have I seen any objections other than "IDONTLIKEIT" type objections, which aren't supposed to count. In the case of Youth protection, I think I have the right to make it an essay, which I did, but it was edit-warred into a rejected policy page. I think this is wrong. Just because there was no consensus for the old version of Protecting children's privacy does not mean there can't be an essay saying that these protections ''should'' exist. After all, there are essays on almost everything else. You or someone else suggested userfying it, which is where it started, but there's nothing wrong with having it as an essay. As for WP:Privacy, this one truly baffles me. Radiant originally created it as a counter to Protecting children's privacy, but once the original version of the latter was "rejected" (which was and is still in dispute), he seemed to lose interest in it. I am quickly coming to the conclusion that policy on Misplaced Pages is all one big game, and the best interests of users in general are trampled by admins who assert ownership of policy pages and get their admin friends to leave stupid warnings on ordinary users' talk pages so they can have the upper hand in disputes. ] 05:25, 7 April 2007 (UTC)
Oh, and one more thing. The current version of WP:Youth protection, when it was properly labeled as an essay, had several passages that suggested that it was a policy. That was my mistake, but when I tried to correct it, Radiant reverted me, because he was so hot to have that "Rejected" tag back up there. But somehow, I was the only one you saw fit to warn, CMummert. Not that I am holding a grudge or anything. ] 05:35, 7 April 2007 (UTC)
:I brought the discussion here in the hopes of expanding the discussion to a broader audience. The basic question is, when is it appropriate to use an essay tag vs. when is it appropriate to use a rejected tag. I hope that others will comment on the situation. The second question is what to do with these three pages. ] · <small>]</small> 12:22, 7 April 2007 (UTC)
::OK, well, as far as I can see, there is no policy or guideline that says that a rejected policy proposal cannot be tagged as an essay if someone wants to do so. I don't see why there should be such a policy. I looked at ] to try to find some guidance on what can and cannot be an essay, and unfortunately there is no policy there; only an essay! It then leads to another essay with a confusing name (somthing like Don't worry about writing essays) which basically seems to say, go ahead and write an essay on anything you want. But, of course, that is only an essay! So the bottom line is, there is no "rule" against what I did at WP:YOUTH, there is no reason why there ''should'' be such a rule, and this non-existent rule should not be enforced as if it were a rule. ] 13:04, 7 April 2007 (UTC)
I think they should stay rejected. There had been no consensus to make them policy (half the room shouting "we have consensus" and the other half "no we don't" can't really be considered consensus) and after a while people simply left to work on something more productive. ]]/] 13:35, 7 April 2007 (UTC)
=== moving forward ===
I was hoping that some uninvolved editors would comment on the issue. The question is how to label these old proposals that didn't gather consensus. ] · <small>]</small> 18:44, 8 April 2007 (UTC)
*Check ] which lists the "tags" and reasoning behind them. In particular, ''"A rejected page is any proposal for which consensus support is not present, regardless of whether there is active discussion or not. Consensus need not be fully opposed; if consensus is neutral on the issue and unlikely to improve, the proposal is likewise rejected."'' ] 09:42, 10 April 2007 (UTC)
I have asked the editor opposed to using the {{tl|rejected}} tag to make a comment on the resolution they would like to see here. ] · <small>]</small> 11:33, 10 April 2007 (UTC)
:I think I have given my opinion above. In any event, I see little point in participating in this at the moment. I do not plan to change the tags for the time being. Hopefully, at some point, some of the many people who saw the need for a policy/guideline in this area will rejoin the discussion, and at that point things can move forward. Hopefully it will not take a Major Bad Incident with screaming headlines on CNN to bring that about. But until something does happen to attract people back to the discussion, I suppose that those who ] these pages and their tags will be able to do as they please. ] 19:54, 10 April 2007 (UTC)
What if I put a {{tl|historic}} tag instead of {{tl|rejected}}? That wording is much more ambiguous about the status of the proposal. ] · <small>]</small> 15:36, 11 April 2007 (UTC)
== Policy/guideline/practice on information about minors ==
Where can I find information about either policy, guideline, or practice regarding the inclusion of personal information of minors on their user pages? I've heard conflicting opinions recently. <font face="Optima"><b>]</b> (])</font> 14:05, 3 April 2007 (UTC)
:Even though ] was rejected by the ArbCom, I think the statement on ] should be a moot point. Perhaps we should have some sort of policy or essay on this. <span style="font-family: Tahoma; font-size: 8pt;">] ]</span> 22:27, 3 April 2007 (UTC)
::There are '''three''' texts on this. See the section on "Privacy proposals" above.
::From watching various noticeboards, my opinion on the current state of affairs is: there is no policy forbidding it, but you are free to counsel users privately, and ] may be willing to delete the information from edit histories if the user requests it. ] · <small>]</small> 22:54, 3 April 2007 (UTC)
:::], to make it easier. Either way, I do believe that sysops remove personal information of minors for their own good. As I've seen on ] on a couple of occasions. <span style="font-family: Tahoma; font-size: 8pt;">] ]</span> 23:16, 3 April 2007 (UTC)
::::Okay, this makes sense. What doesn't make sense is why an instance of this that I sent to oversight was ignored... the response that I received said that he oversight user felt that nothing was wrong with a fifteen year old identifying themselves by their e-mail and the school that they attend. <font face="Optima"><b>]</b> (])</font> 07:37, 4 April 2007 (UTC)
::::I will suggest to the user that they avoid publishing identifying personal information. <font face="Optima"><b>]</b> (])</font> 07:39, 4 April 2007 (UTC)
:::::I can't remember, but I have seen something like 13 being the threshold. I put a lot of information on my userpage when I was 15 when I joined Misplaced Pages and nobody told me to take it off. Still, I think those policies do need some sort of reconsideration, especially considering the fact Misplaced Pages is being mirrored and forked more and more times, and there are more and more users thinking this is like MySpace. <span style="font-family: Tahoma; font-size: 8pt;">] ]</span> 13:16, 4 April 2007 (UTC)
:::::*There is no threshold per se; basically, it's the user's own responsibility. ] 11:57, 5 April 2007 (UTC)
::::::There is an essay at ], which due to tag-warring by obstructionists, has been erroneously labeled as a rejected proposal (and the text has some errors because when I tried to fix it I was reverted and warned against fixing it again). This essay (adapted by me from another page) suggests that '''all''' children (as defined by your local definition) refrain from posting personal information. There are some administrators who regard the posting of such information by a self-identified child as inherently disruptive, especially if accompanied by "provocative" comments, and who will delete the information and request permanent removal by ] when they see it. Others, no doubt, do not. ] 17:10, 5 April 2007 (UTC)
::::::::"to tag-warring by obstructionists"? 6SJ7, I can no longer assume good faith in regard to your continued incivility. You attempted to unilaterally change the status of rejected proposals to being policy, were repeatedly reverted by several users (all this over the course of over 2 weeks) and annouced that you "will continue to do what I think is right" - which does sound quite alot that you wish to continue to try force through your "right version", even it if it means editwarring with many others. ]]/] 16:13, 7 April 2007 (UTC)
:::::::::What you assume is irrelevant to me. And for the record, I stopped the reversions after I received a direct warning on my user page. I think the warning was an abuse of the administrator's authority, but that's the way things are here on Misplaced Pages. Doing what is "right" sometimes has to give way to the fact that other people have power and are willing to abuse it. ] 23:41, 7 April 2007 (UTC)
::::::::::I would be glad for someone else to review the messages I left on your talk page. ] · <small>]</small> 00:23, 8 April 2007 (UTC)
::::::::Would you explain your opinion on the difference between an essay and a rejected proposal, and how to tell them apart? ] started with the {{tl|proposed}} tag at the top; nobody claimed it was an essay until after it was tagged {{tl|rejected}}. As the primary author, if you would like to move it to your user space, I don't believe anyone would object. ] · <small>]</small> 18:43, 5 April 2007 (UTC)
:::::::Is a person with oversight responsibilities bound to act in a certain way when receiving requests for removal of personal information self-posted by a minor? <font face="Optima"><b>]</b> (])</font> 17:20, 5 April 2007 (UTC)
::::::::It is my understanding that there is no policy on this matter and each incident is handled on a case-by-case basis (which is probably the best way to handle it anyway). Obviously a case involving a 15 year old is not that dire and I personally would not object to them posting personal info (up to a point). It would be up to the discretion of the individual oversight person as to whether or not to take any action on the matter. ] 19:01, 5 April 2007 (UTC)
::::::::*Age has little to do with it; in general, personal information is frequently removed if it is posted by someone else (obviously) or in more uncommon cases if the oversighter believes it's plausible that this could harm the person. ] 08:52, 6 April 2007 (UTC)
:::::::::It is mind-boggling to me that you can say that age has little to do with it. Age has a lot to do with it. What is the big objection to protecting chidren who may post their ''own'' personal information without realizing the dangers? And in any event, my opinion aside, there are admins who will remove personal information posted by a self-identified child, and not remove personal information posted by an adult, so Common Practice ''does'' take age into account. ] 05:32, 7 April 2007 (UTC)
::::::::::I don't see what you mean - admins can't remove information from the edit history. Users with ] abilities can do so, but in these cases they do so at their own discretion, especially since none of the three "official" uses of oversight is to remove correct information users post about themselves. ] · <small>]</small> 18:55, 7 April 2007 (UTC)
] ("''Reasonable measures which forestall the drama associated with interactions between naive children, predatory pedophiles, and sting operations by law enforcement are appropriate.''") passed 5-0. I think discussion about what is reasonable should take place. One specific question that I don't know the answer to is: is it reasonable to delete the sentence "I'm a sexy 13 year old boy" under the motivation that the deletion will forestall the drama associated with interactions between naive children and predatory pedophiles? <span style="font: small-caps 1em Optima">]</span> 20:17, 7 April 2007 (UTC)
*A somewhat related question regarding WP policies (or lack thereof) about minors, concerns identifying minors in articles pertaining to criminal trials. Many newspapers and TV networks won't show pictures of, or name, minors in such cases. Does WP have a similar restriction? For example, the Article ] does not mention his accuser's last name. Is there any reason why the name (and/or a Fair Use screenshot from the ABC-TV program showing Jackson with his accuser, to illustrate the article about this program) has to be omitted? <i><b>]<font color = "darkblue"> <sup>]</sup></font></b> - </i> 21:04, 7 April 2007 (UTC)
*:Ordinarily, until reliable media sources publish the name there is no reliable source that can be used to source it, and so in a BLP setting it will get deleted from the article. This is just a consequence of the citation requirements, not a specific policy about releasing names. ] · <small>]</small> 21:17, 7 April 2007 (UTC)
== Courtesy titles - The Honourable ==
I've had the courtesy title, "The Honourable", removed from the body text of an about the daughter of a Viscount when used for the first time (is that referred to as inline?). Having taken some time to read up on it, I don’t understand WP's policy on this, which is -
''1. Styles and honorifics which are derived from noble title, including ], ], ], and ], should not be included in the text inline but may be legitimately discussed in the article proper. ''
when contrasted with social convention -
''The younger sons of earls, along with the sons and daughters of Viscounts and Barons are granted the courtesy title of "The Honourable" before their name. This is usually abbreviated to "The Hon.".''
''Usage''
''The style The Honourable is always written on envelopes (where it is usually abbreviated to The Hon), and formally elsewhere, in which case the style Mr or ] is omitted.''
''6. Courtesy titles (also referred to as an honorific prefix)² such as Lord or Lady differ from full titles because unlike full titles they are included as part of the personal name, often from birth.''
Please can someone explain the WP policy and point me towards the relevant discussion that lead to it ? Thanks ] 17:38, 3 April 2007 (UTC)
: Misplaced Pages generally follows press reporting form, as seen in the AP Style Manual,
rather than diplomatic form, which is too bulky for general use. --] 04:22, 4 April 2007 (UTC)
:: Thanks for your response John :-). In respect of a first mention within an encyclopedia, though, I think WP policy is wrong, because a matter of style has suppressed a matter of fact. As the articles stands now, it is up to the individual reader to derive the full title from the parents title and this only if they know the rules for succession of titles.
:: It sounds as if this has already been the subject of discussion, which I can't locate, so I'd be grateful for any onward pointers. Thanks - ] 11:17, 4 April 2007 (UTC)
:::There has been a discussion on ]. ] 11:39, 5 April 2007 (UTC)
:::The honorific ''can'' be mentioned in the body of the article, just not in the first line. The reason for omission is largely because in many countries "The Honourable" is used as a prefix denoting various offices (such as judges, government ministers etc) and allowing an exception would lead to honorifics springing up all over the place, which would complicate matters and be generally undesirable. It was therefore decided to omit them all from article first lines. -- ] 12:47, 5 April 2007 (UTC)
:::: Thanks ! :-) ] 16:01, 5 April 2007 (UTC)
== Usernames with advocacy ==
I have been noticing usernames such as these:
*]
*]
I checked ] and there doesn't seem to be any policy regarding these types of usernames. So my question is, ought there be policy regarding usernames which push a POV?--<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 22:19, 4 April 2007 (UTC)
:POV usernames are OK unless they are disruptive. No need for such policy. ]<sup>], ]</sup> 22:21, 4 April 2007 (UTC)
::Disruptive in what sense? Because isn't advocacy in direct contradiction with ]?--<font color="red">]</font><font color="green">]</font><font color="yellow">]</font><font color="black">]</font><font color="pink">]</font><font color="blue">]</font> 22:23, 4 April 2007 (UTC)
:::It's OK if they're not editing articles relating to their usernames. Even still, so long as they provide verifiable references to support their additions, I have no quarrel even if they ''are'' editing such articles. Their dedication to an issue may make them more aware of useful resources which may not have been referenced within the respective Misplaced Pages entry. --] (<small>] ;; ]</small>) 02:16, 5 April 2007 (UTC)
:::*I see no problem with such names. If anything they do themselves a disservice (as pointed out in the ]) because people will tend to assume they are biased in their edits. ] 11:52, 5 April 2007 (UTC)
::::*The problem with banning such things is where do we stop? User:AnimalRights? User:ChristianWarrior? maybe we'd ban them, but what about User:ProudAmerica? or User:YoungSocialist? and then do we ban usernames with implied POV like User:CommradeRed? then we end up in wikilawyering definitions. If it is disruptive kill it, otherwise suggest a change and leave it at that. If POV warriors want to flag themselves up as such, that's probably helpful in the long run.--]<sup>g</sup> 12:02, 5 April 2007 (UTC)
:::::*I have no problem with usernames which state a position in general terms, so long as the position is not an extreme one or obviously inflammatory. However, yesterday I encourged ] to change his name because that was a bit too specific. ] 12:06, 5 April 2007 (UTC)
* Usernames that state a position are fine, even if they edit the articles that their username reflects. The problem is when it becomes disruptive. Logically, if we were to prevent people with names like "AnimalRights" from editing articles about animal rights, it would make sense to do the same with POV userboxes ("This user supports animal rights.") As a result, the actions of a user need to be judged independently of their username. ''']''' <sub>]|]]</sub> 16:36, 5 April 2007 (UTC)
== Proposal to abolish ] ==
There is an ongoing MfD discussion regarding the future of RFCN at ]. ]<sup>]</sup>]</sub> 04:01, 5 April 2007 (UTC)
*Which, by theway, is not a proposal to abolish checking for invalid user names, but a protest against the recent complexification of the page. ] 11:31, 5 April 2007 (UTC)
:::The current process can archive properly to reduce loss of records, it's a good thing. ]<sup>], ]</sup> 21:36, 5 April 2007 (UTC)
== Template:LocateMe ==
There is discussion in a number of places (e.g. ] and ) as to whether ] should be placed on the article page or the talk page. 540 articles have been tagged with this template to date (e.g. ]). If you're interested in whether & when nagging templates can be placed in the article space, please consider adding your thoughts at ]. --] ]
==External links==
Is there a policy regarding the content or type of external links listed in an article? Recently in ], two picture blogs have been added. Even though the pictures therein shown are outstanding (one of them includes pictures taken from a helicopter), I do not know if they are allowed, coming from personal blogs or webpages. --] 21:05, 5 April 2007 (UTC)
:There is a guideline, see ], which says links to blogs (I suspect meaning text blogs) should normally be avoided. You might ask for clarification at ]. -- ] <small>(])</small> 13:48, 6 April 2007 (UTC)
::Not linking to blogs has to do with problems with verifiability (blogs are essentially personal opinion, unless published by a newspaper, in which case editorial review and corrections are to be expected). An external link to a picture blog doesn't raise verifiability issues (unless it's, say, pictures of "UFOs"); rather, it's a question of whether we want to provide readers with links to sites with pictures rather than text. I'd argue that we ''don't'' (except, say, collected works of an artist, from that artist's bio on Misplaced Pages); per ], Misplaced Pages isn't an indiscriminate collector of information. -- <font style="font-family:Monotype Corsiva; font-size:15px;">] </font> ] 13:58, 6 April 2007 (UTC)
== "Undue Weight" on NPOV policy ==
I feel strongly that the policy ] should be changed in the "Undue Weight" section. The provision states that a majority view should have major proportion on an article while a minority view should be represented only marginally or not at all. This isn't reasonable. First, Wikipedis is not a democracy, it's not like U.S. Congress which has a majority party and minority party with different representation. In here everyone is equal in article editting, and any non-trivial sourced views should be represented in equal footing. Because the so-called "proportional" representation is ''de facto'' endorsement of the majority opinion, as a naive reader would assume that the opinion represented in large proportion in an article would be the correct opinion. ]<sup>], ]</sup> 21:32, 5 April 2007 (UTC)
:Like Gallileo vs The Inquisition we need the luxury of hindsight to understand that the minority view was/is the truth. As Misplaced Pages is about verifiability and citations then the ''status quo'' witl always be better represented. The only way round this would be to create an article for the minority viewpoint, where undue weight should not be afforded to the standard sources, which links to the main article. ] 10:05, 6 April 2007 (UTC)
::We ''don't'' create articles for minority views - see ]. The reality is that in most cases, the minority view ''is wrong'' - Galileo was right, but the myriads of proponents of perpetual motion machines and miracle cures have pretty universally been wrong.
::Misplaced Pages isn't about suppressing information, but saying ''any non-trivial sourced views should be represented in equal footing'' is absurd. It's enough to mention a minority view if there in fact is a '''reliable source''' (as opposed, say, to some crank's personal website) and let the reader pursue the matter if interested (it's not as if people don't know who to do a Google search).
::For further information, please see ]. -- <font style="font-family:Monotype Corsiva; font-size:15px;">] </font> ] 14:05, 6 April 2007 (UTC)
::::What you are citing ] is a policy, and what I'm trying to do here is getting that policy changed as well. Because it's unreasonable and unfair. ]<sup>], ]</sup> 19:57, 6 April 2007 (UTC)
:::I had assumed that ] was talking about a situation where the minority view didn't fall under ] etc. and was supported by reliable sources, for instance whether Homo Neanderthal bred out into Homo Sapiens rather than just die out through competition. Even as a fork of the ascent of Homo Sapiens Sapiens this would be creation, where the proponents sources should be given more weight than opponents. (This supposes that the example I gave is not considered Fringe, I thought it had some credibility/support some little time ago). ] 19:39, 6 April 2007 (UTC)
::::I agree with LessHeard vanU, minority view and fringe view are different things. A minority view is often held by a handful of professors and prominent people, while "fringe" views are often published in trivial sources (personal blogs, etc.) When a view is presented through non-trivial means, it does deserve equal footing. If Galileo lives today, he'd probably be angry at Misplaced Pages. ]<sup>], ]</sup> 19:50, 6 April 2007 (UTC)
:::::In the case of the "paranormal", as in your query here , which refers back to , generally, paranormal arguments are seen as fringe views rather than legitimate minority scientific views, since they tend to be published in non-mainstream journals. --- ] 19:13, 7 April 2007 (UTC)
:This discussion is based on a misunderstanding of the rules. I believe the rules we have are correct. The misunderstanding is this: some editors wish to assume that they know what a majority view is, even when none has been stated. This is evident in the article on Electronic voice phenomenon. Editors there wish to give weight to a "majority view" which is actually a "skeptical view." They believe that a few skeptics who claim to speak for science are automatically a majority. But the majority of science has not stated any view on the subject. Among those who study the matter, the majority view is that the phenomenon is paranormal. This puts Misplaced Pages in a very difficult position: we are dealing with a field which is notable and makes factual claims. We know in our hearts as editors that many scientists -who knows how many since most scientists do believe in the paranormal- would think EVP is bunk. Yet at the same time, the actual peer-reviewed papers (published in parapsychological journals) we have on the subject are inconclusive (one positive, one inconclusive). Mainstream science has no opinion specifically on EVP whatsoever, though some studies have been done which skeptics (not, I believe, the scientists themselves) claim might explain EVP. We are being asked, in the EVP page, to present the view of a few skeptics and the silence of the mainstream as if it constituted a mainstream consensus that EVP has been determined to be bunk. If any change is needed, it is to make it (even) clear(er) that editors of Misplaced Pages cannot invent a consensus of the mainstream where there is none. ''']''' <sub>(] Ψ ])</sub> 21:19, 7 April 2007 (UTC)
::The counter argument is that ''"mainstream"'' scientific journals do not comment upon such matters as they feel that it falls outside of their remit; they do not partake in discussions of the dimensions or physical attributes of the Flat Earth for the same reason. Many of the people who request that ''"due weight"'' be given to the skeptics are doubtless taking the same stance toward the EVP example you give. ] 21:55, 7 April 2007 (UTC) (ps. I know nothing of EVP, I am just suggesting the reason for a lack of mainstream comment on the matter and the consequent thinking of some editors.)
:::] already covers this: '''"If proper attribution cannot be found among reliable sources of an idea's standing, it should be assumed that the idea has not received consideration or acceptance."''' To insist otherwise is to insist on a burden of disproof. --] 22:22, 7 April 2007 (UTC)
::::Which is exactly what I have been trying to do to the article: state clearly that the scientific mainstream has not considered, nor accepted, EVP. But the skeptics want to state that it has been rejected. But if it hasn't been considered, it hasn't been rejected. Therefore, it is OR to state that it has. You are proposing, basically, that we break the rules. ''']''' <sub>(] Ψ ])</sub> 02:55, 8 April 2007 (UTC)
:::::If you would like a clearer rule: '''If reliable sources have not been found to indicate that mainstream science accepts an idea, mainstream science rejects it.''' Science journals get sent articles on pseudoscientific stuff (such as EVP) all the time. The fact that all those submissions go in the garbage can without comment speaks for itself. ] <small><sup>]</sup></small> 05:02, 8 April 2007 (UTC)
::::::If this is really the policy, then it should be no trouble to change it. Why don't you? It won't take you much time to edit. ''']''' <sub>(] Ψ ])</sub> 05:58, 8 April 2007 (UTC)
:::::::"You are proposing, basically, that we break the rules." That's a pretty strong accuation, especially since I just did nothing more than quote a policy. Where exactly did I propose breaking the rules? And it's a strawman to insist that people have argued to make the EVP article say that it has been rejected, all along we've wanted to say nothing more than that science hasn't accepted it, and more importantly, to follow undue weight so that the article isn't 90% arguments that the purported phenomena exists, or writing the definition to say it exists. --] 12:38, 8 April 2007 (UTC)
::::::::The current policy is logical and accurate. Misplaced Pages is not the place to push forward fringe theories or minority views. I often see this in articles, people want to be fair and balanced so they give negative aspects of a certain topic—which really aren't significantly noteworthy—as much coverage as more well known positive aspects. What we need is more of this policy, not less of it. ] 16:07, 8 April 2007 (UTC)
:::::::::Also you see advocates of a certain minority theory or interpretation using Misplaced Pages as a soapbaox and shifting the focus of an article to their views or theories. ] 16:13, 8 April 2007 (UTC)
We are talking here -I think- about articles which are specifically ''about'' the fringe topics. It looks above as if people are talking about articles on other topics which give too much coverage to alternative fringe interpretations etc. Minderbinder, the way the EVP article has been written in the past has had innuendo or outright statements which basically say that the mainstream has rejected -as opposed to not considered or accepted- EVP. Seraphimblade's comment above was basically followed in the article. I suggest that this statement be added to the rules. Then things would be clear. You would get to write the articles the way you, ScienceApologist et al have been trying to, and no argument. ''']''' <sub>(] Ψ ])</sub> 20:13, 8 April 2007 (UTC)
One problem with this discussion is that we are trying to find one rule for lots of different things. The point was made above that we don't create articles for minority view (John Broughton said it I think), and the probelm is that yes we do, sort of. That is, most of the topics that are being discussed here do not fall into the round Earth v's Flat Earth dichotomy. That is, the Earth being round has an abundance of scientific evidence to support it (peer review mainstream science about the Earth), whereas on a topic like ghosts there is nothing similar. Mainstream scince hasn't really considered ghosts and so even if one were to claim that the majority scientific view is that ghosts don't exist (rather than simply scince has not considered or accepted the existence of ghosts) you are going to have a hard time saying very much more than that. The problem that this creates is that unless we are going to write a 10-word article on ghosts the "mainstream" view is either going to be take up very little space in ocomparison to other views/points etc. about ghosts, or else we can write "science/sceptics say ghosts don't exist" every few lines in the article (a method that sems to have been adopted in the EVP article).
I also agree with Martinphi that Seraphimblade should put his/her money where his/her mouth is and either change the policy to say "if mainstream scince hasn't considered something then it should be taken to have rejected it", or accept that it doesn't actually mean that at all.] 20:41, 8 April 2007 (UTC)
:We are '''now''' talking about fringe theory but originally the discussion was regarding minority views that are supported by reputable sources, but by less than a nominal 50% of the community, where the wording of ''Undue Weight'' means that the views of a sizeable minority should be represented ''"only marginally or not at all"''. As the original commenter said, if the minority represented 45% of the scientific community then this guideline would effectively censor that element.
:The EVP matter does not appear to be a scientific minority viewpoint, but a viewpoint that does not have any citable credibility in the mainstream scientific world. ] 21:03, 8 April 2007 (UTC)
Yes, I didn't think of the point that there simply isn't enough mainstream material a lot of the time to make it a large part of the article. LessHeard is right, also. ''']''' <sub>(] Ψ ])</sub> 21:49, 8 April 2007 (UTC)
:] says that views should be represented "in proportion to the prominence of each." In other words, it ''encourages'' us to make a distinction between a "minority" view that is supported by 45% of the scientific community, and one that is supported by a tiny minority. I don't see a problem here. ] is one of the most important (if least understood and least obeyed) policies we have, and it already deals with the situations mentioned above effectively. What I'm hearing is that proponents of certain minoritarian views would like more freedom to expound on them uncritically here. There are many forums to do so, but Misplaced Pages generally is not one of them. ''']''' <sup>]</sup> 22:57, 8 April 2007 (UTC)
::Unless the minority view is Scientism, in which case whole articles (and many sections of other articles) can be used to expound on it using the "this is what scientists would say if they said something and this is what experiments would show if they had been done" rule. ] 23:05, 8 April 2007 (UTC)
:::Yes, MastCell, but the problem is cases like EVP. In that case, 90 percent -and that's probably not an overestimation though it is OR- of the people who make it prominent believe it is communication from spirits. So, that means we should give 90 percent of the article to those views? Or maybe even 100%, since the skeptics are a very very tiny minority? I believe there should be more skepticism in the article than that. On the other hand, skeptics are arguing that the 90 percent actually represent a minority because..... ummmmmm.... because they aren't skeptical. So what do you think should be done? ''']''' <sub>(] Ψ ])</sub> 02:28, 9 April 2007 (UTC)
::::Simple... fields which have not been studied critically by mainstream science should not be presented as if they are mainstream scientific fields. They are "fringe" fields by definition. That's my opinion, but then I'm just one person. ''']''' <sup>]</sup> 02:52, 9 April 2007 (UTC)
:::::And that's what WP policy already says, repeatedly. And the 90% thing ignores undue weight and values quantity over quality (reliability) of sources. If there are only two or three articles appearing in journals discussing a topic, we're supposed to consider that enough evidence of mainsteam acceptance? Or a whole pile of self published "experiments" along with those?
:::::I have to admit I'm amused by the addition of "scientism" to the rhetorical arsenal, it's a nice change of pace from "pseudoskeptic". --] 12:06, 9 April 2007 (UTC)
No one is saying that they should. WP:FRINGE says:
"Articles which cover controversial, disputed, or discounted ideas in detail should document (with reliable sources) the current level of their acceptance for the idea among the relevant academic community. If proper attribution cannot be found among reliable sources of an idea's standing, it should be assumed that the idea has not received consideration or acceptance. However, a lack of consideration or acceptance does not necessarily imply rejection; ideas should not be portrayed as rejected or labeled as pseudoscience, unless such claims can be documented in reliable sources."
This is interpreted by skeptics to mean what Seraphimblade says above. If that is really policy, then let's change it. If it is not policy, then let's present the articles that way. I have '''absolutely no problem with the current rules'''. I have a problem with skeptics who don't want to follow them. EVP, for instance, has not been considered or rejected, and the skeptics, for pure repugnance to the subject, want to write the article, by giving undue weight and outright innuendo or statements, as if it has been considered and rejected. They want to do OR to make out as if it has. So either change the rules or follow them! (to paraphrase Davkal.) ''']''' <sub>(] Ψ ])</sub> 23:12, 9 April 2007 (UTC)
:Again, you're arguing with a strawman. All along, editors have been editing EVP to present it as a subject not accepted by science (which you seem to agree we should assume based on the policy above), and present it so undue weight isn't given to those advocating the topic (since it hasn't been accepted by science, and since the sources supporting it as a "proven" topic are few and questionable). '''YOU''' are the one who wants to ignore the rules and give undue weight to the arguments supporting it, regardless of how poorly sourced they are or whether they have been cited or reproduced by any other scientists or scientific publications. You have basically been arguing to present a fringe topic as if it were a mainstream one (simply because the mainstream has failed to disprove it).
:Martin, at this point, upwards of twenty editors have agreed that you are misinterpreting NPOV and FRINGE, yet you still insist you're the one who is right. What would it take for you to accept that your interpretation of wikipedia policies is a misinterpretation and twisting through wikilawyering? I'm serious, please tell us what would clear this up for you once and for all, and would let you accept that your interpretation is wrong? --] 12:51, 10 April 2007 (UTC)
::No, they have been editing it to subtly or not so subtly- present it as a subject ''rejected'' by science. . First, it would take some reasonable argument instead of ignoring arguments and POV-pushing. Second, as Seraphimblade made clear above, there is a very wide disagreement as to how to interpret the rules. Why don't you put that interpretation in the rules? If it sticks, then our argument is over, and you win. If it doesn't, then please concede. ''']''' <sub>(] Ψ ])</sub> 22:39, 10 April 2007 (UTC)
:::Ah. So editors haven't been editing the article to say that it's rejected, they've been editing it to ''say things that you've interpreted as (in some cases subtly) implying rejected''. You sure have policy on your side there. And is there even any point in debating it with you if you can just declare anything you don't like "presents it as rejected!" (whether it actually says that or not)? There isn't "wide disagreement" either, there seems to be wide agreement and a small group that doesn't agree (which includes you). I'm disappointed to hear you say that you aren't going to change your mind until either you declare an argument "reasonable" (love the ridiculous strawman that you have been ignored, that's just hilarious) or the policy is changed.
:::But along those lines...I think the policy is just fine but it's just getting wikilawyered in this case - is there any reason to tweak the policy wording to make it more weaselproof? Or is it fine as-is, and should we just take the refusal to follow policy to the next stage of dispute resolution? --] 23:32, 10 April 2007 (UTC)
::::Let no one unfamiliar with the page and its/their history be fooled: the skeptical position, even where only a very few skeptics have spoken and even where no science has been done on the subject, have been given a huge amount of attention in the article. It has been argued that even when 90% of the people who know about the subject believe the thing is paranormal, they are actually in the minority. This for no other reason than that they are not skeptics. No, I think that the rules need to be made clear, and I think you should put them in just as Seraphimblade said. Then no one would be in doubt.
::::Put that in the rules or concede the argument. Don't come and try to weasel out. I'm calling you out on this.
::::I meant "wide disagreement" in terms of "great gulf" not "lots of people."
::::Reason is reason. Why do you think it can merely be "declared"?
::::Don't bother with the wikilawyer thing- you can't get away with it here just because few people here know you. You taught me all I know about wikilawyering, and I would absolutely love to be half as good at it as you are, because I could really put to good use the power it unfortunately gives one around here. Coming from you, really, it is a compliment that you would think me capable of it, so thanks.
::::Put that in the rules or concede the argument. Don't come and try to weasel out. I'm calling you out on this. '''If reliable sources have not been found to indicate that mainstream science accepts an idea, mainstream science rejects it.''' Put that in ]. Do it. Don't try to get out of it. That's the way you and others have been writing the articles, so put it in the rules and see if it sticks. ''']''' <sub>(] Ψ ])</sub> 01:19, 11 April 2007 (UTC)
:::::Martin is right here. The rule (the actual rule) explicitly says that if mainstream sources cannot be found then it should not be assumed that a subject has been rejected. But the rule is being interpreted as if it should be assumed that a subject has been rejected - as per Seraphimblade's direct statement of that very thing above. The point here is either change the rule or obey it as it currently is. Re the EVP article, it is ludicrous to suggest that the rule is being applied appropriately. We have had statements saying "scientific explanations for EVP include...", and we have had those supposed scientific explanations actually take the place of the definition at one point. We have also had the claim "EVP has not been considered or accepted by the mainstream scientific community" - a direct quote from the rule - removed on a number of occasions by skeptical editors (it is not currently in the article). What this does is serve to muddy (hide) that point and pave the way for the "skeptical" explanations to become the mainstream. For example, we currently have about 90 words for paranormal explanations and about 900 for skeptical explanations (even though those 900 words just say the same thing over and over again). One would not think, from that ratio, that the skeptical view was not the mainstream scientific view. How else does a minority view of this type come to be given so much air-time. There is much pretense going on in the EVP article and all of it surrounds the muddying/changing/breaking of the rule Martin is talking about here.] 12:59, 11 April 2007 (UTC)
===Messianic Judaism and Undue Weight===
I am confused about how the Undue Weight policy should be applied in certain cases. I recently spent some time trying to clean up and expand articles relating to ] (MJ), which admittedly is a minor religious movement within Judaism. In fact, mainstream Judaism considers it not to be Judaism at all. This creates conflict between editors who hold views of different sides of the issue. MJ is a real phenomena in the world that can/should be covered by Misplaced Pages. By its own claims it is related to (or is a sect of) Judaism, and thus could be mentioned in certain articles where relevant. The counter-argument is that MJ is such a small minority that virtually ''any'' mention gives undue weight to this fringe position, thus MJ should be relegated to its own, separate articles. This use of Undue Weight policy is criticized by pro-MJ editors as it tends to lend support to the anti-MJ view. (Popularity doesn't make it correct.) Since MJ ''is'' a minority view within the realm of things Jewish, and this specific issue is particularly charged, true consensus is nearly impossible to find. It seems that certain policies (], ], etc.) can be used by a majority faction to censor differing views, and in situations where there is no one view that can be proven correct in a "scientific" sense—which covers nearly everything religious—editors such as myself are left in a quandary. This conflict has been so polarizing at times that not only have MJ references been completely eliminated from articles in the Judaism domain repeatedly, but articles/templates within the ] have had links ''to'' "regular Jewish" articles removed, as this was seen as "hijacking" and/or "misrepresentation of MJ as mainstream". With these policies in place, and given the existing understanding of them, is it even possible for legitimate (albeit minority) views to be fairly represented on Misplaced Pages? Can there be ]? Or is it acceptable that the ignorant reader of Subject X be kept in the dark that different views of the subject even exist? ⇔ ] 15:58, 11 April 2007 (UTC)
: Maybe some fresh eyes would help. Being a total outsider to Judaism in general and having read the article ] for the first time, my impression is that the article is very informative, yet has a slight edge of defensive ] towards the end where it discusses the controversy between mainstream Judaism and the conflict with Jews For Jesus. Regarding links to your article, in the "mainstream" ] article, I see mention of the MJ movement in ] which appears to be in appropriate weight to the other topics. Again, this is just my opinion after a cursory glance. -- ] 23:58, 11 April 2007 (UTC)
::The ] is much appreciated. I have a feeling that is what this situation really needs for resolution, as all the people who typically weigh in are too close to the issue. OTOH, those not close to the issue have no interest in following its development for any length of time. If the MJ articles seem a tad defensive in places, it's probably because they are—seeing most every edit reverted tends to wear on a person. (Is it a ] if the perception of persecution is legitimate?) ] is going to start trying to mark articles where these differences have been worked out amicably (or not), as a step toward better resolutions in the future. ⇔ ] 15:53, 12 April 2007 (UTC)
::Louie, here is (a revert war over a footnote, in this case) for you. Follow the edit history through the rest of 2007-02. ⇔ ] 17:15, 12 April 2007 (UTC)
== ] ==
A case has been filed concerning ] --<small> ]</small> <sup>]</sup> 19:52, 6 April 2007 (UTC)
== Uploading other people's images from Flickr with Creative Commons tags ==
Are we letting people upload images from Flickr that they do not own just because they are tagged as Creative Commons (tagged on Flickr, that is)? I noticed someone uploading the images of various Flickr members that use Creative Commons tags on their pictures. I think that it is a bad idea. First, if the owner closes their Flickr account or removes the image from their account, then all we have is the uploader's claim that it is licensed under Creative Commons (I say "is licensed" because I checked the Creative Commons website, which claims that the licensing is non-revocable (actually, it would be nice if there were a conditional variant)). Also, while Misplaced Pages might be able to legally use the images under Creative Commons, the image owners may not have envisioned this use. If this is the case, the images are not worth the ill will using them would create. -- ] 10:01, 7 April 2007 (UTC)
:I see nothing wrong with taking images from flickr, as long as everything is credited properly. I would strongly encourage anyone who takes an image from flickr to drop a message with the flickr member to let them know where their image is used, just out of courtesy. I wouldn't be too concerned with the flickr people being opposed to us using the image as they went to the effort to change the license and presumably they understand what the license meant. As far as verifying that the license is correct, if uploading to the commons, there is a bot that automatically handles that if you choose the flickr option from the drop down menu during the upload. That way if, as you suggested, the flickr user deletes their account, there will be a secondary confirmation that the license is indeed correct. I don't think WP has such a thing, but all flickr images should probably just go onto the commons anyway, so there really isn't a need for it. --] (]) 10:13, 7 April 2007 (UTC)
::The purpose of the creative commons share alike licence is to allow specifically this action: the unhindered downstream use of material under an identical licence. <span style="font: small-caps 1em Optima">]</span> 19:36, 7 April 2007 (UTC)
:::While I agree with PS2pcGAMER and Sancho in principle, I would also urge caution. I've seen copies of my own work appear on Flickr under blatantly incorrect licensing. We should keep in mind that some of what appears on Flickr is simply stolen. Anonymous Flickr users who claim to have very large, diverse and professional seeming image protfolios should be treated with all due scepticism. ] 19:46, 7 April 2007 (UTC)
::::Good point. I was thinking about a similar problem the other day. I requested via e-mail that somebody release under the ] an image that I found on their website. They agreed, I uploaded the image, credited the creator, and forwarded their agreement to release the image under the GFDL to Wikimedia (all the standard procedure when obtaining GFDL permission for use of material found on the web or elsewhere). However, it seems extremely hard to verify that the person releasing the material actually legally has the ability to do this! Maybe it was a copyright violation on their part before I even made the request for them to release it to the GFDL. How is this problem dealt with in this case? <span style="font: small-caps 1em Optima">]</span> 20:09, 7 April 2007 (UTC)
:::::I thought Commons has their own Flickr reviewer, who is an admin. ]<sup>], ]</sup> 22:21, 7 April 2007 (UTC)
::::::If memory serves, it was original setup so that admins had to review flickr images. Now a bot ] handles that task and an admin only has to intervene when ]. --] (]) 07:52, 8 April 2007 (UTC)
:::::::Oh yeah, I forgot the name, it is FlickreviewR. But I didn't know it was a bot. Then the question becomes if the bot reviewer is reliable or not. ]<sup>], ]</sup> 16:12, 8 April 2007 (UTC)
== Another false Living Person bio. ==
Today, the bio of Hollywood actor ] was vandalized by anon. IP 209.226.38.87, who stated that Sevier "announced he was gay on April 4". This was undetected for two hours.
Further, said vandal also added a "Category:Gay Actors" to the Sevier article, which went undetected for '''6''' hours.
I know that ] is strongly committed to the founding principle of anon. edits to Misplaced Pages, but realistically, how much longer can this go on for Living Person bios, especially high-profile celebrities?
Is this the proper forum to propose a revision to Misplaced Pages Policy? If so, I propose changing the policy to:
:'''Automatic "Semi-Protection" for all Living Person articles'''
<i><b>]<font color = "darkblue"> <sup>]</sup></font></b> - </i> 12:27, 7 April 2007 (UTC)
::I believe that the current policy of allowing anonymous edits can go on indefinitely, even for Living Person bios. In the example you give, the vandalism was noticed and corrected. Perhaps we just need to watch more diligently articles that are biographies of living persons. <span style="font: small-caps 1em Optima">]</span> 20:24, 7 April 2007 (UTC)
:::I agree. Also if editors have been away from WP when they notice vandalism, checking the edit history for any previous vandalism before reverting only the last example would help. ] 20:30, 7 April 2007 (UTC)
::::Perhaps there should be an easy access BLP watchlist/recentchanges like many Wikiprojects have. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 22:23, 7 April 2007 (UTC)
::::Apparantly there is: see ]. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 22:34, 7 April 2007 (UTC)
:::::Very nice. How can we bring more attention to this? <span style="font: small-caps 1em Optima">]</span> 22:45, 7 April 2007 (UTC)
::::::I've requested that this be added to the top of the RecentChanges page. I will report back here later to announce where exactly. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 03:22, 8 April 2007 (UTC)
::::::Include a link on the BLP (or whatever the Living Person Biography acronym is) template? ] 20:42, 8 April 2007 (UTC)
::Okay, its been added to the Recentchanges page in the "Utilities" row as a link titled BLP. I've tried to advertise this the best I can. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 18:44, 9 April 2007 (UTC)
I'm going to go out on a limb and agree with JGHowes. I am against shutting Misplaced Pages down to anonymous users but I believe I could support a proposal to make all BLPs semi-protected. Yes, we will inevitably lose some constructive edits by anons. However, I feel that Misplaced Pages's reputation is continuously hurt by incorrect information/vandalism to BLPs. They seem to bring the most negative attention to Misplaced Pages and it appears to be getting more frequent. If I remember correctly, the edit that claimed Sinbad had died was reverted after only a few minutes but that didn't stop the presses from reporting Misplaced Pages's claims he had died (also despite the fact that it was reported elsewhere before it was added to Misplaced Pages). There are many people out there that would like to see Misplaced Pages fail and I'm sure they are aware of Misplaced Pages's vulnerabilities regarding BLPs. Besides, if an editor truly wishes to improve a BLP, it may be more of an incentive to register.↔]•] 19:36, 11 April 2007 (UTC)
==See Also==
Is there an official policy regarding criteria for inclusion into the "See Also" category of an article's page? I removed some things which I felt did not belong and am wondering what the policy is. I didn't see anything in the ]. ] 13:00, 7 April 2007 (UTC)
:There is a bit in ]. -- ] (]) 14:06, 7 April 2007 (UTC)
== Deleting Policy and Samuel Ball (academic) ==
I get the conflict of interest issue and am ambivalent over the matter. I believe I have learned much with the posting and am satisfied with that.
I am concerned that notable persons may be deleted for no better reason than the apparent conflict of interest. It is easy for some, who falsely believe themselves to somehow feel slighted by something I wrote, which didn't, to gang up and claim disinterest. I have never spoken up for the article, and won't, but would appreciate knowing whom may be interested in improving such material ] 01:00, 8 April 2007 (UTC)
== Lists... ==
Is there a policy or guideline on wikipedia about lists in articles?]<sup>]</sup> 01:43, 8 April 2007 (UTC)
: There's {{tl|cleanup-laundry}}, and the ] guideline that covers which cases it might be best to convert embedded lists into prose. --] 01:48, 8 April 2007 (UTC)
Thanks ]<sup>]</sup> 01:51, 8 April 2007 (UTC)
== Conflict of interest rewrite ==
I've completed a rewrite of ]. You can see the rewritten version , or see it . Comments are welcome on the ]. --] (]) 02:13, 8 April 2007 (UTC)
== WP:SELF ==
I recently stumbled across the following image: ]. Concerns have been raised on that talk page before over a number of years, (but no one really looks at image talk pages in the first place.) Anyway, I'm wondering whether or not this is directly violating ] and is breaking the fourth wall; it appears to be used on a large number of articles so alot of work (or a little code) is needed to fix the broken links if deleted, so I decided to raise the issue here. - ] <sub>]</sub> 14:35, 8 April 2007 (UTC)
: WP:SELF says:
{{cquote|An article which is still in its initial development or under dispute often will include tags such as <nowiki>{{stub}}, and {{npov}}</nowiki> to help editors further develop the article, and the text in these templates include self-references.}}
: And the same applies to this image... it's something that facilitates development of the article. --] 17:38, 8 April 2007 (UTC)
::Query: Are there any templates/tags that simply state, "This article could be improved by the addition of images"? (You know, something similar to the concept of, "This article does not cite any references") Seems like it'd be a solution that was a bit more separated from the article (and that wouldn't be so incredibly ugly). ] 17:19, 11 April 2007 (UTC)
:::Indeed: {{tl|reqimage}} and related templates. But the "not picture available" might still be useful under many possible circumstances. ] 20:28, 11 April 2007 (UTC)
==African-American==
I originally posted this here ], but an editor suggested I bring it here for consensus. Now, this is a very PC topic, but please understand I'm not being insensitive, I just want to discuss what I feel to be ludicrous terminology.
The term African-American is a ] political term which in the past fifteen years has been forced upon us by the NAACP, politicians, and journalists, mainly the latter two. The majority of people however still use the correct descriptives ''white American'' and ''black American'', etc. Why does Misplaced Pages not also follow suit? Having said that, ], thus far, is the only country engaged in this ''politically correct'', though inaccurate, terminology. Since this is an international site, I would like to propose and see Misplaced Pages set up a guideline or policy to use ''black American'' rather than ''African-American'' to describe color. The latter doesn't make sense for many reasons. What if someone is 6th generation Jamaican and they come as a tourist to America? Does that make them a ''Jamaican African-American'' an ''African-American'' or a black? And what about people such as ], ], ], and others who are true African's but only white? Are they ''White African-Americans'' or are they ''African-Americans''? African-American is an ethnic term, '''not a color descriptive'''. In the rest of the world it adds confusion and people automatically think ethnicity, and even here in the ].
African American is widely viewed more as a media created term.
The term 'African American' has also been misused by some in lieu of 'Black', regardless of an
individual's nationality, ethnicity or geography. For example, during the 2005 civil unrest in
France, CNN anchorwoman Carol Lin referred to the rioters as "African Americans". This leads
to the belief amongst many opponents of the term that 'African American' presents an
'American-centric' view of black people across the world.<ref>http://en.wikipedia.org/African_american#Criticisms of the term</ref>
Is an individual from Calcutta is black and they are being described, are they then called a ''Asian African-American'' when visiting America? What about ]? Is he an ''African African-American''? Where does this confusing lunacy stop? Is a ''Black Englishman'' tourist then called a ''English African-American''? or in the quote above, is a Black French called and ''French African-American''? Additionally, on Misplaced Pages, America and American is a disambiguation which you have to direct someone to the correct meaning you're referring to. So to keep with Misplaced Pages, the term is not even properly used. Additionally the definition of African-American usually means ''someone who descended primarily from enslaved Africans brought to the United States.'' However, in today's mobile society, many have moved from the Caribbean, from Africa itself, from the UK, or from the Pacific islands, etc. Lastly, it does not follow common sense or pattern; An Iraqi-American is someone born in Iraq who became an ] citizen; an Asian-American is someone born in Asia who became an an ]; a Canadian-American is a person born in Canada who became an ] citizen; an African-American...however is suppose to be a black person...what? Looking at this from another country, there is no sense to this term.
My grandfather was black, my grandmother mixed, my mother mixed, one of my brothers black, my father white and so I'm not doing this maliciously. I am from the Caribbean and my whole mixed family still uses the term Black along with the majority of ] as well as non-Americanized West Indians. As mentioned I would like to see a policy/guideline set up instructing Misplaced Pages to balk the PC world like it does in many other areas and go for color, not the confusing exclusive-to-American-Media-and-Politicians ethnic descriptive political term that makes no sense. I would like to hear some feedback from the rest of you. --] (]) 15:09, 8 April 2007 (UTC)
:I would agree that using the term that will be understood by the world, including those in the US, is the thing to do. <span style="font: small-caps 1em Optima">]</span> 16:20, 8 April 2007 (UTC)
::Black is equally as controversial: I think we all remember sometime about 2-3 weeks ago when tha woman tried to insist that Barack Obama wasn't "black" because she said that in the US "black" means descended from slaves (which Obama isn't). --]<sup><font color="green">]</font></sup>'''<font color="orange">]</font>''' 16:27, 8 April 2007 (UTC)
:::I don't think the issue raised by Maniwar was one of controversy, but of world-wide understandability. Perhaps diligent wiki-linking to articles describing the term being used would help. <span style="font: small-caps 1em Optima">]</span> 16:46, 8 April 2007 (UTC)
::::Sanchom is correct in the assertion. And ybbor, you make my point for me. Because of the unclear African-American PC, there is a mis-conception in a few as to what a person should be. I would venture to say that the person who made the statement about Obama is either ignorant or because PC, is confused themselves. Again, African-American is an ethnic description, not a color descriptive. The rest of the world sees it this way. --] (]) 20:32, 8 April 2007 (UTC)
: Are you aware of ]? (] 18:45, 8 April 2007 (UTC))
::What are you trying to say? What relevance is that to the proposal? Please help me understand. --] (]) 18:52, 8 April 2007 (UTC)
:If we are going to be encyclopedic about this, how are minority ethnic groups in the US referred to in other major encyclopedia? This may be one case where the dusty language of authorative printed media could serve as the model to be used here.
:In the UK the terms '''when''' used are usually either Black, Asian, other followed or preceded by nationality (Black Briton, British Asian, etc.) where the emphasis is that they are are British, but of descent other than European. This obviously may differ from the preferences and realities in the US. (FYI, in the case of ], he is generally referred to as just ''"British"'').
:If this is intended to derive consensus in an attempt to form policy or a guideline, it may be wise to understand that what may be deemed appropriate in the US may not be so in the rest of the English speaking Nations with large non-European communities. Any policy/Guideline will have to be flexible enough to incorporate all groups existing in all Nations. As such it may not be possible to form such a policy/guideline. ] 20:04, 8 April 2007 (UTC)
::LessHeard vanU, I think it could work. You yourself mentioned, ''...'''when''' used are usually either Black, Asian, other followed or preceded by nationality (Black Briton, British Asian, etc.)...'' So to propose we use black would work both in the UK as well as the U.S. Again, we're looking for something that would work internationally. To say ] is an African-American is misleading and confusing. People the UK know he is British and so would wonder if we are they saying he's an American. To say he's black fulfills the color descriptive, and then we could indicate whether he's a U.S. citizen or a U.K. citizen. The quote from Carol Lin shows how wrong the term ''African-American'' is. If a reporter is talking about a black man in the U.S. and calls him an African-American (to use for color descriptive) they must then follow suit if saying a black man in Briton is an African-American British subject. Again, this term is ludicrous and just wreaks havoc with my logic and thinking and insults my intelligence. I am not a politician seeking office, so I can make sense rather than PC. Additionally, you are saying exactly what I am, that the term must be widely accepted, internationally. Yet the term, African-American is not. To say a black British is an African-American, which one must to be consistent, is very U.S. centric. ---] (]) 20:32, 8 April 2007 (UTC)
:::As I understand it, the term ''African American'' '''specifically''' refers to an American of Negro ancestry (notwithstanding the process by which the individual arrives in America). Asian American, Sino American, Indo American, etc. similarly defines ethnic derived populations in the United States only. In that context perhaps the wording is correct. When speaking of ethnic minorities in other nations then the naming conventions of that nation apply (which can differ; Asians to Americans refer to Japanese/Korean/Vietnamese origins, but Indian/Pakistani/Bangladeshi/Sri Lankan in UK terminology).
:::I am now unsure what the basis of your comment are. Are you addressing the point that it is only Americans racially dissimiliar from the (North) European origin majority that are referred to by their cultural origin, or some other point? I do not see how a person of African or other origin could be described as African American outside of the context of US citizenship. ] 23:23, 8 April 2007 (UTC)
::::if you reference the comment above by CNN anchorwoman Carol Lin, you will see that sometimes the media does just that. I am talking about how the Political correctness world of American politicians and the media use the term African-American, which is an ethnic description to describe a black American. When the American Media and politicians use the term, it is, incorrectly, being used as a color descriptive rather than an ethnic descriptive.--] (]) 01:13, 9 April 2007 (UTC)
:::::Oh, I see. Yes. Carol Lin used the wrong phrase to describe French of African descent (although the phrase French African is often used to describe people from the former French colonies, both those who live in France and those living in the former colonies - so there may not be an easily available phrase). When WP reports what was said by an individual then such ''mistakes'' should be retained, but when WP includes such ethnic groups then the appropriate phrase should be used (which may include <u>not</u> mentioning the ethnic background if not appropriate.)
:::::I don't think there need be a new or altered policy or guideline. It is simply a matter of good editing standards. People should be described as suits the subject matter, and as appropriate. If a black Briton is described as of African American ethnicity then it is an editing error and should be corrected. As a whole ethnic group then Africans and African descended people can be described as "''Black(s)''" in popular culture articles, and as "''Negro(es)''" in scientific articles. Same for all ethnic groups. Usually I would think that defining such individuals as a particular nationality first and foremost and only then as a ethnic group within that nation if appropriate. Does this make sense? ] 11:24, 9 April 2007 (UTC)
:We are losing site of the biggest issue here in this whole debate. The biggest issue is of ''self-determination''. We should only use terms to desribe a person that they themselves use. If John Doe calls himself "Black" than use that term in an article about him. If Jane Smith calls herself an "African american" use that term. It is rather presumptuous to decide how ''we'' should idenitify other individuals; we should let them do that themselves. This applies not only to this issue, it applies to ALL issues of labeling.--]|]|] 17:03, 10 April 2007 (UTC)
::It seems to me that ''both'' terms ("black" and "African-American") are, currently, socially acceptable, mainstream terms in the U.S., for (approximately) the same group of people. Some people prefer one, some prefer the other and some have no preference. That being the case, I believe that both are acceptable on Misplaced Pages. ] 18:28, 10 April 2007 (UTC)
::Well, yes... but do we always know how the subject prefers to be called? If we are citing other sources then we use their terminology without considering if the subject agrees or even objects. What is the subject refers to themselves as ''"American"''?
::The original point, though, was that a newsreader referred to Africans in a different (European) Nation ''as'' African Americans, which showed an Ameri-centric lapse of attention. I'm pretty sure it was just a mistake, but one that would cause some dismay if repeated in Misplaced Pages. ] 21:35, 10 April 2007 (UTC)
* I disagree with the contention that "African-American" is a media-created term. I'm from the US. I'm white, my sister-in-law is black. She educated us to call her "African-American", but also uses "black". My sense is that the hyphenated term emphasises that Americans of African extraction have legitimacy as Americans; people of European extraction don't have a special claim on that legitimacy. I agree that the terms "African-American" and "black" are primarily a matter of self-definition, so we should leave it to editors to balance respect for self-definition with clarity for an international audience. It's pretty clear to me that using the term "anything-American" to describe people who are not from the USA is simply mistaken (leaving aside the issue that "America" refers to two whole continents and not just the USA). --] | ] 09:17, 12 April 2007 (UTC)
:::Jdlh, you can disagree, however it is known by many that the term is more media centered and media forced. Misplaced Pages itself has stated this, and other encyclopedia's have stated this. It grew out of Political Correctness and was adopted by the media and politicians who took it mainstream. The fact is, it ''is'' driven by the media because of PC. A similar case would be the term ''undocumented workers'' being used instead of ''illegal alien''. It is media and politician driven. But again, you all are missing the point as LessHeard vanU pointed out. This is not a universal term and it causes confusion to international readers. It is not proper English. You cannot use an ethnic descriptive to describe a color. Additionally, who is going to decide whether the person should be a black or an African-American? Again, do we say Seal (the musician) is black or is he a black Enlishman, or an African-American? The latter is false because he is not an American. And what about true African's, as pointed out, like Roger Whittaker (etc.) but who are white? No one has addressed these issues. We want to express truth and facts, not political correctness. Case in point, though maybe not a good one, in the UK, the term Fag refers to Cigarettes, but we don't use this term universally because it has different meanings in different parts of the world. So we use the more accurate and universal term of cigarette. Again, this term adds confusing to the rest of the world...''It is a ] exclusive term'''. We should represent the world on this encyclopedia, not our own country. Just like we are not going to change all the instances of cigarettes to fags, we should not use an ethnic term to describe color. The ] is the only nation that uses this term. --] (])
* Not that I (or anybody) can do anything about it, but I find it distressing that these 'labels' are not only politically charged, but mostly grossly inaccurate and even confusing. What are we trying to label? Geographic origin, as in African, Asian, European, American, Oriental? The problems here are obvious. White Africans, South and Central Americans and Canadians. Racial origins, as in Negro, Caucasian? (also has geographic and skin clour connotations). And where does the racial classification "Hispanic" come into the picture? Or are we trying to pigeonhole by skin colour? Black (well, not really), white, (well not really), er....yellow (not acceptable and not really). Or is it by cultural/historic/religious affiliation, as in Muslim, Buddhist, Jew? The next problem is that with changing perceptions, politics and fashion these epithets gain and lose favour. "Negro" makes way for "Black", makes way for "African American", which will, no doubt, make way for whatever. ] 04:39, 13 April 2007 (UTC)
'''Vote temporarily stopped...will resume after more discussion.''' --] (]) 12:11, 13 April 2007 (UTC)
*<s>===Consensus call===
I'm not sure if this topic is too PC that no one wants to touch it or if it has run it's course of discussion(s). I would like to call for a consensus of Misplaced Pages adopting the policy to the replace the inaccurate, politically-correct, ''African-American'' term to describe color to the more global and accurate term ''Black'' (see original post and discussion). As mentioned, the term is ]-Centric and causes confusion on a global scale. Again, refer to original post and discussion. --] (]) 17:08, 11 April 2007 (UTC)
'''Replace''' - per discussion. --] (]) 17:14, 11 April 2007 (UTC)
*'''Keep discussion open'''. Maniwar opened this topic, what, 90 hours ago? I see active discussion still underway. I don't see signs that it's too PC to touch. A vote now is premature. If I have to vote now, I say '''No Policy Change Needed''', leave this writing issue to editors' discretion. --] | ] 09:17, 12 April 2007 (UTC)</s>
Should it be decided to put this to a straw poll or consensus call, then it should be on its own page with a redirect from here.] 20:30, 12 April 2007 (UTC)
== Put SEARCH window back near top of page ==
Moving the SEARCH window down so far in the left-hand colum means it is necessary for the majority of users to have to scroll first to get to it -- bad policy. "Sign in/create account" is nowhere near as important as having SEARCH right there up at top, ready to go, on every single page of the Wiki. Please revert to previous format.
-- JRS <small>—The preceding ] comment was added by ] (]) 17:46, 8 April 2007 (UTC).</small><!-- HagermanBot Auto-Unsigned -->
:First, I think it was always like this; there is no earlier format to revert to. Second, a quick look at photoshop reveals that the distance from the top of the page to the ''bottom'' of the search box is exactly 481 pixels. The typical Internet explorer window bar and browser bar, etc. takes up 116. This comes out to 597 pixels from the top for the average user. Unless you're using 800x600 resolution, it shouldn't be an issue. Besides, it's getting pretty rare to see an 800x600 (it was originally proposed in 1989). --]<sup><font color="green">]</font></sup>'''<font color="orange">]</font>''' 20:32, 8 April 2007 (UTC)
::The indicates Misplaced Pages hasn't had a search bar on top of the page since at least May 2004. --]<sup><font color="green">]</font></sup>'''<font color="orange">]</font>''' 21:44, 8 April 2007 (UTC)
::: The location of the search bar depends on the skin one uses with Misplaced Pages. The Classic skin put the search box at the top of the page in 2004, & still does now in 2007. -- ] 23:30, 9 April 2007 (UTC)
: states that ~81% of users use a resolution of 1024x768 or higher. -- ] <small>(])</small> 21:49, 8 April 2007 (UTC)
== Links to or mentiosn of "attack sites" ==
There is dispute now on ] as to whether '''any and all'' links to, or even mentions on-wiki of the names of "attack sites", should be considered blockable offenses. Some editors are caliming a very black&white approach to this should be followed. I think this is too absolute. I don't think there is policy-level consensus ywet on claims being made and, I gather, acted on. More eyes would be good here. ] ] 01:04, 9 April 2007 (UTC)
== Research ==
Question: If I can cite reliable sources, what type of research is allowed?
] 16:30, 9 April 2007 (UTC)
:You might have read this already, but the ] page in a nutshell is:
:*Misplaced Pages is not a publisher of original thought.
:*Articles should only contain verifiable content from reliable sources without further analysis.
:*Content should not be synthesized to advance a position.
:<span style="font: small-caps 1em Optima">]</span> 16:54, 9 April 2007 (UTC)
:Yes, thank you, i did. However, what I'd like to post is a culmination of reliable content. It certainly falls within the domain of theory; however, the topic of Gravity is listed and that is only theory, as is much of quantum physics. Again I ask, if my sources are reliable what is allowed?
:] 17:20, 9 April 2007 (UTC)
::Generally, any material that can be attributed by reference to a reliable source can be included. The topics that you mention, gravity and quantum physics, for example, should include only information that can be attributed to a reliable source. The way in which it is worded, or the manner in which the article is structured, however, should also comply with the ] policy. One thing that is not allowed is taking one source that says, "If A, then B", and a second source that says "If B, then C", and using them together in a Misplaced Pages article to support a statement that says "If A, then C". We'd have to wait for a third party reliable source to make this connection before it we can include it in a Misplaced Pages article. <span style="font: small-caps 1em Optima">]</span> 17:38, 9 April 2007 (UTC)
Excellent Answer Sancho! I have been searching wiki for the last hour and finally have my answer. I also found relevant information here: http://en.wikipedia.org/Wikipedia_talk:Attribution/Community_discussion#What_does_No_Original_Research_have_to_do_with_Verifiability_.26_Reliable_Resources.3F. Thank you very much.
Jhize 17:50, 9 April 2007 (UTC)
Basically, if at anytime I reach a conclusion (If A, then C). I must provide a reference to that as a citation.
Now one last question if you'll entertain me...If what I am describing in this article I am referring to has a specific name and this name is scientific in nature and I provide a link to the definition, is that acceptible? I have read the policy about coining a phrase and this seems to tell me no. However, I didn't coin the phrase "Endothermic Nucleosynthesis". This term is used on the following page; http://www.theoriginofthesolarsystem.com/pb/wp_54bea476/wp_54bea476.html. The problem is, it refers to this process on a stellar scale; while my article would be atomic scale. Additionally, Endothermic is found here: http://en.wikipedia.org/Endothermic and Nucleosynthesis is found here: http://en.wikipedia.org/Nucleosynthesis. Together these two Wiki definitions are exactly the definition I require. It seems that the Wiki definitions are more appropriate for my use. Is this still considered "coining a phrase"?
I am obviously going to have to cite anything that seems "new". Is my thought process way off track here?
Jhize 18:05, 9 April 2007 (UTC)
:No, you're not off track at all; any material added must be directly and explicitly supported by cited sources. As regards the term "Endothermic Nucleosynthesis", however, I believe that since you intend to use the term in a way that hasn't been used before that it would be "coining a phrase" (]). I tried looking for references that use the term in this manner (at an atomic scale), but couldn't find any. Maybe you know of some sources that use this term applied to the atomic scale. If there are none, it's probably a little too early to add an article on this topic to Misplaced Pages. I hope you will still join our efforts in improving other articles, and later, you can create this article. <span style="font: small-caps 1em Optima">]</span> 18:38, 9 April 2007 (UTC)
== New Handicap Symbol ==
]
Why are we so stuck on it being a wheelchair? What does everyone think of this? --] 20:22, 9 April 2007 (UTC)
:It kind of looks like a slingshot. But you're right, maybe there's another symbol that we can use. <span style="font: small-caps 1em Optima">]</span> 20:35, 9 April 2007 (UTC)
::We're stuck on the wheelchair, because it indicates where a person in a wheelchair can go. Way different from where a person on crutches can go. I think they can go pretty much anywhere, can't they? - ] 21:10, 9 April 2007 (UTC)
* I'm not sure what problem you are trying to solve by using a new symbol. I do know that there is a broad, international recognition of the wheelchair symbol to signify information or locations or what have you that are relevant to people with disabilities. By using the standard symbol, we build on shared understanding. I would want to see a very strong reason to give up that advantage. --] | ] 09:22, 12 April 2007 (UTC)
:: Some silly person put the "standard" symbol under a restrictive license. :-/ --] 11:08, 12 April 2007 (UTC)
== Image size ==
A short while back I was blocked for 24 hrs by what I feel to be an overzealous administrator for allegations of incivility and vandalism against me that have thus far been unsubstantiated.
The dispute centred about the size of images used in various articles I had written - ], ], ], ] to mention just a few. The reversionists who favour thumbnail images cited MoS guidelines that are not at all clearcut. I pointed out that the vast majority of articles using images, do not confine themselves to thumbnail sizes, and in fact use quite large images, for example ], ], ], ], ], ], ], ] to name but a few. Apparently the editors of these pages have
# not heard of the thumbnail guidelines OR
# know of such guidelines but ignore them OR
# don't interpret these guidelines to mean obligatory use of thumbnails.
*'''1 Does WP have a firm clearcut guideline for image sizes?'''
*'''2 If such a guideline exists, why is it ignored by the vast majority of articles with images?'''
*'''3 Why is such a guideline necessary (if it exists)?
''' ] 21:16, 9 April 2007 (UTC)
:First of all, I just listed a handful of your images at ]. You have tagged these images as GFDL when they probably are not. The name and year of death of the author should be given, as well as the date of publication of the image.
:When we use copyrighted images we generally reduce their resolution to avoid infringing copyright. There is no specific rule about how low the resolution should be, however the resolution should not be larger than necessary. 300px wide is a general rule of thumb, but it ultimately depends on the image in question and how it is used. —] <sup>(])</sup> 21:35, 9 April 2007 (UTC)
:For more information, please read ]. —] <sup>(])</sup> 21:38, 9 April 2007 (UTC)
::After looking about a bit, it seems that Remember the dot's answer misses the point some. This is not about the size of images uploaded, but rather the size of images as they appear in the article. Paul has been involved in a dispute with ] over the formatting of images in articles, specifically the specification of the size of thumbnail images. Kitty feels that the size should not be specified, and points to the MOS. Paul replies that the MOS is a guideline and not policy, and therefore optional. The discussion became heated. Paul was blocked by ] for ''Personal attack after specific warning'' after Kitty brought an edit to the attention of Tyrenius in which Paul claimed in the edit summary to be "repairing damage by a stalker" after being warned by Tyrenius that such summaries violated ]. (I apologize to any and all involved if my summation is inaccurate.) To answer Paul's question: it is my understanding that the MOS is indeed a guideline, but it is widely followed. Without a compelling reason, it is probably a bad idea to violate it. In this case, specifying the width of an image can screw up the layout for some readers so much as to make the article unreadable. Misplaced Pages is used by people who may have very good reasons for specifying smaller, or larger images than what looks good in your browser. Since specifying an image size overrides the preferences they may have set, it should not be done without a very good reason. Essentially the guidelines sat that it should only be done if shrinking the image to default size will make the image unusable. ] 23:02, 9 April 2007 (UTC)
:::Your summation is accurate, although I regret that you introduced the users' names - I was hoping to keep personalities out of the discussion, since an issue is automatically polarised and mindless supporters are often drawn in to add to the noise, if not to constructive ideas. Your setting out of the reasons leading to WP's favouring thumbnails, though, leads right back to my question 2 above.] 07:01, 10 April 2007 (UTC)
::::In a word ignorance. I do a lot of medieval manuscript articles, and I used to specify image size. However, when the reasoning for the guideline was brought to my attention, I uderstood and accepted it. Perhaps the other editors are not aware of the guideline. Also, many (but not all) of the images in the articles you point to are of paintings with a horizontal orientation. Perhaps the editor in question decided that in order for the image to be understood it needed to be wider than the default thumbnail setting (for an extreme example of this see Monet's ''Waterlillies'' in his article). Although the guideline doesn't state it I believe that certain images have such iconic status that an argument can be made for making them larger. For example, ''The Child's Bath (The Bath)'', by Mary Cassatt, is probably her best known work, and deserves a larger image. Other editors may disagree. ] 14:35, 10 April 2007 (UTC)
The thumbnail issue is also important because it allows the user to have the pics appear at his/her size according to their preferences (see the preferences box on top of your screen and click on files). ] 23:07, 11 April 2007 (UTC)
:I posted a question in the technical section, but it bears repeating here:- "Just how difficult is it changing WP's image-handling software to deal with the 'screwing-the-browser' issue without forcing thumbnails on everyone?". The other thing that puzzles me is that some articles happily mix thumbnails and larger images. What does that do to the problematic browser? ] 12:30, 12 April 2007 (UTC)
==Infoboxes and MOS==
Is there anything in the ] about the use and content of Infoboxes? If not, shouldn't there be? ] 08:16, 10 April 2007 (UTC)
:There are a number of topic specific subpages of the MOS that include guidelines for infoboxes for articles about that topic, for example ], and ] purports to be part of the MOS (although it's reachable from ] only through ]). Many infoboxes are "owned" by a specific ]. Including general guidelines about infoboxes in the main MOS seems like a reasonable idea to me. Please bring this up at ]. -- ] <small>(])</small> 14:38, 10 April 2007 (UTC)
== ] ==
An essay I wrote, ], was promoted by others to proposed guideline status. Please take a look and contribute. The aim was to define what is an 'attack site', which seeks to out the personal identies of Wikipedians, and/or harass them, and why they should never, ever be linked to or promoted on Misplaced Pages for the safety and protection of editors. - <font color="#0000C0">]</font> <sup><i>(<font color="#7A1616">]</font>)</i></sup> 13:15, 10 April 2007 (UTC)
== Lists of names ==
Right now, lists of names appear in three contexts:
# The ].
# Articles dedicated to names. These vary dramatically in quality: I cite ] as a very good example, and ] as a very bad one.
# ] pages, such as (good) and (better).
This triplicity of formats scatters our efforts and confuses editors (such as yours truly) who are trying to clean up pages with lists of names. I think we need a policy to specify what to do with lists of names. In particular, I think we should either officially endorse LoPbN or remove it once and for all. --] (]) 18:27, 10 April 2007 (UTC)
:I disagree that LoPbN should be the only name list or not exist at all. (BTW, would you mind editing your own entry above to display the names of the pages you link? ] instead of ], and likewise for ], ], ]?) But I do think that a policy statement on the acceptability of pages or sections listing people by their given name, surname, or middle name might ease some churn. A list of people named John would be difficult, whereas a list of people named Banana would be manageable (]). Some questions that would need to be discussed:
:#Should surnames be treated differently than given names
:#When to lump the name holders on dab pages (])
:#When to make name pages (]) separate from dabs (])
:#When to make separate pages for given-name and surname holders (] and ] - and the disambiguation info should really be pulled out into ] instead of ] IMO; I'll get to that soon)
:#Whether any of these options should be used in favor of lists like ], ], or ]
:#How (if at all) this affects people who are at least commonly known by a single name (], ], ], ], ]))
:Some links to prior and current discussions:
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:*]
:I'm sure there are more; the discussion surfaces frequently. These aren't truly disambiguation pages -- they don't disambiguate articles that would otherwise have the same title. No article on ] would have been titled ], for example. The list of names (by given or surname) appear to me to go counter to ], but mine was the minority opinion in the discussions I was part of.-- ] 00:31, 11 April 2007 (UTC)
::Links clarified per request. --] (]) 05:01, 11 April 2007 (UTC)
== ] and the inability of anons to see the ''new messages'' bar ==
How how these two never affected one another? I mean one would expect that this would necessitate a change in the vandalism policy--<small>'''VectorPotential'''</small><sup>]</sup> 23:13, 10 April 2007 (UTC)
: The people who thought that up never edit as anons (anymore) --] 01:09, 11 April 2007 (UTC)
:: What? I post warnings incrementally assuming that anonymous users see the "new messages" bar. Do they not? <span style="font: small-caps 1em Optima">]</span> 02:29, 11 April 2007 (UTC)
:::I believe they do see the bar actually. (I once asked this somewhere). From looking at some comments on the ] and on ], it seems the some anons are having problems with the bar not going away after checking messages. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 02:40, 11 April 2007 (UTC)
:::Not all of them see it (for example, I just tried it on myself, and I don't see it). There is a short thread on this at the technical village pump. I don't know much about it. ] · <small>]</small> 02:43, 11 April 2007 (UTC)
== Template deletion RANT(ish) ==
'''<rant>''' <small>''(hey, I need to blow off steam too, sometimes)''</small>
Alright, now this is really insane. I found {{tl|Policyalteration}}, which is obviously broken (and was broken both before and after I made some clarifying edits to ]) . So since people really shouldn't be using this template ever, I put a quick {{tl|db|inappropriate template}}, I mean, duh. :-P
So I got back a ''(decline speedy, discuss at MFD instead)''.
Well that sucks. You can always trust CSD %-)
So let's see, first of all, shouldn't that be '''TFD'''? And then, all the *FDs have different policies with strange gotchas, and odd, confusing jargon, and I'm not going to wade through 10 different pages memorising the Local-Deletion-"Policy" of the day just to get rid of a single silly template.
So no, let's not do that.
So finally I throw on a {{tl|PROD}} like I should have done in the first place. But like, fsck, what's this? I need to subst it... well fine... but, oh crap, I'm not supposed to use it for templates.
Ok, pursuing this further was just not worth it. At that point, I just gave up.
We now have one crappy template still alive, ready to be abused by some pitiable fool for next week's wikidrama installment;-)
'''</rant>'''
In practice, it turns out that ordinary users can't get blatantly silly templates removed at all easily.
Of course, the reason I had my admin flag turned off is for precicely this kind of reason. Now I'm forced to try to figure some way to {{tl|sofixit}} at least. ;-)
--] 01:04, 11 April 2007 (UTC)
:You're right, the 3 steps at ] are ''so hard'' (and one is optional, depending how you read it). It would have taken you less time to list it at TFD than to write this. ]≈<small>]</small> 01:11, 11 April 2007 (UTC)
:: <looks, looks twice, finds after 3rd try> Oh you mean the 3 steps spanning a single screenful, wedged in after the > 100 line index, the what and what not to do on the one side, and the surely over 1 megabyte of substs on the other side? Ahuh.Ok... now reading the steps... they are marked I, II, III... let's see.... step I is just under 1k of details you need to remember... II seems simple enough, oh and step III tells you to go off and canvas people and stuff. Ok, let's not quite do that.
:: You know what? I think that just figuring that through cost more time than typing the rant. :-P
:: This was supposed to be quick :-/
:: Granted TFD currently looks to be somewhat more streamlined than some other *FD processes, but there is no standardization, so you have to learn different ways of doing things for each. There's no one-stop-shop. --] 01:26, 11 April 2007 (UTC)
:Oh, and I object to the term "ordinary users". I find that offensive. ]≈<small>]</small> 01:17, 11 April 2007 (UTC)
:: Fair enough, ''"users without an admin flag"'', then? --] 01:26, 11 April 2007 (UTC)
:::So are you suggesting we overhaul, standardize, and simplify XfDs or cleanout some of the hyper-specific, totally unused templates? Either way I'm behind it. <font color="maroon">]</font>'''<small>]</small>''<font color="navy" face="cursive">]</font>''''' 02:44, 11 April 2007 (UTC)
:::: <sigh> Um, see ... that's why I should learn to keep my mouth shut. Now I've just made myself a new big job, haven't I? </sigh> --] 12:41, 11 April 2007 (UTC)
==Proposed guideline: Misplaced Pages is timeless==
I have proposed a guideline at ]. Should I announce it anywhere else? --] 05:51, 11 April 2007 (UTC)
:well, for one thing, it isn't. ] are included because they are ], which is equivalent to saying that some aren't because they are not. I would phrase this as an effort to "counter temporal bias", not as a statement of intent to weed out recentisms. We can't help it that Misplaced Pages as it is was written in the 2000s. ] <small>]</small> 12:44, 11 April 2007 (UTC)
::Are you implying that we shouldn't have an article on a similar "scandal" from 50 years ago, if sources exist? My intent is not to "weed out recentisms" but to ensure that older stuff is not deleted just because it's old. --] 02:52, 12 April 2007 (UTC)
:This looks a lot like: ]. There has been next to no discussion about this portion of the guideline, however. There was a bit of discussion of that phrase's use at ], but not much. It will be interesting to see how discussion on this goes. <span style="font: small-caps 1em Optima">]</span> 12:52, 11 April 2007 (UTC)
::Notability only deals with the existence of articles; this also covers inclusion of information in articles. --] 02:52, 12 April 2007 (UTC)
==Naming conventions for baseball players==
Please take the time to review and contribute to the discussion regarding naming conventions & disambiguation for baseball player articles going on ]. Thanks, ] 20:53, 11 April 2007 (UTC)
== Centralized Discussions ==
Are there any pages/lists of centralized discussions of commonly discussed issues, such as blanking user talk pages, removing warnings, etc. ? ] 23:03, 11 April 2007 (UTC)
:Nevermind, I found it: ]. ] 03:25, 12 April 2007 (UTC)
== Community Service? ==
Don't know if this belongs here, but I couldn't find a better place to post it
Does Misplaced Pages offer community service to members for making positive edits and contributions?
As a junior in high school, anything that can be put onto my transcript will be beneficial. Editing on Misplaced Pages is similar to other forms of "community service", and Misplaced Pages is a non-profit organization.
I guess the point I'm getting at, simply put, is can I put the hours I put into editing Misplaced Pages onto my college transcript?
I have seen a few instances where, an editor will raise the issue that an article is too large at, say, 7500 words or 8100 words. We have multiple history pages (and medical/psychology pages) with well over 11,000+ words, even some with over 16000. Where does one draw the line? It seems like Misplaced Pages leaves it to the discretion of the editor after about 8000 words. ] (]) 07:21, 18 December 2024 (UTC)
Thanks in advance
] 01:56, 12 April 2007 (UTC)
:Looking at the table, it's obvious that "above 8000 words=Split" is not "an absolute rule". I promise you that if it were, that table would say something that sounded remarkably like "if the article is above 8,000 words, then it absolutely must be split".
== Proposal for a "Stub:" namespace ==
:Additionally, we have ].
:Where one draws the line is: In a place that makes sense for the topic of that specific article, having thoughtfully considered all the facts and circumstances that apply to that unique article. ] (]) 07:41, 18 December 2024 (UTC)
:There was a lengthy discussion at ] about the size guidance, for the record. Splitting pages is a lot of work and not everyone thinks that spreading stuff over multiple pages is better for readers than having in one big page. ] (]) 08:19, 18 December 2024 (UTC)
::In addition to the above, what matters for the technical aspects of article size is not the number of words but the number of bytes. Word count can only ever be an approximation of that as the length of the words used matters ("a" is 1 byte, "comprehensive" is 13), the number and size of included media matters very significantly more. ] (]) 09:20, 18 December 2024 (UTC)
:::I think ] is a bigger technical challenge for long articles. The more templates, and the more complicated templates, the more likely you are to need to split for technical reasons. ] needs a split in part due to PEIS reasons. ] (]) 18:43, 18 December 2024 (UTC)
:What's more, there's nothing even in the excerpt here that would purport an absolute guideline. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 09:44, 18 December 2024 (UTC)
::It isn't an absolute rule, but ''usually'' an article having an extremely long high word count is evidence of a bigger problem with ] -- that it's too dense or detailed for a reader to use it as a first-port-of-call summary. As such, ''usually'', it's a wise move to create daughter articles for the detailed material, and strim it down to its essentials in the main article; this improves the readability of the main article and allows interested readers to follow up into the nitty-gritty. As {{u|Jo-Jo Eumerus}} rightly says above, though, there's not really such thing as an absolute rule in this place. '']'' <sup>]·]</sup> 09:59, 18 December 2024 (UTC)
:::What we now know is that many readers are looking for specific information, with few reading from top to bottom, but the search engines send them to the mother article even when a more specific daughter article exists. So the first port of call needs to be the most highly detailed. The advice in ] is therefore considered well intentioned but obsolete; stripping the mother article and pushing information down to the daughter articles defeats our whole purpose in providing information. ] ] 11:31, 22 December 2024 (UTC)
::::When you say “we know…”, “is considered” and similar, are you pointing to specific previous discussions, RfCs etc on this matter? “In the wild”, as it were, I still see these size limits regularly invoked, even if the conversation rarely ends at them. '']'' <sup>]·]</sup> 09:17, 23 December 2024 (UTC)
: Rather than draw a line, I'd rather just remove that chart. Can't imagine why a suite of concrete word counts and procedures would ever be very helpful. — <samp>] <sup style="font-size:80%;">]</sup></samp> \\ 16:29, 18 December 2024 (UTC)
::It absolutely makes sense to say at what page sizes that editors should start considering other options, as well as where splitting can be absolutely unnecessary. Nothing wrong with the table as long as it's clear those aren't hard or fast rules. ] (]) 16:41, 18 December 2024 (UTC)
:::Agreed, I find it helpful because it helps me remember what is generally too long for mobile users (I understand that mobile is generally a blindspot for us as editors because the vast majority of us don't edit on mobile but most of the readers are actually on mobile) ] (]) 16:49, 18 December 2024 (UTC)
::::I also believe that the chart is helpful. ] (]) 17:29, 18 December 2024 (UTC)
:There don't seem to be any absolute rules laid out there... Even "Almost certainly" is qualified not an absolute rule. ] (]) 16:38, 18 December 2024 (UTC)
*The optimal article size varies quite a lot, actually. Key things we need to consider include:
*:The likely readership. Someone who's looking up ] probably has time to read something long and thoughtful. Someone who's looking up ] might need basic facts, in simple words, very fast.
*:The cognitive load associated with the topic. ] is (very) long but easy to understand; ] is much shorter, but I bet it takes you longer to read, unless you have unusual expertise in mathematics.
:This is not the kind of thing on which we can produce simplistic guidance.—] <small>]/]</small> 17:03, 18 December 2024 (UTC)
:Misplaced Pages leaves it to the discretion of editors far far before 8,000 words. We have thousands of single sentence articles to attest to this. The average article is less than 700 words. ] (]) 17:15, 18 December 2024 (UTC)
::The median article length is around 350 words, and the mean is 750. About one in 75 articles has more than 6,000 words. ] (]) 17:34, 18 December 2024 (UTC)
:::You'll have to take the specifics up with ], although that ballpark range sounds the same. ] (]) 18:45, 18 December 2024 (UTC)
:No. ] (]) 18:52, 18 December 2024 (UTC)
*I've always felt that the kB of readable prose was a better metric for page size (such as is produced by various page size gadgets). Turns out, bigger words take longer to read than shorter words :P Doing it just by wordcount encourages a certain verbosity. For me, my rule of thumb has always aimed to keep big articles under 100kb readable prose. But there's no hard and fast rule, and there shouldn't be. ] <sup>]</sup>] 23:08, 22 December 2024 (UTC)
*:If I'm being honest, what might be the best metric is starting at the top and lightly hammering the {{key|Page Down}} key for a bit. If I groan before reaching the References section, it's too long. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 23:10, 22 December 2024 (UTC)
*::For example, results were heavily discouraging for ] until recently; ] at the article's uncaring girth—thanks Nikki et al.! <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 23:18, 22 December 2024 (UTC)
*:::26,000 words is {{tomats|26000}}. Another way to look at that table is by saying that if it's more than half the length of a book, it's pushing past being "an article" and edging up towards being "a book".
*:::Or you can look at it in terms of how many minutes reading the whole thing would take. There's quite a bit of variation, but for easy math, 300 words per minute means that a 15,000-word-long article would take 50 minutes to read, which almost certainly exceeds the interest and attention span of most readers. ] (]) 00:35, 23 December 2024 (UTC)
*::::I think the most fundamental scalar isn't quite reading time or even visual size, but structural complexity—for an online encyclopedia article, being overlong expresses itself in my increasing inability to navigate an article comfortably to read or locate what I want, or to understand the structure of the scope covered by it at a glance. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:38, 23 December 2024 (UTC)
*:::::Come to think of it, one thing that makes an article feel longer than its word count is if its sections, media, and other landmarks have been laid out in a careless or unnatural way. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 00:48, 23 December 2024 (UTC)
*'''No.''' And this was rather a pointless, self-answering question in the first place, not something for a VP thread. The answer to the posed question of 'Is the "above 8000 words=Split" an absolute rule?' is obviously "no", both by observing actual WP community practice, and just by reading the table the OP quoted: {{tq|> 8,000 words — May need to be divided or trimmed; likelihood goes up with size}}. Is anyone here actually confused into believing that A) "must" and "may" are synonymous, or B) that a guideline, to which reasonable exceptions sometimes apply, is somehow a legal-level policy that must be obeyed at all costs? In reality, there is never any hurry to split a large article, and doing it properly often involves a tremendous amount of work, involving both repair of citations (sometimes in great detail), and resummarizing the background context in the side article while also resummarizing the side-matter in ] style within the main article (and doing them distinctly enough that the results are not obnoxiously repetitive if the reader moves between the articles). Doing a good job of this can take several days up to a month or longer of tightly focused work, depending on the detail level of the material, the number citations, etc. It is not trivial, we're all volunteers here, and our readers are not going keel over and die if they reach a detailed article that's a bit longer than they were expecting or would prefer. Ultimately, an article that is ginormous {{em|usually}} should split, but there is no deadline, and it needs to be done properly (plus there are often conceptually different ways to go about it from a content-flow perspective, and that might require some consensus discussion). <span style="white-space:nowrap;font-family:'Trebuchet MS'"> — ] ] ] 😼 </span> 01:22, 23 December 2024 (UTC)
*:Ever since WAID reminded me of it, I've thought we should maybe link somewhere as a lemma. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 01:36, 23 December 2024 (UTC)
*::I think I linked it once in ], years ago, and someone objected. I didn't follow up to see whether the objecting editor is one of the handful who think that ''should'' is a more polite and/or IAR-compliant way to say ''must'', but as that's a fairly uncommon POV among editors, it probably wasn't. ] (]) 05:41, 23 December 2024 (UTC)
*:::The linked document pushes very hard on ''should'', "here may exist valid reasons in particular circumstances to ignore a particular item, but the full implications must be understood and carefully weighed" is not a low bar. It sounds much like must except when IAR. ] (]) 09:39, 23 December 2024 (UTC)
*1: no 2: I don’t see anything wrong with the chart if you just use it as a rule of thumb; 3: I don’t know why this needed to be discussed here, rather than a Q&A desk. ] (]) 20:50, 28 December 2024 (UTC)
*'''No''', Misplaced Pages ]. It's just a general rule of thumb, and should be adjusted or ignored if the situation/article warrants it. <span class="nowrap">—] (] | ])</span> 04:38, 3 January 2025 (UTC)
Hi, most of my ideas get shot down here, but hey, you throw enough and something's gotta stick! How about a stub namespace? Or at least some way to store them differently, as we do redirects. Since we're so proud of our "random article" button — and roughly half the time it turns up a measly scrap of an article — it seems like we should want to make it appear that we're as credible as possible. I stub-sort a bit, so I've seen quite a few, and while some stubs blossom, many end up at AFD, but hardly any are yet ready to be included in an encyclopaedia. Think of it like a testing/holding place for that which could be. Any takers? — <font face="Verdana">''']''' <small>· ] · 02:18, Thursday, 12 April 2007</small></font>
:No. Fundamentally, your suggestion assumes a distinction between stubs and full articles. That distinction is arbitrary and left to the judgment of individual editors. Thus, there are one-line articles not tagged as stubs, and four-paragraph articles that are stubs. All it takes to fix a stub is add a little content and referencing, then remove the template. In this respect, a stub template is like a {{tl|cleanup}} tag. As for the "Random Article" concern, some people use that feature with the specific goal of finding problem articles to fix or to nominate for deletion. ] 15:42, 12 April 2007 (UTC)
::Indeed: there is no "distinction between stubs and full articles", stubs are '''a form of article'''. Incomplete ones, certainly, but still articles.] 15:55, 12 April 2007 (UTC)
== Guideline against use of AI images in BLPs and medical articles? ==
== Notification when user talk page has been blanked ==
I have recently seen AI-generated images be added to illustrate both BLPs (e.g. ], now removed) and medical articles (e.g. ]). While we don't have any clear-cut policy or guideline about these yet, they appear to be problematic. Illustrating a living person with an AI-generated image might misinform as to how that person actually looks like, while using AI in medical diagrams can lead to anatomical inaccuracies (such as the lung structure in the second image, where the pleura becomes a bronnchiole twisting over the primary bronchi), or even medical misinformation. While a guideline against AI-generated images in general might be more debatable, do we at least have a consensus for a guideline against these two specific use cases?
Accepting that users have the (general) right to clear their talk page of warnings, I'm wondering if there should be some kind of template or bug (like the cute little admin broom) that must be displayed to indicate to others that user warnings have been removed from a particular talk page. Seems to make sense rather than having to check the history to see if there is an on-going problem... ] 03:44, 12 April 2007 (UTC)
::This is a problem with the bots' automated warnings. A disruptive user will blank off their warnings, then a bot will leave an automated warning on the clean page. This means that unless a manual revert-then-edit is done, at least one of the warnings will be lost. Any template indicating deleted warnings is just as apt to be blanked off by a disruptive editor anyway. ] 05:35, 12 April 2007 (UTC)
::*Note that in general people are ''allowed'' to remove warnings from their talk page. So I'd suggest you check the history tab, which should show the issues in the edit summaries. ] 12:33, 12 April 2007 (UTC)
::**I remember several months ago however that an anon account replaced the images on a Montenegro-related article with images of female anuses. I considered this to be such an obvious bad faith action (not a newbie test) that I went straight to {{tl|test4im}}. I blocked when he ''replaced the warning'' with a standard {{tl|test}}... as if a new IP entitles you to vandalize four times without getting blocked. I blocked that guy immediately. (Good thing that this is no longer an admin...) ] ] 14:37, 12 April 2007 (UTC)
It just seems to make sense to have some kind of easy indication that warnings ''have'' been issued and since blanked, rather than having to rifle through the history. I dunno. ] 16:21, 12 April 2007 (UTC)
:Speaking for myself, possibly for others as well, I usually did not only review the user's talkpage, but also the contribution history. This usually reveals a lot more than the history of warnings. ] ] 06:06, 13 April 2007 (UTC)
When leaving a warning, you should put a description in the edit summary. That can't be blanked and should be visible at a glance unless they have an ''extremely'' busy talk page. ] (]/]) 12:16, 13 April 2007 (UTC)
To clarify, I am not including potentially relevant AI-generated images that only ''happen'' to include a living person (such as in ]), but exclusively those used to illustrate a living person in a ] context. ] (] · ]) 12:11, 30 December 2024 (UTC)
== Is there a policy/guideline regarding punctuation style? Apostrophes and quotation marks, specifically? ==
:What about any biographies, including dead people. The lead image shouldn't be AI generated for any biography. - ] (]) 12:17, 30 December 2024 (UTC)
This isn't of major improtance but I thought to the ] article was odd, mainly because I hadn't seen this type of edit before. The apostrophes and quotation marks have been swapped from the conventional ones to a different style. I don't even have that type of punctuation on my keyboard, just ' and ". This is such a small detail I never expected Misplaced Pages to have a policy on it, but if this editor went to the effort of changing the quotation marks, then I wondered if there is a guideline? <font color="blue">Pufnstuf</font> 04:08, 12 April 2007 (UTC)
::Same with animals, organisms etc. - ] (]) 12:20, 30 December 2024 (UTC)
:The ] has a lot of stylistic guidelines, but I don't think it has anything on what particular type of quotation marks to use. Those look like Unicode ones, you can generate them with a regular word processor and paste them in. (I don't know of any keyboards that specifically have them). Usually we just use the standard "" or <nowiki>''</nowiki>, but it's probably not a tremendously big deal. ] <small><sup>]</sup></small> 04:11, 12 April 2007 (UTC)
:I personally am '''strongly against''' using AI in biographies and medical articles - as you highlighted above, AI is absolutely not reliable in generating accurate imagery and may contribute to medical or general misinformation. I would 100% support a proposal banning AI imagery from these kinds of articles - and a recommendation to not use such imagery other than in specific scenarios. ]] 12:28, 30 December 2024 (UTC)
::In particular, the MOS ] uses the Unicode directional quotes, but does not say that they are required. It does say that grave and acute accents should not be used for single quotes. ] 01:21, 13 April 2007 (UTC)
:I'd prefer a guideline prohibiting the use of AI images full stop. There are too many potential issues with accuracy, honesty, copyright, etc. Has this already been proposed or discussed somewhere? – ] <small>(])</small> 12:38, 30 December 2024 (UTC)
::There hasn't been a full discussion yet, and we have a list of uses at ], but it could be good to deal with clear-cut cases like this (which are already a problem) first, as the wider discussion is less certain to reach the same level of consensus. ] (] · ]) 12:44, 30 December 2024 (UTC)
:Discussions are going on at ] and somewhat at ]. I recommend workshopping an RfC question (or questions) then starting an RfC. ] (]) 13:03, 30 December 2024 (UTC)
::Oh, didn't catch the previous discussions! I'll take a look at them, thanks! ] (] · ]) 14:45, 30 December 2024 (UTC)
:There is one very specific exception I would put to a very sensible blanket prohibition on using AI images to illustrate people, especially BLPs. That is where the person themselves is known to use that image, which I have encountered in ]. ] (]) 15:00, 30 December 2024 (UTC)
::While the Ekpa portrait is just an upscale (and I'm not sure what positive value that has for us over its source; upscaling does not add accuracy, nor is it an artistic interpretation meant to reveal something about the source), this would be hard to translate to the general case. Many AI portraits would have copyright concerns, not just from the individual (who may have announced some appropriate release for it), but due to the fact that AI portraits can lean heavily on uncredited individual sources. --] (]) 16:04, 30 December 2024 (UTC)
:::For the purposes of discussing whether to allow AI images at all, we should always assume that, for the purposes of (potential) policies and guidelines, there exist AI images we can legally use to illustrate every topic. We cannot use those that are not legal (including, but not limited to, copyright violations) so they are irrelevant. An image generator trained exclusively on public domain and cc0 images (and any other licenses that explicitly allow derivative works without requiring attribution) would not be subject to any copyright restrictions (other than possibly by the prompter and/or generator's license terms, which are both easy to determine). Similarly we should not base policy on the current state of the technology, but assume that the quality of its output will improve to the point it is equal to that of a skilled human artist. ] (]) 17:45, 30 December 2024 (UTC)
::::The issue is, either there are public domain/CC0 images of the person (in which case they can be used directly) or there aren't, in which case the AI is making up how a person looks. ] (] · ]) 20:00, 30 December 2024 (UTC)
::::We tend to use art representations either where no photographs are available (in which case, AI will also not have access to photographs) or where what we are showing is an artist's insight on how this person is perceived, which is not something that AI can give us. In any case, we don't have to build policy now around some theoretical AI in the future; we can deal with the current reality, and policy can be adjusted if things change in the future. And even that theoretical AI does make it more difficult to detect copyvio -- ] (]) 20:54, 30 December 2024 (UTC)
:::I wouldn't call it an upscale given whatever was done appears to have removed detail, but we use that image as it was specifically it is the edited image which was sent to VRT. ] (]) 10:15, 31 December 2024 (UTC)
:Is there any clarification on using purely AI-generated images vs. using AI to edit or alter images? AI tools , such as to identify objects and remove them, or generate missing content. The generative expand feature would appear to be unreliable (and it is), but I use it to fill in gaps of cloudless sky produced from stitching together photos for a panorama (I don't use it if there are clouds, or for starry skies, as it produces non-existent stars or unrealistic clouds). ] (]) 18:18, 30 December 2024 (UTC)
::Yes, my proposal is only about AI-generated images, not AI-altered ones. That could in fact be a useful distinction to make if we want to workshop a RfC on the matter. ] (] · ]) 20:04, 30 December 2024 (UTC)
:I'm not sure if we need a clear cut policy or guideline against them... I think we treat them the same way as we would treat an editor's kitchen table sketch of the same figure. ] (]) 18:40, 30 December 2024 (UTC)
:For those wanting to ban AI images full stop, well, you are too late. Most professional image editing software, including the software in one's smartphone as well as desktop, uses AI somewhere. Noise reduction software uses AI to figure out what might be noise and what might be texture. Sharpening software uses AI to figure out what should be smooth and what might have a sharp detail it can invent. For example, a bird photo not sharp enough to capture feather detail will have feather texture imagined onto it. Same for hair. Or grass. Any image that has been cleaned up to remove litter or dust or spots will have the cleaned area AI generated based on its surroundings. The sky might be extended with AI. These examples are a bit different from a 100% imagined image created from a prompt. But probably not in a way that is useful as a rule.
:I think we should treat AI generated images the same as any user-generated image. It might be a great diagram or it might be terrible. Remove it from the article if the latter, not because someone used AI. If the image claims to photographically represent something, we may judge whether the creator has manipulated the image too much to be acceptable. For example, using AI to remove a person in the background of an image taken of the BLP subject might be perfectly fine. People did that with traditional Photoshop/Lightroom techniques for years. Using AI to generate what claims to be a photo of a notable person is on dodgy ground wrt copyright. -- ]°] 19:12, 30 December 2024 (UTC)
::I'm talking about the case of using AI to generate a depiction of a living person, not using AI to alter details in the background. That is why I only talk about AI-generated images, not AI-altered images. ] (] · ]) 20:03, 30 December 2024 (UTC)
:Regarding some sort of brightline ban on the use of any such image in anything article medical related: absolutely not. For example, if someone wanted to use AI tools as opposed to other tools to make an image such as ] (as used in the "medical" article ]) I don't see a problem, so long as it is accurate. Accurate models and illustrations are useful and that someone used AI assistance as opposed to a chisel and a rock is of no concern. — ] <sup>]</sup> 19:26, 30 December 2024 (UTC)
:I believe that the appropriateness of AI images depends on how its used by the user. In BLP and medical articles, it is inappropriate for the images, but it is inappropriate to ban it completely across thw site. By the same logic, if you want full ban of AI, you are banning fire just because people can get burned, without considering cooking. ] (]) 13:33, 31 December 2024 (UTC)
] <sup>]</sup> 00:13, 31 December 2024 (UTC)]]
:I agree that AI-generated images should not be used in most cases. They essentially serve as misinformation. I also don't think that they're really comparable to drawings or sketches because AI-generation uses a level of photorealism that can easily trick the untrained eye into thinking it is real. ] (]) 20:46, 30 December 2024 (UTC)
::AI doesn't need to be photorealistic though. I see two potential issues with AI. The first is images that might deceive the viewer into thinking they are photos, when they are not. The second is potential copyright issues. Outside of the copyright issues I don't see any unique concerns for an AI-generated image (that doesn't appear photorealistic). Any accuracy issues can be handled the same way a user who manually drew an image could be handled. ] (]) 21:46, 30 December 2024 (UTC)
{{multiple image
| image1 = Pope Francis in puffy winter jacket.jpg
| image2 = Illustration of Brigette Lundy Paine by Sandra Mu.png
| footer = ] and ]
| total_width = 300
}}
::AI-generated depictions of BLP subjects are often more "illustrative" than drawings/sketches of BLP subjects made by 'regular' editors like you and me. For example, compare the AI-generated image of Pope Francis and the user-created cartoon of Brigette Lundy-Paine. Neither image belongs on their respective bios, of course, but the AI-generated image is no more "misinformation" than the drawing. ] (]) 00:05, 31 December 2024 (UTC)
:::I would argue the opposite: neither are made up, but the first one, because of its realism, might mislead readers into thinking that it is an actual photograph, while the second one is clearly a drawing. Which makes the first one less illustrative, as it carries potential for misinformation, despite being technically more detailed. ] (] · ]) 00:31, 31 December 2024 (UTC)
::::AI-generated images should always say "AI-generated image of " in the image caption. No misleading readers that way. ] (]) 00:36, 31 December 2024 (UTC)
:::::Yes, and they don't always do it, and we don't have a guideline about this either. The issue is, many people have many different proposals on how to deal with AI content, meaning we always end up with "no consensus" and no guidelines on use at all, even if most people are against it. ] (] · ]) 00:40, 31 December 2024 (UTC)
::::::{{tq|always end up with "no consensus" and no guidelines on use at all, even if most people are against it}} Agreed. Even a simple proposal to have image captions note whether an image is AI-generated will have editors wikilawyer over the definition of 'AI-generated.' I take back my recommendation of starting an RfC; we can already predict how that RfC will end. ] (]) 02:28, 31 December 2024 (UTC)
:Of interest perhaps is ] on the use of drawn cartoon images in BLPs. ] (]) 22:38, 30 December 2024 (UTC)
:We should absolutely not be including any AI images in anything that is meant to convey facts (with the obvious exception of an AI image illustrating the concept of an AI image). I also don't think we should be encouraging AI-altered images -- the line between "regular" photo enhancement and what we'd call "AI alteration" is blurry, but we shouldn't want AI edits for the same reason we wouldn't want fake Photoshop composites.
:That said, I would assume good faith here: some of these images are probably being sourced from Commons, and Commons is dealing with a lot of undisclosed AI images. ] (]) 23:31, 30 December 2024 (UTC)
::]
::Why wouldn't we want "fake Photoshop composites"? A ] can be very useful. I'd be sad if we banned ]. ] (]) 06:40, 31 December 2024 (UTC)
:::Sorry, should have been more clear -- composites that present themselves as the real thing, basically what people would use deepfakes for now. ] (]) 20:20, 31 December 2024 (UTC)
:I don't think any guideline, let alone policy, would be beneficial and indeed on balance is more likely to be harmful. There are always only two questions that matter when determining whether we should use an image, and both are completely independent of whether the image is AI-generated or not:
:#Can we use this image in this article? This depends on matters like copyright, fair use, whether the image depicts content that is legal for an organisation based in the United States to host, etc. Obviously if the answer is "no", then everything else is irrelevant, but as the law and WMF, Commons and en.wp policies stand today there exist some images in both categories we can use, and some images in both categories we cannot use.
:#Does using this image in this article improve the article? This is relative to other options, one of which is always not using any image, but in many cases also involves considering alternative images that we can use. In the case of depictions of specific, non-hypothetical people or objects one criteria we use to judge whether the image improves the article is whether it is an accurate representation of the subject. If it is not an accurate representation then it doesn't improve the article and thus should not be used, regardless of why it is inaccurate. If it is an accurate representation, then its use in the article will not be misrepresentative or misleading, regardless of whether it is or is not AI generated. It may or may not be the best option available, but if it is then it should be used regardless of whether it is or is not AI generated.
:The potential harm I mentioned above is twofold, firstly Misplaced Pages is, by definition, harmed when an images exists we could use that would improve an article but we do not use it in that article. A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.
:Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. ] (]) 00:52, 31 December 2024 (UTC)
::I agree with almost the entirety of your post with a caveat on whether something "is an accurate representation". We can tell whether non-photorealistic images are accurate by assessing whether the image accurately conveys ''the idea'' of what it is depicting. Photos do more than convey an idea, they convey the actual look of something. With AI generated images that are photorealistic it is difficult to assess whether they accurately convey the look of something (the shading might be illogical in subtle ways, there could be an extra finger that goes unnoticed, a mole gets erased), but readers might be deceived by the photo-like presentation into thinking they are looking at an actual photographic depiction of the subject which could differ significantly from the actual subject in ways that go unnoticed. ] (]) 04:34, 31 December 2024 (UTC)
::{{tq|A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article.}} That's why I'm suggesting a guideline, not a policy. Guidelines are by design more flexible, and ] still does (and should) apply in edge cases.{{pb}}{{tq|The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.}} In that case, there is a licensing problem. AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that ''might'' have been AI-generated.{{pb}}{{tq|Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware.}} In that case, it's mostly because the ambiguity in wording: AI-edited images are very common, and are sometimes called "AI-generated", but here we should focus on actual prompt outputs, of the style "I asked a model to generate me an image of a BLP". ] (] · ]) 11:13, 31 December 2024 (UTC)
:::Simply not having a completely unnecessary policy or guideline is infinitely better than relying on IAR - especially as this would have to be ignored ''every'' time it is relevant. When the AI image is not the best option (which obviously includes all the times its unsuitable or inaccurate) existing policies, guidelines, practice and frankly common sense mean it won't be used. This means the only time the guideline would be relevant is when an AI image ''is'' the best option and as we obviously should be using the best option in all cases we would need to ignore the guideline against using AI images.
:::{{tpq|AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.}} The key words here are "supposed to be" and "shouldn't", editors absolutely ''will'' speculate that images are AI-generated and that the Commons labelling is incorrect. We are supposed to assume good faith, but this very discussion shows that when it comes to AI some editors simply do not do that.
:::Regarding your final point, that might be what you are meaning but it is not what all other commenters mean when they want to exclude all AI images. ] (]) 11:43, 31 December 2024 (UTC)
::::For your first point, the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image), but the model likely doesn't have any available image either and most likely just made it up. As my proposal is essentially limited to that (I don't include AI-edited images, only those that are purely generated by a model), I don't think there will be many cases where IAR would be needed.{{pb}}Regarding your two other points, you are entirely correct, and while I am hoping for nuance on the AI issue, it is clear that some editors might not do that. For the record, I strongly disagree with a blanket ban of "AI images" (which includes both blatant "prompt in model" creations and a wide range of more subtle AI retouching tools) or anything like that. ] (] · ]) 11:49, 31 December 2024 (UTC)
:::::{{tpq|the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image)}}. There are only two possible scenarios regarding verifiability:
:::::#The image is an accurate representation and we can verify that (e.g. by reference to non-free photos).
:::::#*Verifiability is no barrier to using the image, whether it is AI generated or not.
:::::#*If it is the best image available, and editors agree using it is better than not having an image, then it should be used whether it is AI generated or not.
:::::#The image is either ''not'' an accurate representation, or we cannot verify whether it is or is not an accurate representation
:::::#*The only reasons we should ever use the image are:
:::::#**It has been the subject of notable commentary and we are presenting it in that context.
:::::#**The subject verifiably uses it as a representation of themselves (e.g. as an avatar or logo)
:::::#:This is already policy, whether the image is AI generated or not is completely irrelevant.
:::::You will note that in no circumstance is it relevant whether the image is AI generated or not. ] (]) 13:27, 31 December 2024 (UTC)
::::::In your first scenario, there is the issue of an accurate AI-generated image misleading people into thinking it is an actual photograph of the person, especially as they are most often photorealistic. Even besides that, a mostly accurate representation can still introduce spurious details, and this can mislead readers as they do not know to what level it is actually accurate. This scenario doesn't really happen with drawings (which are clearly not photographs), and is very much a consequence of AI-generated photorealistic pictures being a thing.{{pb}}In the second scenario, if we cannot verify that it is not an accurate representation, it can be hard to remove the image with policy-based reasons, which is why a guideline will again be helpful. Having a single guideline against fully AI-generated images takes care of all of these scenarios, instead of having to make new specific guidelines for each case that emerges because of them. ] (] · ]) 13:52, 31 December 2024 (UTC)
:::::::If the image is misleading or unverifiable it should not be used, regardless of why it is misleading or unverifiable. This is existing policy and we don't need anything specifically regarding AI to apply it - we just need consensus that the image ''is'' misleading or unverifiable. Whether it is or is not AI generated is completely irrelevant. ] (]) 15:04, 31 December 2024 (UTC)
::::{{tpq|AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.}}
::::I mean... yes, we should? At the very least Commons should go hunting for mislabeled images -- that's the whole point of license review. The thing is that things are absolutely swamped over there and there are hundreds of thousands of images waiting for review of some kind. ] (]) 20:35, 31 December 2024 (UTC)
:::::Yes, but that's a Commons thing. A guideline on English Misplaced Pages shouldn't decide of what is to be done on Commons. ] (] · ]) 20:37, 31 December 2024 (UTC)
::::::I just mean that given the reality of the backlogs, there are going to be mislabeled images, and there are almost certainly going to be more of them over time. That's just how it is. We don't have control over that, but we do have control over what images go into articles, and if someone has legitimate concerns about an image being AI-generated, then they should be raising those. ] (]) 20:45, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated images on Misplaced Pages'''. As others have highlighted above, the is not just a slippery slope but an outright downward spiral. We don't use AI-generated text and we shouldn't use AI-generated images: these aren't reliable and they're also ] scraped from who knows what and where. '''Use only reliable material from reliable sources'''. As for the argument of 'software now has AI features', we all know that there's a huge difference between someone using a smoothing feature and someone generating an image from a prompt. ] (]) 03:12, 31 December 2024 (UTC)
*:'''Reply''', the section of ] concerning images is ] which states "Original images created by a Wikimedian are not considered original research, ''so long as they do not illustrate or introduce unpublished ideas or arguments''". Using AI to generate an image only violates ] if you are using it to illustrate unpublished ideas, which can be assessed just by looking at the image itself. COPYVIO, however, cannot be assessed from looking at just the image alone, which AI could be violating. However, some images may be too simple to be copyrightable, for example AI-generated images of chemicals or mathematical structures potentially. ] (]) 04:34, 31 December 2024 (UTC)
*::Prompt generated images are unquestionably violation of ] and ]: Type in your description and you get an image scraping who knows what and from who knows where, often Misplaced Pages. Misplaced Pages isn't an ]. Get real. ] (]) 23:35, 1 January 2025 (UTC)
*:::"Unquestionably"? Let me question that, @]. <code>;-)</code>
*:::If an editor were to use an AI-based image-generating service and the prompt is something like this:
*:::"I want a stacked bar chart that shows the number of games won and lost by ] each year. Use the team colors, which are red #DC052D, blue #0066B2, and black #000000. The data is:
*:::* 2014–15: played 34 games, won 25, tied 4, lost 5
*:::* 2015–16: played 34 games, won 28, tied 4, lost 2
*:::* 2016–17: played 34 games, won 25, tied 7, lost 2
*:::* 2017–18: played 34 games, won 27, tied 3, lost 4
*:::* 2018–19: played 34 games, won 24, tied 6, lost 4
*:::* 2019–20: played 34 games, won 26, tied 4, lost 4
*:::* 2020–21: played 34 games, won 24, tied 6, lost 4
*:::* 2021–22: played 34 games, won 24, tied 5, lost 5
*:::* 2022–23: played 34 games, won 21, tied 8, lost 5
*:::* 2023–24: played 34 games, won 23, tied 3, lost 8"
*:::I would expect it to produce something that is not a violation of either OR in general or OR's SYNTH section specifically. What would you expect, and why do you think it would be okay for me to put that data into a spreadsheet and upload a screenshot of the resulting bar chart, but you don't think it would be okay for me to put that same data into a image generator, get the same thing, and upload that?
*:::We must not mistake the tools for the output. Hand-crafted bad output is bad. AI-generated good output is good. ] (]) 01:58, 2 January 2025 (UTC)
*::::Assuming you'd even get what you requested the model without fiddling with the prompt for a while, these sort of 'but we can use it for graphs and charts' devil's advocate scenarios aren't helpful. We're discussing generating images of people, places, and objects here and in those cases, yes, this would unquestionably be a form of ] & ]. As for the charts and graphs, there are any number of ways to produce these. ] (]) 03:07, 2 January 2025 (UTC)
*:::::{{tpq|We're discussing generating images of people, places, and objects here}} The proposal contains no such limitation. {{tpq| and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH.}} Do you have a citation for that? Other people have explained better than I can how that it is not necessarily true, and certainly not unquestionable. ] (]) 03:14, 2 January 2025 (UTC)
*::::::As you're well aware, these images are produced by scraping and synthesized material from who knows what and where: it's ultimately pure ] to produce these fake images and they're a straightforward product of synthesis of multiple sources (]) - worse yet, these sources are unknown because training data is by no means transparent. Personally, I'm strongly for a total ban on generative AI on the site exterior to articles on the topic of generative AI. Not only do I find this incredible unethical, I believe it is intensely detrimental to Misplaced Pages, which is an already a flailing and shrinking project. ] (]) 03:23, 2 January 2025 (UTC)
*:::::::So you think the lead image at ] is a SYNTH violation? Its (human) creator explicitly says "This is not done from one specific photo. As I usually do when I draw portraits of people that I can't see in person, I look at a lot of photos of them and then create my own rendition" in the image description, which sounds like the product of synthesis of multiple sources" to me, and "these sources are unknown because" the the images the artist looked at are not disclosed.
*:::::::A lot of my concern about blanket statements is the principle that what's ] is sauce for the gander, too. If it's okay for a human to do something by hand, then it should be okay for a human using a semi-automated tool to do it, too.
*:::::::<small>(Just in case you hadn't heard, the rumors that the editor base is shrinking have been false for over a decade now. Compared to when you created your account in mid-2005, we have about twice as many high-volume editors.)</small> ] (]) 06:47, 2 January 2025 (UTC)
*:::::::Review ] and your attempts at downplaying a prompt-generated image as "semi-automated" shows the root of the problem: if you can't detect the difference between a human sketching from a reference and a machine scraping who-knows-what on the internet, you shouldn't be involved in this discussion. As for editor retention, this remains a serious problem on the site: while the site continues to grow (and becomes core fodder for AI-scraping) and becomes increasingly visible, editorial retention continues to drop. ] (]) 09:33, 2 January 2025 (UTC)
*::::::::Please scroll down below SYNTH to the next section titled "What is not original research" which begins with ], our policies on how images relate to OR. OR (including SYNTH) only applies to images with regards to if they illustrate "unpublished ideas or arguments". It does not matter, for instance, if you synthesize an original ''depiction'' of something, so long as the ''idea'' of that thing is not original. ] (]) 09:55, 2 January 2025 (UTC)
*:::::::::Yes, which explicitly states:
*::::::::::It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.
*:::::::::Using a machine to generate a fake image of someone is far beyond "manipulation" and it is certainly "false". Clearly we need explicit policies on AI-generated images of people or we wouldn't be having this discussion, but this as it stands clarly also falls under ]: there is zero question that this is a result of "synthesis of published material", even if the AI won't list what it used. Ultimately it's just a synthesis of a bunch of published composite images of who-knows-what (or who-knows-who?) the AI has scraped together to produce a fake image of a person. ] (]) 10:07, 2 January 2025 (UTC)
*:The latter images you describe should be SVG regardless. If there are models that can generate that, that seems totally fine since it can be semantically altered by hand. Any generation with photographic or "painterly" characteristics (e.g. generating something in the style of a painting or any other convention of visual art that communicates aesthetic particulars and not merely abstract visual particulars) seems totally unacceptable. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:00, 31 December 2024 (UTC)
*:]
*:@], here's an image I created. It illustrates the concept of 1% in an article. I made this myself, by typing 100 emojis and taking a screenshot. Do you really mean to say that if I'd done this with an image-generating AI tool, using a prompt like "Give me 100 dots in a 10 by 10 grid. Make 99 a dark color and 1, randomly placed, look like a baseball" that it would be hopelessly tainted, because AI is always bad? Or does your strongly worded statement mean something more moderate?
*:I'd worry about photos of people (including dead people). I'd worry about photos of specific or unique objects that have to be accurate or they're worse than worthless (e.g., artwork, landmarks, maps). But I'm not worried about simple graphs and charts like this one, and I'm not worried about ordinary, everyday objects. If you want to use AI to generate a photorealistic image of a cookie, or a spoon, and the output you get ], I'm not actually going to worry about it. ] (]) 06:57, 31 December 2024 (UTC)
*::As you know, Misplaced Pages has the unique factor of being entirely volunteer-ran. Misplaced Pages has fewer and fewer editors and, long-term, we're seeing plummeting birth rates in areas where most Misplaced Pages editors do exist. I wouldn't expect a wave of new ones aimed at keeping the site free of bullshit in the near future.
*::In addition, the Wikimedia Foundation's hair-brained continued effort to turn the site into its political cash machine is no doubt also not helping, harming the site's public perception and leading to fewer new editors.
*::Over the course of decades (I've been here for around 20 years), it seems clear that the site will be negatively impacted by all this, especially in the face of generative AI.
*::As a long-time editor who has frequently stumbled upon intense ] content, fended off armies of outside actors looking to shape the site into their ideological image (and sent me more than a few death threats), and who has identified large amount of politically-motivated nonsense explicitly designed to fool non-experts in areas I know intimately well (such as folklore and historical linguistics topics), I think it need be said that the use of generative AI for content is especially dangerous because of its capabilities of fooling Misplaced Pages readers and Misplaced Pages editors alike.
*::Misplaced Pages is written by people for people. We need to draw a line in the sand to keep from being flooded by increasingly accessible hoax-machines.
*::A blanket ban on generative AI resolves this issue or at least hands us another tool with which to attempt to fight back. We don't need what few editors we have here wasting what little time they can give the project checking over an ocean of AI-generated slop: '''we need more material from reliable sources and better tools to fend off bad actors usable by our shrinking editor base (anyone at the Wikimedia Foundation listening?), not more waves of generative AI garbage'''. ] (]) 07:40, 31 December 2024 (UTC)
*:::A blanket ban doesn't actually resolve most of the issues though, and introduces new ones. Bad usages of AI can already be dealt with by existing policy, and malicious users will ignore a blanket ban anyways. Meanwhile, a blanket ban would harm many legitimate usages for AI. For instance, the majority of professional translators (at least Japanese to English) incorporate AI (or similar tools) into their workflow to speed up translations. Just imagine a professional translator who uses AI to help generate rough drafts of foreign language Misplaced Pages articles, before reviewing and correcting them, and another editor learning of this and mass reverting them for breaking the blanket ban, and ultimately causing them to leave. Many authors (particularly with carpal tunnel) use AI now to control their voice-to-text (you can train the AI on how you want character names spelled, the formatting of dialogue and other text, etc.). A wikipedia editor could train an AI to convert their voice into Misplaced Pages-formatted text. AI is subtly incorporated now into spell-checkers, grammar-checkers, photo editors, etc., in ways many people are not aware of. A blanket AI ban has the potential to cause many issues for a lot of people, without actually being that affective at dealing with malicious users. ] (]) 08:26, 31 December 2024 (UTC)
*::::I think this is the least convincing one I've seen here yet: It contains the ol' 'there are AI features in programs now' while also attempting to invoke accessibility and a little bit of 'we must have machines to translate!'.
*::::As a translator myself, I can only say: ''Oh please''. Generative AI is notoriously terrible at translating and that's not likely to change. And I mean ''ever'' beyond a very, very basic level. Due to the complexities of communication and little matters like nuance, all machine translated material must be thoroughly checked and modified by, yes, ''human'' translators, who often encounter it spitting out complete bullshit scraped from who-knows-where (often Misplaced Pages itself).
*::::I get that this topic attracts a lot of 'but what if generative AI is better than humans?' from the utopian tech crowd but the ''reality'' is that anyone who needs a machine to invent text and visuals for whatever reason simply shouldn't be using it on Misplaced Pages.
*::::Either you, a human being, can contribute to the project or ''you can't''. Slapping a bunch of machine-generated (generative AI) visuals and text (much of it ultimately coming from Misplaced Pages in the first place!) isn't some kind of human substitute, it's just machine-regurgitated slop and is not helping the project.
*::::If people can't be confident that Misplaced Pages is ''made by humans, for humans'' the project is finally on its way out.] (]) 09:55, 31 December 2024 (UTC)
*:::::I don't know how up to date you are on the current state of translation, but:
*::::::''''
*::::::''Over three thousand full-time professional translators from around the world responded to the surveys, which were broken into a survey for CAT tool users and one for those who do not use any CAT tool at all.''
*::::::''88% of respondents use at least one CAT tool for at least some of their translation tasks.''
*::::::''Of those using CAT tools, 83% use a CAT tool for most or all of their translation work.''
*:::::Mind you, traditionally CAT tools didn't use AI, but many do now, which only adds to potential sources of confusion in a blanket ban of AI. ] (]) 17:26, 31 December 2024 (UTC)
*::::::You're barking up the tree with the pro-generative AI propaganda in response to me. I think we're all quite aware that generative AI tool integration is now common and that there's also a big effort to replace human translators — and anything that can be "written" with machines-generated text. I'm also keenly aware that generative AI is ''absolutely horrible'' at translation and ''all of it must be thoroughly checked by humans'', as you would be if you were a translator yourself. ] (]) 22:20, 31 December 2024 (UTC)
*:::::"''all machine translated material must be thoroughly checked and modified by, yes, ''human'' translators''"
*:::::You are just agreeing with me here.
*::::::'''' -American Translation Society
*:::::There are translators (particularly with non-creative works) who are using these tools to shift more towards reviewing. It should be up to them to decide what they think is the most efficient method for them. ] (]) 06:48, 1 January 2025 (UTC)
*::::::And any translator who wants to use generative AI to ''attempt'' to translate can do so off the site. We're not here to check it for them. I strongly support a total ban on any generative AI used on the site exterior to articles on generative AI. ] (]) 11:09, 1 January 2025 (UTC)
*:::::::I wonder what you mean by "on the site". The question here is "Is it okay for an editor to go to a completely different website, generate an image all by themselves, upload it to Commons, and put it in a Misplaced Pages article?" The question here is ''not'' "Shall we put AI-generating buttons on Misplaced Pages's own website?" ] (]) 02:27, 2 January 2025 (UTC)
*:::::::I'm talking about users slapping machine-translated and/or machine-generated nonsense all over the site, only for us to have to go behind and not only check it but correct it. It takes users minutes to do this and it's already happening. It's the same for images. There are very few of us who volunteer here and our numbers are growing fewer. We need to be spending our time improving the site rather than opening the gate as wide as possible for a flood of AI-generated/rendered garbage. The site has enough problems that compound every day rather than having to fend off users armed with hoax machines at every corner. ] (]) 03:20, 2 January 2025 (UTC)
*::::::::Sure, we're all opposed to "nonsense", but my question is: What about when the machine happens to generate something that is ''not'' "nonsense"?
*::::::::I have some worries about AI content. I worry, for example, that they'll corrupt our sources. I worry that ] will get dramatically longer, and also that even more undetected, unconfessed, unretracted papers will get published and believed to be true and trustworthy. I worry that academia will go back to a model in which personal connections are more important, because you really can't trust what's published. I worry that scientific journals will start refusing to publish research unless it comes from someone employed by a trusted institution, that is willing to put its reputation on the line by saying they have directly verified that the work described in the paper was actually performed to their standards, thus scuttling the citizen science movement and excluding people whose institutions are upset with them for other reasons (Oh, you thought you'd take a job elsewhere? Well, we refuse to certify the work you did for the last three years...).
*::::::::But I'm not worried about a Misplaced Pages editor saying "Hey AI, give me a diagram of swingset" or "Make a chart for me out of the data I'm going to give you". In fact, if someone wants to pull the numbers out of ], feed it to an AI, and replace the template's contents with an AI-generated image (until they finally fix the Graphs extension), I'd consider that helpful. ] (]) 07:09, 2 January 2025 (UTC)
*::::::Translators are not using ''generative'' AI for translation, the applicability of LLMs to regular translation is still in its infancy and regardless will not be implementing any ''generative'' faculties to its output since that is the exact opposite of what translation is supposed to do. ] (]) 02:57, 2 January 2025 (UTC)
*:::::::{{tpq|Translators are not using generative AI for translation}} this entirely depends on what you mean by "generative". There are at least three contradictory understandings of the term in this one thread alone. ] (]) 03:06, 2 January 2025 (UTC)
*:::::::Please, you can just go through the entire process with a simple prompt command now. The results are typically shit but you can generate a ton of it quickly, which is perfect for flooding a site like this one — especially without a strong policy against it. I've found myself cleaning up tons of AI-generated crap (and, yes, rendered) stuff here and elsewhere, and now I'm even seeing AI-generated responses to my own comments. It's beyond ridiculous. ] (]) 03:20, 2 January 2025 (UTC)
* '''Ban AI-generated from all articles, AI anything from BLP and medical articles''' is the position that seems it would permit all instances where there are plausible defenses that AI use does not fabricate or destroy facts intended to be communicated in the context of the article. That scrutiny is stricter with BLP and medical articles in general, and the restriction should be stricter to match. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 06:53, 31 December 2024 (UTC)
*:@], please see my comment immediately above. (We had an edit conflict.) Do you really mean "anything" and everything? Even a simple chart? ] (]) 07:00, 31 December 2024 (UTC)
*::I think my previous comment is operative: almost anything we can see AI used programmatically to generate should be SVG, not raster—even if it means we are embedding raster images in SVG to generate examples like the above. I do not know if there are models that can generate SVG, but if there are I happily state I have no problem with that. I think I'm at risk of seeming downright paranoid—but understanding how errors can propagate and go unnoticed in practice, if we're to trust a black box, we need to at least be able to check what the black box has done on a direct structural level. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:02, 31 December 2024 (UTC)
*:::A quick web search indicates that there are generative AI programs that create SVG files. ] (]) 07:16, 31 December 2024 (UTC)
*::::Makes perfect sense that there would be. Again, maybe I come off like a paranoid lunatic, but I really need either the ability to check what the thing is doing, or the ability to check and correct exactly what a black box has done. (In my estimation, if you want to know what procedures person has done, theoretically you can ask them to get a fairly satisfactory result, and the pre-AI algorithms used in image manipulation are canonical and more or less transparent. Acknowledging human error etc., with AI there is not even the theoretical promise that one can be given a truthful account of how it decided to do what it did.) <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 07:18, 31 December 2024 (UTC)
*:::::Like everyone said, there should be a ''de facto'' ban on using AI images in Misplaced Pages articles. They are effectively fake images pretending to be real, so they are out of step with the values of Misplaced Pages.--'''''] <sup>]</sup>''''' 08:20, 31 December 2024 (UTC)
*::::::Except, not everybody ''has'' said that, because the majority of those of us who have refrained from hyperbole have pointed out that not all AI images are "fake images pretending to be real" (and those few that are can already be removed under existing policy). You might like to try actually reading the discussion before commenting further. ] (]) 10:24, 31 December 2024 (UTC)
*:::::@], exactly how much "ability to check what the thing is doing" do you need to be able to do, when the image shows 99 dots and 1 baseball, to illustrate the concept of 1%? If the image above said {{tl|pd-algorithm}} instead of {{tl|cc-by-sa-4.0}}, would you remove if from the article, because you just can't be sure that it shows 1%? ] (]) 02:33, 2 January 2025 (UTC)
*::::::The above is a useful example to an extent, but it is a toy example. I really do think i is required in general when we aren't dealing with media we ourselves are generating. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 04:43, 2 January 2025 (UTC)
*:::::::How do we differentiate in policy between a "toy example" (that really would be used in an article) and "real" examples? Is it just that if I upload it, then you know me, and assume I've been responsible? ] (]) 07:13, 2 January 2025 (UTC)
*::::There definitely exist generative AI for SVG files. Here's an example: I used generative AI in Adobe Illustrator to generate the SVG gear in ] (from ]) before drawing by hand the more informative parts of the image. The gear drawing is not great (a real gear would have uniform tooth shape) but maybe the shading is better than I would have done by hand, giving an appearance of dimensionality and surface material while remaining deliberately stylized. Is that the sort of thing everyone here is trying to forbid?
*::::I can definitely see a case for forbidding AI-generated photorealistic images, especially of BLPs, but that's different from human oversight of AI in the generation of schematic images such as this one. —] (]) 01:15, 1 January 2025 (UTC)
*:::::I'd include BDPs, too. I had to get a few AI-generated images of allegedly Haitian presidents deleted a while ago. The "paintings" were 100% fake, right down to the deformed medals on their military uniforms. An AI-generated "generic person" would be okay for some purposes. For a few purposes (e.g., illustrations of ]) it could even be preferable to have a fake "person" than a real one. But for individual/named people, it would be best not to have anything unless it definitely looks like the named person. ] (]) 07:35, 2 January 2025 (UTC)
*I put it to you that our decision on this requires nuance. It's obviously insane to allow AI-generated images of, for example, Donald Trump, and it's obviously insane to ban AI-generated images from, for example, ] or ].—] <small>]/]</small> 11:21, 31 December 2024 (UTC)
*:Of course, that's why I'm only looking at specific cases and refrain from proposing a blanket ban on generative AI. Regarding Donald Trump, we do have one AI-generated image of him that is reasonable to allow (in ]), as the image itself was the subject of relevant commentary. Of course, this is different from using an AI-generated image to illustrate ] himself, which is what my proposal would recommend against. ] (] · ]) 11:32, 31 December 2024 (UTC)
*::That's certainly true, but others are adopting much more extreme positions than you are, and it was the more extreme views that I wished to challenge.—] <small>]/]</small> 11:34, 31 December 2024 (UTC)
*:::Thanks for the (very reasoned) addition, I just wanted to make my original proposal clear. ] (] · ]) 11:43, 31 December 2024 (UTC)
*Going off WAID's example above, perhaps we should be trying to restrict the use of AI where image accuracy/precision is essential, as it would be for BLP and medical info, among other cases, but in cases where we are talking generic or abstract concepts, like the 1% image, it's use is reasonable. I would still say we should strongly prefer am image made by a human with high control of the output, but when accuracy is not as important as just the visualization, it's reasonable to turn to AI to help. ] (]) 15:12, 31 December 2024 (UTC)
* '''Support total ban of AI imagery''' - There are probable copyright problems and veracity problems with anything coming out of a machine. In a word of manipulated reality, Misplaced Pages will be increasingly respected for holding a hard line against synthetic imagery. ] (]) 15:39, 31 December 2024 (UTC)
*:For both issues AI vs not AI is irrelevant. For copyright, if the image is a copyvio we can't use it regardless of whether it is AI or not AI, if it's not a copyvio then that's not a reason to use or not use the image. If the images is not verifiably accurate then we already can (and should) exclude it, regardless of whether it is AI or not AI. For more detail see the extensive discussion above you've either not read or ignored. ] (]) 16:34, 31 December 2024 (UTC)
*'''Yes''', we absolutely should ban the use of AI-generated images in these subjects (and beyond, but that's outside the scope of this discussion). AI should not be used to make up a simulation of a living person. It does not actually depict the person and may introduce errors or flaws that don't actually exist. The picture ''does not depict the real person'' because it is quite simply fake.
*Even worse would be using AI to develop medical images in articles ''in any way''. The possibility for error there is unacceptable. Yes, humans make errors too, but there there is a) someone with the responsibility to fix it and b) someone conscious who actually made the picture, rather than a black box that spat it out after looking at similar training data. '']'' 🎄 ] — ] 🎄 20:08, 31 December 2024 (UTC)
*:It's ''incredibly'' disheartening to see multiple otherwise intelligent editors who have apparently not read and/or not understood what has been said in the discussion but rather responding with what appears to be knee-jerk reactions to anti-AI scaremongering. The sky will not fall in, Misplaced Pages is not going to be taken over by AI, AI is not out to subvert Misplaced Pages, we already can (and do) remove (and more commonly not add in the first placE) false and misleading information/images. ] (]) 20:31, 31 December 2024 (UTC)
*::So what benefit does allowing AI images bring? We shouldn't be forced to decide these on a case-by-case basis.
*::I'm sorry to dishearten you, but I still respectfully disagree with you. And I don't think this is "scaremongering" (although I admit that if it was, I would of course claim it wasn't). '']'' 🎄 ] — ] 🎄 21:02, 31 December 2024 (UTC) '']'' 🎄 ] — ] 🎄 20:56, 31 December 2024 (UTC)
*:::Determining what benefits ''any'' image brings to Misplaced Pages can ''only'' be done on a case-by-case basis. It is literally impossible to know whether any image improves the encyclopaedia without knowing the context of which portion of what article it would illustrate, and what alternative images are and are not available for that same spot.
*:::The benefit of allowing AI images is that when an AI image is the best option for a given article we use it. We gain absolutely nothing by prohibiting using the best image available, indeed doing so would actively harm the project without bringing any benefits. AI images that are misleading, inaccurate or any of the other negative things ''any'' image can be are never the best option and so are never used - we don't need any policies or guidelines to tell us that. ] (]) 21:43, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated text or images in articles''', except in contexts where the AI-generated content is itself the subject of discussion (in a ] or ]). Generative AI is fundamentally at odds with Misplaced Pages's mission of providing reliable information, because of its propensity to distort reality or make up information out of whole cloth. It has no place in our encyclopedia. <span class="nowrap">—] (] | ])</span> 21:34, 31 December 2024 (UTC)
*'''Support blanket ban on AI-generated images''' except in ABOUTSELF contexts. This is ''especially'' a problem given the preeminence Google gives to Misplaced Pages images in its image search. ] (]) 22:49, 31 December 2024 (UTC)
*'''Ban across the board''', except in articles which are actually about AI-generated imagery or the tools used to create them, or the image itself is the subject of substantial commentary within the article for some reason. Even in those cases, clearly indicating that the image is AI-generated should be required. ] <small><sup>]</sup></small> 00:29, 1 January 2025 (UTC)
*'''Oppose blanket bans''' that would forbid the use of AI assistance in creating diagrams or other deliberately stylized content. Also oppose blanket bans that would forbid AI illustrations in articles about AI illustrations. I am not opposed to banning photorealistic AI-generated images in non-AI-generation contexts or banning AI-generated images from BLPs unless the image itself is specifically relevant to the subject of the BLP. —] (]) 01:27, 1 January 2025 (UTC)
]?]]
*'''Oppose blanket bans''' AI is just a new buzzword so, for example, Apple phones now include "Apple Intelligence" as a standard feature. Does this means that photographs taken using Apple phones will be inadmissable? That would be silly because legacy technologies are already rife with issues of accuracy and verification. For example, there's an image on the main page right now ''(right)''. This purports to be a particular person ("]") but, if you check the , you find that it may have been his brother and even the attribution to the artist is uncertain. AI features may help in exposing such existing weaknesses in our image use and so we should be free to use them in an intelligent way. ]🐉(]) 08:03, 1 January 2025 (UTC)
*:So, you expect an the AI, ''notoriously trained on Misplaced Pages (and whatever else is floating around on the internet)'', to correct Misplaced Pages where humans have failed... using the data it ''scraped from Misplaced Pages (and who knows where else)''? ] (]) 11:12, 1 January 2025 (UTC)
*::I tried using the Deep Research option of Gemini to assess the attribution of the Macquarie portrait. Its stated methodology seemed quite respectable and sensible.
{{cot|The Opie Portrait of Lachlan Macquarie: An Examination of its Attribution: Methodology}}
To thoroughly investigate the attribution of the Opie portrait of Lachlan Macquarie, a comprehensive research process was undertaken. This involved several key steps:
#Gathering information on the Opie portrait: This included details about its history, provenance, and any available information on its cost.
#Reviewing scholarly articles and publications: This step focused on finding academic discussions specifically addressing the attribution of the portrait to John Opie.
#Collecting expert opinions: Statements and opinions from art experts and historians were gathered to understand the range of perspectives on the certainty of the attribution.
#Examining historical documents and records: This involved searching for any records that could shed light on the portrait's origins and authenticity, such as Macquarie's personal journals or contemporary accounts.
#Exploring scientific and technical analyses: Information was sought on any scientific or technical analyses conducted on the portrait, such as pigment analysis or canvas dating, to determine its authenticity.
#Comparing the portrait to other Opie works: This step involved analyzing the style and technique of the Opie portrait in comparison to other known portraits by Opie to identify similarities and differences.
{{cob}}
*::It was quite transparent in listing and citing the sources that it used for its analysis. These included the Misplaced Pages image but if one didn't want that included, it would be easy to exclude it.
*::So, AIs don't have to be inscrutable black boxes. They can have programmatic parameters like the existing bots and scripts that we use routinely on Misplaced Pages. Such power tools seem needed to deal with the large image backlogs that we have on Commons. Perhaps they could help by providing captions and categories where these don't exist.
*::]🐉(]) 09:09, 2 January 2025 (UTC)
*:::They don't ''have to be black boxes'' but they are ''by design'': they exist in a legally dubious area and thus hide what they're scraping to avoid further legal problems. That's no secret. We know for example that Misplaced Pages is a core data set for likely most AIs today. They also notoriously and quite confidently spit out a lie ("hallucinate") and frequently spit out total nonsense. Add to that that they're restricted to whatever is floating around on the internet or whatever other data set they've been fed (usually just more internet), and many specialist topics, like texts on ancient history and even standard reference works, are not accessible on the internet (despite Google's efforts). ] (]) 09:39, 2 January 2025 (UTC)
*:::While its stated methodology seems sensible, there's no evidence that it actually followed that methodology. The bullet points are pretty vague, and are pretty much the default methodologies used to examine actual historical works. ] (] · ]) 17:40, 2 January 2025 (UTC)
*:::: Yes, there's evidence. As I stated above, the analysis is transparent and cites the sources that it used. And these all seem to check out rather than being invented. So, this level of AI goes beyond the first generation of LLM and addresses some of their weaknesses. I suppose that image generation is likewise being developed and improved and so we shouldn't rush to judgement while the technology is undergoing rapid development. ]🐉(]) 17:28, 4 January 2025 (UTC)
* '''Oppose blanket ban''': best of luck to editors here who hope to be able to ban an entirely undefined and largely undetectable procedure. The term 'AI' as commonly used is no more than a buzzword - what ''exactly'' would be banned? And how does it improve the encyclopedia to encourage editors to object to images not simply because they are inaccurate, or inappropriate for the article, but because they subjectively look too good? Will the image creator be quizzed on Commons about the tools they used? Will creators who are transparent about what they have created have their images deleted while those who keep silent don’t? Honestly, this whole discussion is going to seem hopelessly outdated within a year at most. It’s like when early calculators were banned in exams because they were ‘cheating’, forcing students to use slide rules. ] (]) 12:52, 1 January 2025 (UTC)
*:I am genuinely confused as to why this has turned into a discussion about a blanket ban, even though the original proposal exclusively focused on ''AI-generated'' images (the kind that is generated by an AI model from a prompt, which are already tagged on Commons, not regular images with AI enhancement or tools being used) and only in specific contexts. Not sure where the "subjectively look too good" thing even comes from, honestly. ] (] · ]) 12:58, 1 January 2025 (UTC)
*::That just show how ill-defined the whole area is. It seem you restrict the term 'AI-generated' to mean "images generated solely(?) from a text prompt". The question posed above has no such restriction. What a buzzword means is largely in the mind of the reader, of course, but to me and I think to many, 'AI-generated' means generated by AI. ] (]) 13:15, 1 January 2025 (UTC)
*:::I used the text prompt example because that is the most common way to have an AI model generate an image, but I recognize that I should've clarified it better. There is definitely a distinction between an image being ''generated'' by AI (like the Laurence Boccolini example below) and an image being ''altered'' or retouched by AI (which includes many features integrated in smartphones today). I don't think it's a "buzzword" to say that there is a meaningful difference between an image being made up by an AI model and a preexisting image being altered in some way, and I am surprised that many people understand "AI-generated" as including the latter. ] (] · ]) 15:24, 1 January 2025 (UTC)
*'''Oppose as unenforceable.''' I just want you to imagine enforcing this policy against people who have not violated it. All this will do is allow Wikipedians who primarily contribute via text to accuse artists of using AI ] to get their contributions taken down. I understand the impulse to oppose AI on principle, but the labor and aesthetic issues don't actually have anything to do with Misplaced Pages. If there is not actually a problem with the content conveyed by the image—for example, if the illustrator intentionally corrected any hallucinations—then someone objecting over AI is not discussing page content. If the image was not even made with AI, they are hallucinating based on prejudices that are irrelevant to the image. The bottom line is that images should be judged on their content, not how they were made. Besides all the policy-driven stuff, if Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? Categorical bans of this kind are ill-advised and anti-illustrator. ] (]) 15:41, 1 January 2025 (UTC)
*:And the same applies to photography, of course. If in my photo of a garden I notice there is a distracting piece of paper on the lawn, nobody would worry if I used the old-style clone-stamp tool to remove it in Photoshop, adding new grass in its place (I'm assuming here that I don't change details of the actual landscape in any way). Now, though, Photoshop uses AI to achieve essentially the same result while making it simpler for the user. A large proportion of all processed photos will have at least some similar but essentially undetectable "generated AI" content, even if only a small area of grass. There is simply no way to enforce the proposed policy, short of banning all high-quality photography – which requires post-processing by design, and in which similar encyclopedically non-problematic edits are commonplace. ] (]) 17:39, 1 January 2025 (UTC)
*:Before anyone objects that my example is not "an image generated from a text prompt", note that there's no mention of such a restriction in the proposal we are discussing. Even if there were, it makes no difference. Photoshop can already generate photo-realistic areas from a text prompt. If such use is non-misleading and essentially undetectable, it's fine; if if changes the image in such a way as to make it misleading, inaccurate or non-encycpopedic in any way it can be challenged on that basis. ] (]) 17:58, 1 January 2025 (UTC)
*::As I said previously, the text prompt is just an example, not a restriction of the proposal. The point is that you talk about editing an existing image (which is what you talk about, as you say {{tq|if if changes the image}}), while I am talking about creating an image ''ex nihilo'', which is what "generating" means. ] (] · ]) 18:05, 1 January 2025 (UTC)
*:::I'm talking about a photograph with AI-generated areas within it. This is commonplace, and is targeted by the proposal. Categorical bans of the type suggested are indeed ill-advised. ] (]) 18:16, 1 January 2025 (UTC)
*:Even if the ban is unenforceable, there are many editors who will choose to use AI images if they are allowed and just as cheerfully skip them if they are not allowed. That would mean the only people posting AI images are those who choose to break the rule and/or don't know about it. That would probably add up to many AI images not used. ] (]) 22:51, 3 January 2025 (UTC)
*'''Support blanket ban''' because "AI" is a fundamentally unethical technology based on the exploitation of labor, the wanton destruction of the planetary environment, and the subversion of every value that an encyclopedia should stand for. ABOUTSELF-type exceptions for "AI" output ''that has already been generated'' might be permissible, in order to document the cursed time in which we live, but those exceptions are going to be rare. How many examples of Shrimp Jesus slop do we need? ] (]) 23:30, 1 January 2025 (UTC)
*'''Support blanket ban''' - Primarily because of the "poisoning the well"/"dead internet" issues created by it. ] (]) 14:30, 2 January 2025 (UTC)
* '''Support a blanket ban''' to assure some control over AI-creep in Misplaced Pages. And per discussion. ] (]) 10:50, 3 January 2025 (UTC)
* '''Support that ] applies to images''': images should be verifiable, neutral, and absent of original research. AI is just the latest quickest way to produce images that are original, unverifiable, and potentially biased. Is anyone in their right mind saying that we allow people to game our rules on ] and ] by using images instead of text? ] (]) 17:04, 3 January 2025 (UTC)
*:As an aside on this: in some cases Commons is being treated as a way of side-stepping ] and other restrictions. Stuff that would get deleted if it were written content on WP gets in to WP as images posted on Commons. The worst examples are those conflict maps that are created from a bunch of Twitter posts (eg the Syrian civil war one). AI-generated imagery is another field where that appears to be happening. ] (]) 10:43, 4 January 2025 (UTC)
*'''Support temporary blanket ban''' with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. I support an exception for the when the article is about the image itself and that image is notable, such as the photograph of the black-and-blue/gold-and-white dress in ] and/or examples of AI images in articles in which they are relevant. E.g. "here is what a hallucination is: count the fingers." ] (]) 23:01, 3 January 2025 (UTC)
* First, I think any guidance should avoid referring to specific technology, as that changes rapidly and is used for many different purposes. Second, assuming that the image in question has a suitable copyright status for use on Misplaced Pages, the key question is whether or not the reliability of the image has been established. If the intent of the image is to display 100 dots with 99 having the same appearance and 1 with a different appearance, then ordinary math skills are sufficient and so any Misplaced Pages editor can evaluate the reliability without performing original research. If the intent is to depict a likeness of a specific person, then there needs to be reliable sources indicating that the image is sufficiently accurate. This is the same for actual photographs, re-touched ones, drawings, hedcuts, and so forth. Typically this can be established by a reliable source using that image with a corresponding description or context. ] (]) 17:59, 4 January 2025 (UTC)
*'''Support Blanket Ban on AI generated imagery''' per most of the discussion above. It's a very slippery slope. I ''might'' consider a very narrow exception for an AI generated image of a person that was specifically authorized or commissioned by the subject. -] (]) 02:45, 5 January 2025 (UTC)
* '''Oppose blanket ban''' It is far too early to take an absolutist position, particularly when the potential is enormous. Misplaced Pages is already is image desert and to reject something that is only at the cusp of development is unwise. '''<span style="text-shadow:7px 7px 8px black; font-family:Papyrus">]<sup>]</sup></span>''' 20:11, 5 January 2025 (UTC)
*'''Support blanket ban''' on AI-generated images except in ABOUTSELF contexts. An encyclopedia should not be using fake images. I do not believe that further nuance is necessary. ] (]) 22:44, 5 January 2025 (UTC)
*'''Support blanket ban''' as the general guideline, as accuracy, personal rights, and intellectual rights issues are very weighty, here (as is disclosure to the reader). (I could see perhaps supporting adoption of a sub-guideline for ways to come to a broad consensus in individual use cases (carve-outs, except for BLPs) which address all the weighty issues on an individual use basis -- but that needs to be drafted and agreed to, and there is no good reason to wait to adopt the general ban in the meantime). ] (]) 15:32, 8 January 2025 (UTC)
]
*'''Support indefinite blanket ban except ABOUTSELF and simple abstract examples''' (such as the image of 99 dots above). In addition to all the issues raised above, including copyvio and creator consent issues, in cases of photorealistic images it may never be obvious to all readers exactly which elements of the image are guesswork. The cormorant picture at the head of the section reminded me of ]. Had AI been trained on paintings of horses instead of actual videos and used to "improve" said videos, we would've ended up with serious delusions about the horse's gait. We don't know what questions -- scientific or otherwise -- photography will be used to settle in the coming years, but we do know that consumer-grade photo AI has already been trained to intentionally fake detail to draw sales, such as on photos of the Moon. I think it's unrealistic to require contributors to take photos with expensive cameras or specially-made apps, but Misplaced Pages should act to limit its exposure to this kind of technology as far as is feasible. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 20:57, 9 January 2025 (UTC)
{{clear}}
== Guidelines for "References in Popular Culture" sections ==
===BLPs===
{{Archive top
|status = Consensus against
|result = There is clear consensus against using AI-generated imagery to depict BLP subjects. Marginal cases (such as major AI enhancement or where an AI-generated image of a living person is itself notable) can be worked out on a case-by-case basis. I will add a sentence reflecting this consensus to the ] and the ]. —] (]) 14:02, 8 January 2025 (UTC)
}}
Are AI-generated images (generated via text prompts, see also: ]) okay to use to depict BLP subjects? The ] example was mentioned in the opening paragraph. The image was created using ], {{tq|a text-to-image model developed by xAI, to generate images...As with other text-to-image models, Aurora generates images from natural language descriptions, called prompts.}} ]]] ] (]) 12:34, 31 December 2024 (UTC)
]]]
Do any such guidelines exist? If not, I'd like to suggest some, namely:
]: <ins>Note</ins>: that these images can either be photorealistic in style (such as the Laurence Boccolini example) or non-photorealistic in style (see the ] example, which was generated using ], another text-to-image model).
1. Avoid such a list if possible. "References in Popular Culture" lists are (almost always) inherently ], because they (almost always) depend on Misplaced Pages editors to determine what is worthy of inclusion.
*'''No.''' I don't think they are at all, as, despite looking photorealistic, they are essentially just speculation about what the person might look like. A photorealistic image conveys the look of something up to the details, and giving a false impression of what the person looks like (or, at best, just guesswork) is actively counterproductive. (Edit 21:59, 31 December 2024 (UTC): clarified bolded !vote since everyone else did it) ] (] · ]) 12:46, 31 December 2024 (UTC)
*:That AI generated image looks like ] wearing a Laurence Boccolini suit. ] (]) 12:50, 31 December 2024 (UTC)
*:There are plenty of non-free images of Laurence Boccolini with which this image can be compared. Assuming at least most of those are accurate representations of them (I've never heard of them before and have no other frame of reference) the image above is similar to but not an accurate representation of them (most obviously but probably least significantly, in none of the available images are they wearing that design of glasses). This means the image should not be used to identify them ''unless'' they use it to identify themselves. It should not be used elsewhere in the article unless it has been the subject of notable commentary. That it is an AI image makes absolutely no difference to any of this. ] (]) 16:45, 31 December 2024 (UTC)
*'''No'''. Well, that was easy.{{pb}}<!--converted from 2 lines ~ToBeFree-->They are fake images; they do not actually depict the person. They depict an AI-generated ''simulation'' of a person that may be inaccurate. '']'' 🎄 ] — ] 🎄 20:00, 31 December 2024 (UTC)
*:Even if the subject uses the image to identify themselves, the image is still fake. '']'' (] — ]) 19:17, 2 January 2025 (UTC)
*'''No''', with the caveat that its mostly on the grounds that we don't have enough information and when it comes to BLP we are required to exercise caution. If at some point in the future AI generated photorealistic simulacrums living people become mainstream with major newspapers and academic publishers it would be fair to revisit any restrictions, but in this I strongly believe that we should follow not lead. ] (]) 20:37, 31 December 2024 (UTC)
*'''No'''. The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person. <span class="nowrap">—] (] | ])</span> 21:30, 31 December 2024 (UTC)
*'''No''' except perhaps, maybe, if the subject explicitly is already using that image to represent themselves. But mostly no. -] (]) 21:32, 31 December 2024 (UTC)
*'''Yes''', when that image is an accurate representation and better than any available alternative, used by the subject to represent themselves, or the subject of notable commentary. However, as these are the exact requirements to use ''any'' image to represent a BLP subject this is already policy. ] (]) 21:46, 31 December 2024 (UTC)
*:How well can we determine how accurate a representation it is? Looking at the example above, I'd argue that the real ] has a somewhat rounder/pointier chin, a wider mouth, and possibly different eye wrinkles, although the latter probably depends quite a lot on the facial expression.
*:How accurate a representation a photorealistic AI image is is ultimately a matter of editor opinion. '']'' 🎄 ] — ] 🎄 21:54, 31 December 2024 (UTC)
*::{{tpq|How well can we determine how accurate a representation it is?}} in exactly the same way that we can determine whether a human-crafted image is an accurate representation. How accurate a representation ''any'' image is is ultimately a matter of editor opinion. Whether an image is AI or not is irrelevant. I agree the example image above is not sufficiently accurate, but we wouldn't ban photoshopped images because one example was not deemed accurate enough, because we are rational people who understand that one example is not representative of an entire class of images - at least when the subject is something other than AI. ] (]) 23:54, 31 December 2024 (UTC)
*:::I think except in a few exceptional circumstances of actual complex restorations, human photoshopping is not going to change or distort a person's appearance in the same way an AI image would. Modifications done by a person who is paying attention to what they are doing and merely enhancing an image, by person who is aware, while they are making changes, that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator. '']'' 🎄 ] — ] 🎄 00:14, 1 January 2025 (UTC)
*::::I'm guessing your filter bubble doesn't include ] and their notorious ] problems. ] (]) 02:46, 2 January 2025 (UTC)
*:::A photo of a person can be connected to a specific time, place, and subject that existed. It can be compared to other images sharing one or more of those properties. A photo that was PhotoShopped is still either a generally faithful reproduction of a scene that existed, or has significant alterations that can still be attributed to a human or at least to a specific algorithm, e.g. filters. The artistic license of a painting can still be attributed to a human and doesn't run much risk of being misidentified as real, unless it's by Chuck Close et al. An AI-generated image cannot be connected to a particular scene that ever existed and cannot be attributable to a human's artistic license (and there is legal precedent that such images are not copyrightable to the prompter specifically because of this). Individual errors in a human-generated artwork are far more predictable, understandable, identifiable, traceable... than those in AI-generated images. We have innate assumptions when we encounter real images or artwork that are just not transferable. These are meaningful differences to the vast majority of people: according to a , 87% of respondents want AI-generated art to ''at least'' be transparent, and 98% consider authentic images "pivotal in establishing trust". {{pb}}And even if you disagree with all that, can you not see the larger problem of AI images on Misplaced Pages getting propagated into generative AI corpora? ] (]) 04:20, 2 January 2025 (UTC)
*::::I agree that our old assumptions don't hold true. I think the world will need new assumptions. We will probably have those in place in another decade or so.
*::::I think we're ], not here to protect AI engines from ingesting AI-generated artwork. Figuring out what they should ingest is their problem, not mine. ] (]) 07:40, 2 January 2025 (UTC)
*'''Absolutely no fake/AI images of people, photorealistic or otherwise'''. How is this even a question? These images are fake. Readers need to be able to trust Misplaced Pages, not navigate around whatever junk someone has created with a prompt and presented as somehow representative. This includes text. ] (]) 22:24, 31 December 2024 (UTC)
*'''No''' except for edge cases (mostly, if the image itself is notable enough to go into the article). ] (]) 22:31, 31 December 2024 (UTC)
*'''Absolutely not''', except for ABOUTSELF. "They're fine if they're accurate enough" is an obscenely naive stance. ] (]) 23:06, 31 December 2024 (UTC)
* '''No''' with no exceptions. ] (]) 23:54, 31 December 2024 (UTC)
*'''No'''. We don't permit falsifications in BLPs. ] <small><sup>]</sup></small> 00:30, 1 January 2025 (UTC)
*:For the requested clarification by {{u|Some1}}, no AI-generated images (except when the image ''itself'' is specifically discussed in the article, and even then it should not be the lead image and it should be clearly indicated that the image is AI-generated), no drawings, no nothing of that sort. ''Actual photographs'' of the subject, nothing else. Articles are not required to have images at all; no image whatsoever is preferable to something which is ''not'' an image of the person. ] <small><sup>]</sup></small> 05:42, 3 January 2025 (UTC)
*'''No, but with exceptions'''. I could imagine a case where a specific AI-generated image has some direct relevance to the notability of the subject of a BLP. In such cases, it should be included, if it could be properly licensed. But I do oppose AI-generated images as portraits of BLP subjects. —] (]) 01:27, 1 January 2025 (UTC)
*:Since I was pinged on this point: when I wrote "I do oppose AI-generated images as portraits", I meant exactly that, including all AI-generated images, such as those in a sketchy or artistic style, not just the photorealistic ones. I am not opposed to certain uses of AI-generated images in BLPs when they are not the main portrait of the subject, for instance in diagrams (not depicting the subject) to illustrate some concept pioneered by the subject, or in case someone becomes famous for being the subject of an AI-generated image. —] (]) 05:41, 3 January 2025 (UTC)
*'''No''', and no exceptions or do-overs. Better to have no images (or Stone-Age style cave paintings) than ''Frankenstein'' images, no matter how accurate or artistic. Akin to shopped manipulated photographs, they should have no room (or room service) at the WikiInn. ] (]) 01:34, 1 January 2025 (UTC)
*:Some "shopped manipulated photographs" are misleading and inaccurate, others are not. We can and do exclude the former from the parts of the encyclopaedia where they don't add value without specific policies and without excluding them where they are relevant (e.g. ]) or excluding those that are not misleading or inaccurate. AI images are no different. ] (]) 02:57, 1 January 2025 (UTC)
*::Assuming we know. Assuming it's material. The infobox image in – and the only extant photo of – ] was "photoshopped" by a marketing team, maybe half a century before Adobe Photoshop was created. They wanted to show him wearing a necktie. I don't think that this level of manipulation is actually a problem. ] (]) 07:44, 2 January 2025 (UTC)
*'''Yes''', so long as it is an accurate representation. ] ] 03:40, 1 January 2025 (UTC)
*'''No''' not for BLPs. ] (]) 04:15, 1 January 2025 (UTC)
*'''No''' Not at all relevant for pictures of people, as the accuracy is not enough and can misrepresent. Also (and I'm shocked as it seems no one has mentioned this), what about Copyright issues? Who holds the copyright for an AI-generated image? The user who wrote the prompt? The creator(s) of the AI model? The creator(s) of the images in the database that the AI used to create the images? It's sounds to me such a clusterfuck of copyright issues that I don't understand how this is even a discussion. --] (]) 07:10, 1 January 2025 (UTC)
*:Under the US law / copyright office, machine-generated images including those by AI cannot be copyrighted. That also means that AI images aren't treated as derivative works.<br style="margin-bottom:0.5em"/>What is still under legal concern is whether the use of bodies of copyrighted works without any approve or license from the copyright holders to train AI models is under fair use or not. There are multiple court cases where this is the primary challenge, and none have yet to reach a decision yet. Assuming the courts rule that there was no fair use, that would either require the entity that owns the AI to pay fines and ongoing licensing costs, or delete their trained model to start afresh with free licensed/works, but in either case, that would not impact how we'd use any resulting AI image from a copyright standpoint.<span id="Masem:1735741774879:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:29, 1 January 2025 (UTC)</span>
*'''No''', I'm in agreeance with ] here. Whether we like it or not, the usage of a portrait on an article implies that it's just that, a portrait. It's incredibly disingenuous to users to represent an AI generated photo as truth. ] (]) 09:32, 1 January 2025 (UTC)
*:So you just said a portrait can be used because wikipedia tells you it's a portrait, and thus not a real photo. Can't AI be exactly the same? As long as we tell readers it is an AI representation? Heck, most AI looks closer to the real thing than any portrait. ] (]) 10:07, 2 January 2025 (UTC)
*::To clarify, I didn't mean "portrait" as in "painting," I meant it as "photo of person."
*::However, I really want to stick to what you say at the end there: {{tq|Heck, most AI looks closer to the real thing than any portrait.}}
*::That's exactly the problem: by looking close to the "real thing" it misleads users into believing a non-existent source of truth.{{br|2}}
*::Per the wording of the RfC of "{{tq|depict BLP subjects}}," I don't think there would be any valid case to utilize AI images. I hold a strong No. ] (]) 04:15, 3 January 2025 (UTC)
*'''No.''' We should not use AI-generated images for situations like this, they are basically just guesswork by a machine as Quark said and they can misinform readers as to what a person looks like. Plus, there's a big grey area regarding copyright. For an AI generator to know what somebody looks like, it has to have photos of that person in its dataset, so it's very possible that they can be considered derivative works or copyright violations. Using an AI image (derivative work) to get around the fact that we have no free images is just fair use with extra steps. ] (]) 19:33, 1 January 2025 (UTC) ]?]]
*'''Maybe''' There was a prominent BLP image which we displayed on the ]. ''(right)'' This made me uneasy because it was an artistic impression created from photographs rather than life. And it was "colored digitally". Functionally, this seems to be exactly the same sort of thing as the ] composite. The issue should not be whether there's a particular technology label involved but whether such creative composites and artists' impressions are acceptable as better than nothing. ]🐉(]) 08:30, 1 January 2025 (UTC)
*:Except it is clear to everyone that the illustration to the right is a sketch, a human rendition, while in the photorealistic image above, it is less clear. '']'' (] — ]) 14:18, 1 January 2025 (UTC)
*::Except it says right below it "AI-generated image of Laurence Boccolini." How much more clear can it be when it say point-blank "AI-generated image." ] (]) 10:12, 2 January 2025 (UTC)
*:::Commons descriptions do not appear on our articles. ] (]) 10:28, 2 January 2025 (UTC)
*:::People taking a quick glance at an infobox image that looks pretty like a photograph are not going to scrutinize commons tagging. '']'' (] — ]) 14:15, 2 January 2025 (UTC)
*::Keep in mind that many AIs can produce works that match various styles, not just photographic quality. It is still possible for AI to produce something that looks like a watercolor or sketched drawing.<span id="Masem:1735742005673:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 14:33, 1 January 2025 (UTC)</span>
*:::Yes, you're absolutely right. But so far photorealistic images have been the most common to illustrate articles (see ] for some examples. '']'' (] — ]) 14:37, 1 January 2025 (UTC)
*::::Then push to ban photorealistic images, rather than pushing for a blanket ban that would also apply to obvious sketches. —] (]) 20:06, 1 January 2025 (UTC)
*:::::Same thing I wrote above, but for "photoshopping" read "drawing": (Bold added for emphasis)
*:::::{{tqq|...human is not going to change or distort a person's appearance in the same way an AI image would. done by a person who is paying attention to what they are doing by '''person who is aware, while they are making , that they might be distorting the image and is, I only assume, trying to minimise it''' – those careful modifications shouldn't be equated with something made up by an AI image generator.}} '']'' (] — ]) 20:56, 1 January 2025 (UTC)
*::::::@] then why are you advocating for a ban on AI images rather than a ban on distorted images? Remember that with careful modifications by someone who is aware of what they are doing that AI images can be made more accurate. Why are you assuming that a human artist is trying to minimise the distortions but someone working with AI is not? ] (]) 22:12, 1 January 2025 (UTC)
*:::::::I believe that AI-generated images are fundamentally misleading because they are a simulation by a machine rather than a drawing by a human. To quote pythoncoder above: {{tqq|The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person.}} '']'' (] — ]) 00:16, 2 January 2025 (UTC)
*::::::::Once again your actual problem is not AI, but with misleading images. Which can be, and are, already a violation of policy. ] (]) 01:17, 2 January 2025 (UTC)
*:::::::::I think all AI-generated images, except simple diagrams as WhatamIdoing point out above, are misleading. So yes, my problem is with misleading images, which includes all photorealistic images generated by AI, which is why I support this proposal for a blanket ban in BLPs and medical articles. '']'' (] — ]) 02:30, 2 January 2025 (UTC)
*::::::::::To clarify, I'm willing to make an exception in this proposal for very simple geometric diagrams. '']'' (] — ]) 02:38, 2 January 2025 (UTC)
*::::::::::Despite the fact that not all AI-generated images are misleading, not all misleading images are AI-generated and it is not always possible to tell whether an image is or is not AI-generated? ] (]) 02:58, 2 January 2025 (UTC)
*:::::::::::Enforcement is a separate issue. Whether or not all (or the vast majority) of AI images are misleading is the subject of this dispute.
*:::::::::::I'm not going to mistreat the horse further, as we've each made our points and understand where the other stands. '']'' (] — ]) 15:30, 2 January 2025 (UTC)
*::::::::::Even "simple diagrams" are not clear-cut. The process of AI-generating any image, no matter how simple, is still very complex and can easily follow any number of different paths to meet the prompt constraints. These paths through embedding space are black boxes and the likelihood they converge on the same output is going to vary wildly depending on the degrees of freedom in the prompt, the dimensionality of the embedding space, token corpus size, etc. The only thing the user can really change, other than switching between models, is the prompt, and at some point constructing a prompt that is guaranteed to yield the same result 100% of the time becomes a ] exercise. This is in contrast with non-generative AI diagram-rendering software that follow very fixed, reproducible, ''known'' paths. ] (]) 04:44, 2 January 2025 (UTC)
*:::::::::::Why does the path matter? If the output is correct it is correct no matter what route was taken to get there. If the output is incorrect it is incorrect no matter what route was taken to get there. If it is unknown or unknowable whether the output is correct or not that is true no matter what route was taken to get there. ] (]) 04:48, 2 January 2025 (UTC)
*::::::::::::If I use BioRender or GraphPad to generate a figure, I can be confident that the output does not have errors that would misrepresent the underlying data. I don't have to verify that all 18,000 data points in a scatter plot exist in the correct XYZ positions because I know the method for rendering them is published and empirically validated. Other people can also be certain that the process of getting from my input to the product is accurate and reproducible, and could in theory reconstruct my raw data from it. AI-generated figures have no prescribed method of transforming input beyond what the prompt entails; therefore I additionally have to be confident in how precise my prompt is ''and'' confident that the training corpus for this procedure is so accurate that no error-producing paths exist (not to mention absolutely certain that there is no embedded contamination from prior prompts). Other people have all those concerns, and on top of that likely don't have access to the prompt or the raw data to validate the output, nor do they necessarily know how fastidious I am about my generative AI use. At least with a hand-drawn diagram viewers can directly transfer their trust in the author's knowledge and reliability to their presumptions about the diagram's accuracy. ] (]) 05:40, 2 January 2025 (UTC)
*:::::::::::::If you've got 18,000 data points, we are beyond the realm of "simple geometric diagrams". ] (]) 07:47, 2 January 2025 (UTC)
*::::::::::::::The original "simple geometric diagrams" comment was referring to your 100 dots image. I don't think increasing the dots materially changes the discussion beyond increasing the laboriousness of verifying the accuracy of the image. ] (]) 07:56, 2 January 2025 (UTC)
*:::::::::::::::Yes, but since "the laboriousness of verifying the accuracy of the image" is exactly what she doesn't want to undertake for 18,000 dots, then I think that's very relevant. ] (]) 07:58, 2 January 2025 (UTC)
*:{{outdent|14}} And where is that cutoff supposed to be? 1000 dots? A single straight line? An atomic diagram? What is "simple" to someone unfamiliar with a topic may be more complex.{{pb}}And I don't want to count 100 dots either! ] (]) 17:43, 2 January 2025 (UTC)
*::Maybe you don't. But I know for certain that you can count 10 across, 10 down, and multiply those two numbers to get 100. That's what I did when I made the image, after all. ] (]) 07:44, 3 January 2025 (UTC)
* '''Comment''': when you Google search someone (at least from the Chrome browser), often the link to the Misplaced Pages article includes a thumbnail of the lead photo as a preview. Even if the photo is labelled as an AI image in the article, people looking at the thumbnail from Google would be misled (if the image is chosen for the preview). ] (]) 09:39, 1 January 2025 (UTC)
*:This is why we should not use inaccurate images, regardless of how the image was created. It has absolutely nothing to do with AI. ] (]) 11:39, 1 January 2025 (UTC)
* '''Already opposed a blanket ban''': It's unclear to me why we have a separate BLP subsection, as BLPs are already included in the main section above. Anyway, I ] there. ] (])
*:Some editors might oppose a blanket ban on ''all'' AI-generated images, while at the same time, are against using AI-generated images (created by using text prompts/]) to depict ]. ] (]) 14:32, 1 January 2025 (UTC)
*'''No''' For at least now, let's not let the problems of AI intrude into BLP articles which need to have the highest level of scrutiny to protect the person represented. Other areas on WP may benefit from AI image use, but let's keep it far out of BLP at this point. --] (]) 14:35, 1 January 2025 (UTC)
*I am not a fan of “banning” AI images completely… but I agree that BLPs require special handling. I look at AI imagery as being akin to a computer generated painting. In a BLP, we allow paintings of the subject, but we ''prefer'' photos over paintings (if available). So… we should prefer photos over AI imagery. {{pb}}<!--list syntax fixed ~ToBeFree--> That said, AI imagery is getting good enough that it can be mistaken for a photo… so… If an AI generated image ''is'' the ''only'' option (ie there is no photo available), then the caption should ''clearly'' indicate that we are using an AI generated image. And that image should be replaced as soon as possible with an actual photograph. ] (]) 14:56, 1 January 2025 (UTC)
*:The issue with the latter is that Misplaced Pages images get picked up by Google and other search engines, where the caption isn't there anymore to add the context that a photorealistic image was AI-generated. ] (] · ]) 15:27, 1 January 2025 (UTC)
*::We're here to build an encyclopedia, not to protect commercial search engine companies.
*::I think my view aligns with Blueboar's (except that I find no firm preference for photos over classical portrait paintings): We shouldn't have ''inaccurate'' AI images of people (living or dead). But the day appears to be coming when AI will generate accurate ones, or at least ones that are close enough to accurate that we can't tell the difference unless the uploader voluntarily discloses that information. Once we can no longer tell the difference, what's the point in banning them? Images need to look like the thing being depicted. When we put an photorealistic image in an article, we could be said to be implicitly claiming that the image ''looks like'' whatever's being depicted. We are not ''necessarily'' warranting that the image was created through a specific process, but the image really does need to look like the subject. ] (]) 03:12, 2 January 2025 (UTC)
*:::You are presuming that sufficient accuracy will prevent us from knowing whether someone is uploading an AI photo, but that is not the case. For instance, if someone uploads large amounts of "photos" of famous people, and can't account for how they got them (e.g. can't give a source where they scraped them from, or dates or any Exif metadata at all for when they were taken), then it will still be obvious that they are likely using AI. ] (]) 17:38, 3 January 2025 (UTC)
*:::As another editor pointed out in their comment, there's the {{blue|ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet}}, especially on a site such as Misplaced Pages and especially on their own biography. ] says the bios {{tq|must be written conservatively and with regard for the subject's privacy.}} ] (]) 18:37, 3 January 2025 (UTC)
*:::{{tqq| Once we can no longer tell the difference, what's the point in banning them?}} Sounds like a wolf's in sheep's clothing to me. Just because the surface appeal of fake pictures gets better, doesn't mean we should ]. '']'' (] — ]) 18:47, 3 January 2025 (UTC)
*:If there are no appropriately-licensed images of a person, then by definition any AI-generated image of them will be either a copyright infringement or a complete fantasy. ] (]) 04:48, 2 January 2025 (UTC)
*::Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant: If an image is a copyvio we can't use it and it is irrelevant why it is a copyvio. If an image is a "complete fantasy" then it is exactly as unusable as a complete fantasy generated by non-AI means, so again AI is irrelevant. I've had to explain this multiple times in this discussion, so read that for more detail and note the lack of refutation. ] (]) 04:52, 2 January 2025 (UTC)
*:::But we can assume good faith that a human isn't blatantly copying something. We can't assume that from an LLM like Stability AI which has been shown to from Getty's images. ] (]) 05:50, 2 January 2025 (UTC)
*::::Ooooh, I'm not sure that we can assume that humans aren't blatantly copying something. We can assume that they meant to be helpful, but that's not quite the same thing. ] (]) 07:48, 2 January 2025 (UTC)
*<s>'''Oppose.'''</s> '''Yes.''' I echo ]: {{Tq2|What this conversation is really circling around is banning entire skillsets from contributing to Misplaced Pages merely because some of us are afraid of AI images and some others of us want to engineer a convenient, half-baked, policy-level "consensus" to point to when they delete quality images from Misplaced Pages. Every time someone generates text based on a source, they are doing some acceptable level of interpretation to extract facts or rephrase it around copyright law, and I don't think illustrations should be considered so severely differently as to justify a categorical ban. For instance, the Gisele Pelicot portrait is based on non-free photos of her. Once the illustration exists, it is trivial to compare it to non-free images to determine if it is an appropriate likeness, which it is. That's no different than judging contributed text's compliance with fact and copyright by referring to the source. It shouldn't be treated differently just because most Wikipedians contribute via text.<br/>Additionally, referring to interpretive skillsets that synthesize new information like, random example, statistical analysis. Excluding those from Misplaced Pages is current practice and not controversial. Meanwhile, I think the ability to create images is more fundamental than that. It's not (inheretly) synthesizing new information. A portrait of a person (alongside the other examples in this thread) contains verifiable information. It is current practice to allow them to fill the gaps where non-free photos can't. That should continue. Honestly, it should expand.}} ] (]) 15:41, 1 January 2025 (UTC)
*:Additionally, in direct response to "these images are fake": All illustrations of a subject could be called "fake" because they are not photographs. (Which can also be faked.) The standard for the inclusion of an illustration on Misplaced Pages has never been photorealism, medium, or previous publication in a RS. The standard is how adequately it reflects the facts which it claims to depict. If there is a better image that can be imported to Misplaced Pages via fair use or a license, then an image can be easily replaced. Until such a better image has been sourced, it is absolutely bewildering to me that we would even discuss removing images of people from their articles. What a person looked like is one of the most basic things that people want to know when they look someone up on Misplaced Pages. Including an image of almost any quality (yes, even a cartoon) is practically by definition an improvement to the article and addressing an important need. We should be encouraging artists to continue filling the gaps that non-free images cannot fill, not creating policies that will inevitably expand into more general prejudices against all new illustrations on Misplaced Pages. ] (]) 15:59, 1 January 2025 (UTC)
*::By "Oppose", I'm assuming your answer to the RfC question is "Yes". And this RfC is about using {{blue|AI-generated images (generated via text prompts, see also: ])}} to depict BLP subjects, not regarding human-created drawings/cartoons/sketches, etc. of BLPs. ] (]) 16:09, 1 January 2025 (UTC)
*:::I've changed it to "yes" to reflect the reversed question. I think all of this is related because there is no coherent distinguishing point; AI can be used to create images in a variety of styles. These discussions have shown that a policy of banning AI images ''will'' be used against non-AI images of all kinds, so I think it's important to say these kinds of things now. ] (]) 16:29, 1 January 2025 (UTC)
*::Photorealistic images scraped from who knows where from who knows what sources are without question simply fake photographs and also clear ] and outright ]. There's no two ways about it. Articles do ''not'' require images: An article with some Frankenstein-ed image scraped from who knows what, where and, when that you "created" from a prompt is not an improvement over having no image at all. If we can't provide a quality image (like something you didn't cook up from a prompt) then people can find quality, non-fake images elsewhere. ] (]) 23:39, 1 January 2025 (UTC)
*:::I really encourage you to read the discussion I linked before because it is ]. Images like these do not inherently include either OR or SYNTH, and the arguments that they do cannot be distinguished from any other user-generated image content. But, briefly, I never said articles required images, and this is not about what articles ''require''. It is about ''improvements'' to the articles. Including a relevant picture where none exists is almost always an improvement, especially for subjects like people. Your disdain for the method the person used to make an image is irrelevant to whether the content of the image is actually verifiable, and the only thing we ought to care about is the content. ] (]) 03:21, 2 January 2025 (UTC)
*::::Images like these are absolutely nothing more than synthesis in the purest sense of the world and are clearly a violation of ]: Again, you have no idea what data was used to generate these images and you're going to have a very hard time convincing anyone to describe them as anything other than outright fakes.
*::::A reminder that WP:SYNTH shuts down attempts at manipulation of images ("It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.") and generating a photorealistic image (from who knows what!) is far beyond that.
*::::Fake images of people do not improve our articles in any way and only erode reader trust. What's next, an argument for the ''fake sources'' LLMs also love to "hallucinate"? ] (]) 03:37, 2 January 2025 (UTC)
*:::::So, if you review the first sentence of SYNTH, you'll see it has no special relevance to this discussion: {{Tq|Do not combine material from multiple sources to state or imply a conclusion not explicitly stated by any of the sources.}}. My primary example has been a picture of a person; what a person looks like is verifiable by comparing the image to non-free images that cannot be used on Misplaced Pages. If the image resembles the person, it is not SYNTH. An illustration of a person created and intended to look like that person is not a manipulation. The training data used to make the AI is irrelevant to whether the image in fact resembles the person. You should also review ] because SYNTH is not a policy; NOR is the policy: {{tq|If a putative SYNTH doesn't constitute original research, then it doesn't constitute SYNTH.}} Additionally, ]. A categorical rule against AI cannot be justified by SYNTH because it does not categorically apply to all use cases of AI. To do so would be illogical on top of ill-advised. ] (]) 08:08, 2 January 2025 (UTC)
*::::::"training data used to make the AI is irrelevant" — spoken like a true AI evangelist! Sorry, 'good enough' photorealism is still just synthetic slop, a fake image presented as real of a ''human being''. A fake image of someone generated from who-knows-what that 'resembles' an article's subject is about as ] as it gets. Yikes. As for the attempts to pass of prompt-generated photorealistic fakes of people as somehow the same as someone's illustration, you're completely wasting your time. ] (]) 09:44, 2 January 2025 (UTC)
*:::::::NOR is a content policy and SYNTH is content guidance within NOR. Because you have admitted that this is not ''about the content'' for you, NOR and SYNTH are irrelevant to your argument, which boils down to ] and, now, inaccurate personal attacks. Continuing this discussion between us would be pointless. ] (]) 09:52, 2 January 2025 (UTC)
*::::::::This is in fact entirely about content (why the hell else would I bother?) but it is true that I also dismissed your pro-AI 'it's just like a human drawing a picture!' as outright nonsense a while back. Good luck convincing anyone else with that line - it didn't work here. ] (]) 09:59, 2 January 2025 (UTC)
*'''Maybe''': there is an implicit assumption with this RFC that an AI generated image would be photorealistic. There hasn't been any discussion of an AI generated sketch. If you asked an AI to generate a sketch (that clearly looked like a sketch, similar to the Gisèle Pelicot example) then I would potentially be ok with it. ] (]) 18:14, 1 January 2025 (UTC)
*:That's an interesting thought to consider. At the same time, I worry about (well-intentioned) editors inundating image-less BLP articles with AI-generated images in the style of cartoons/sketches (if only photorealistic ones are prohibited) etc. At least requiring a human to draw/paint/whatever creates a barrier to entry; these AI-generated images can be created in under a minute using these text-to-image models. Editors are already wary about human-created cartoon portraits (]), now they'll be tasked with dealing with AI-generated ones in BLP articles. ] (]) 20:28, 1 January 2025 (UTC)
*::It sounds like your problem is not with AI but with cartoon/sketch images in BLP articles, so AI is once again completely irrelevant. ] (]) 22:14, 1 January 2025 (UTC)
*::That is a good concern you brought up. There is a possibility of the spamming of low quality AI-generated images which would be laborious to discuss on a case-by-case basis but easy to generate. At the same time though that is a possibility, but not yet an actuality, and ] states that new policies should address current problems rather than hypothetical concerns. ] (]) 22:16, 1 January 2025 (UTC)
*Easy '''no''' for me. I am not against the use of AI images wholesale, but I do think that using AI to represent an existent thing such as a person or a place is too far. Even a tag wouldn't be enough for me. ] </nowiki></span>''']] 19:05, 1 January 2025 (UTC)
*'''No''' obviously, per previous discussions about cartoonish drawn images in BLPs. Same issue here as there, it is essentially original research and misrepresentation of a living person's likeness. ] (]) 22:19, 1 January 2025 (UTC)
*'''No''' to photorealistic, no to cartoonish... this is not a hard choice. The idea that "this has nothing to do with AI" when "AI" magnifies the problem to stupendous proportions is just not tenable. ] (]) 23:36, 1 January 2025 (UTC)
*:While AI might "amplify" the thing you dislike, that does not make AI the problem. The problem is whatever underlying thing is being amplified. ] (]) 01:16, 2 January 2025 (UTC)
*::The thing that amplifies the problem is necessarily a problem. ] (]) 02:57, 2 January 2025 (UTC)
*:::That is arguable, but banning the amplifier does not do anything to solve the problem. In this case, banning the amplifier would cause multiple other problems that nobody supporting this proposal as even attempted to address, let alone mitigate. ] (]) 03:04, 2 January 2025 (UTC)
*'''No''' for all people, per Chaotic Enby. ] (]) 03:23, 2 January 2025 (UTC) Add: no to any AI-generated images, whether photorealistic or not. ] (]) 04:00, 3 January 2025 (UTC)
*'''No''' - We should not be hosting faked images (except as notable fakes). We should also not be hosting copyvios ({{tq|"Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant"}} is just totally wrong - we should be steering clear of copyvios, and if the issue is unsettled then we shouldn't use them until it is).
*If people upload faked images to WP or Commons the response should be as it is now. The fact that fakes are becoming harder to detect simply from looking at them hardly affects this - we simply confirm when the picture was supposed to have been taken and examine the plausibility of it from there. ] (]) 14:39, 2 January 2025 (UTC) ] (]) 14:39, 2 January 2025 (UTC)
*:{{tpq|we should be steering clear of copyvio}} we do - if an image is a copyright violation it gets deleted, regardless of why it is a copyright violation. What we do not do is ban using images that are not copyright violations because they are copyright violations. Currently the WMF lawyers and all the people on Commons who know more about copyright than I do say that at least some AI images are legally acceptable for us to host and use. If you want to argue that, then go ahead, but it is not relevant to ''this'' discussion.
*:{{tpq|if people upload faked images the response should be as it is now}} in other words you are saying that the problem is faked images not AI, and that current policies are entirely adequate to deal with the problem of faked images. So we don't need any specific rules for AI images - especially given that not all AI images are fakes. ] (]) 15:14, 2 January 2025 (UTC)
*::The idea that {{tq|current policies are entirely adequate}} is like saying that a lab shouldn't have specific rules about wearing eye protection when it already has a poster hanging on the wall that says "don't hurt yourself". ] (]) 18:36, 2 January 2025 (UTC)
*:::I rely on one of those up in my workshop at home. I figure if that doesn't keep me safe, nothing will. ] (]) 18:41, 2 January 2025 (UTC)
*::::"{{tq|in other words you are saying that the problem is faked images not AI}}" - AI generated images *are* fakes. This is merely confirming that for the avoidance of doubt.
*::::"{{tq|at least some AI images are legally acceptable for us}}" - Until they decide which ones that isn't much help. ] (]) 19:05, 2 January 2025 (UTC)
*:::::Yes – what FOARP said. AI-generated images are fakes and are misleading. '']'' (] — ]) 19:15, 2 January 2025 (UTC)
*:::Those specific rules exist because generic warnings have proven not to be sufficient. Nobody has presented any evidence that the current policies are not sufficient, indeed quite the contrary. ] (]) 19:05, 2 January 2025 (UTC)
*'''No!''' This would be a massive can of worms; perhaps, however, we wish to cause problems in the new year. ] <small>(]) | :) | he/him | </small> 15:00, 2 January 2025 (UTC)
*:Noting that I think that no AI-generated images are acceptable in BLP articles, regardless of whether they are photorealistic or not. ] <small>(]) | :) | he/him | </small> 15:40, 3 January 2025 (UTC)
*'''No''', unless the AI image has encyclopedic significance beyond "depicts a notable person". AI images, if created by editors for the purpose of inclusion in Misplaced Pages, convey little reliable information about the person they depict, and the ways in which the model works are opaque enough to most people as to raise verifiability concerns. ] (] • ]) 15:25, 2 January 2025 (UTC)
*:To clarify, do you object to uses of an AI image in a BLP when the subject uses that image for self-identification? I presume that AI images that have been the subject of notable discussion are an example of "significance beyond depict a notable person"? ] (]) 15:54, 2 January 2025 (UTC)
*::If the subject uses the image for self-identification, I'd be fine with it - I think that'd be analogous to situations such as "cartoonist represented by a stylized self-portrait", which definitely has some precedent in articles like ]. I agree with your second sentence as well; if there's notable discussion around a particular AI image, I think it would be reasonable to include that image on Misplaced Pages. ] (] • ]) 19:13, 2 January 2025 (UTC)
* '''No''', with obvious exceptions, including if the subject theyrself uses the image as a their representation, or if the image is notable itself. Not including the lack of a free aleternative, if there is no free alternative... where did the AI find data to build an image... non free too. Not including images generated by WP editors (that's kind of ]... - ] (]) 18:02, 2 January 2025 (UTC
*'''Maybe''' I think the question is unfair as it is illustrated with what appears to be a photo of the subject but isn't. People are then getting upset that they've been misled. As others note, there are copyright concerns with AI reproducing copyrighted works that in turn make an image that is potentially legally unusable. But that is more a matter for Commons than for Misplaced Pages. As many have noted, a sketch or painting never claims to be an accurate depiction of a person, and I don't care if that sketch or painting was done by hand or an AI prompt. I strongly ask ] to abort the RFC. You've asked people to give a yes/no vote to what is a more complex issue. A further problem with the example used is the unfortunate prejudice on Misplaced Pages against user-generated content. While the text-generated AI of today is crude and random, there will come a point where many professionally published photos illustrating subjects, including people, are AI generated. Even today, your smartphone can create a groupshot where everyone is smiling and looking at the camera. It was "trained" on the 50 images it quickly took and responded to the build-in "text prompt" of "create a montage of these photos such that everyone is smiling and looking at the camera". This vote is a knee jerk reaction to content that is best addressed by some other measure (such as that it is a misleading image). And a good example of asking people to vote way too early, when the issues haven't been throught out -- ]°] 18:17, 2 January 2025 (UTC)
*'''No''' This would very likely set a dangerous precedent. The only exception I think should be if the image itself is notable. If we move forward with AI images, especially for BLPs, it would only open up a whole slew of regulations and RfCs to keep them in check. Better no image than some digital multiverse version of someone that is "basically" them but not really. Not to mention the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet. ] (]) 18:31, 2 January 2025 (UTC)
*'''No'''. LLMs don't generate answers, they generate ''things that look like'' answers, but aren't; a lot of the time, that's good enough, but sometimes it very much isn't. It's the same issue for text-to-image models: they don't generate photos of people, they generate ''things that look like'' photos. Using them on BLPs is unacceptable. ] (]) 19:30, 2 January 2025 (UTC)
*'''No'''. I would be pissed if the top picture of me on Google was AI-generated. I just don't think it's moral for living people. The exceptions given above by others are okay, such as if the subject uses the picture themselves or if the picture is notable (with context given). ] (]) 19:56, 2 January 2025 (UTC)
*'''No.''' Uploading alone, although mostly a Commons issue, would already a problem to me and may have personality rights issues. Illustrating an article with a fake photo <ins>(or drawing)</ins> of a living person, even if it is labeled as such, would not be acceptable. For example, it could end up being shown by search engines or when hovering over a Misplaced Pages link, without the disclaimer. ] (]) 23:54, 2 January 2025 (UTC)
* I was going to say no... but we allow paintings as portraits in BLPs. What's so different between an AI generated image, and a painting? Arguments above say the depiction may not be accurate, but the same is true of some paintings, right? (and conversely, not true of other paintings) ] (]) 00:48, 3 January 2025 (UTC)
*::A painting is clearly a painting; as such, the viewer knows that it is not an accurate representation of a particular reality. An AI-generated image made to look exactly like a photo, looks like a photo but is not.
*:] (]) 02:44, 3 January 2025 (UTC)
*::Not all paintings are clearly paintings. Not all AI-generated images are made to look like photographs. Not all AI-generated images made to look like photos do actually look like photos. This proposal makes no distinction. ] (]) 02:55, 3 January 2025 (UTC)
*:::Not to mention, hyper-realism is a style an artist may use in virtually any medium. If Misplaced Pages would accept an analog substitute like a painting, there's no reason Misplaced Pages shouldn't accept an equivalent painting made with digital tools, and there's no reason Misplaced Pages shouldn't accept an equivalent painting made with AI. That is, one where any obvious defects have been edited out and what remains is a straightforward picture of the subject. ] (]) 03:45, 3 January 2025 (UTC)
*::::For the record (and for any media watching), while I personally find it fascinating that a few editors here are spending a substantial amount of time (in the face of an overwhelming 'absolutely not' consensus no less) attempting to convince others that computer-generated (that is, ''faked'') photos of human article subjects are somehow ''a good thing'', I also find it interesting that these editors seem to express absolutely no concern for the intensely negative reaction they're already seeing from their fellow editors and seem totally unconcerned about the inevitable trust drop we'd experience from Misplaced Pages readers when they would encounter fake photos on our BLP articles especially. ] (]) 03:54, 3 January 2025 (UTC)
*:::::Misplaced Pages's reputation would not be affected positively or negatively by expanding the current-albeit-sparse use of illustrations to depict subjects that do not have available pictures. In all my writing about this over the last few days, you are the only one who has said anything negative about me as a person or, really, my arguments themselves. As loath as I am to cite it, ] means assuming that people you disagree with are not ''trying to hurt Misplaced Pages.'' Thryduulf, I, and others have explained in detail why we think our ultimate ideas are explicit benefits to Misplaced Pages and why our opposition to these immediate proposals comes from a desire to prevent harm to Misplaced Pages. I suggest taking a break to reflect on that, matey. ] (]) 04:09, 3 January 2025 (UTC)
*::::::Look, I don't know if you've been living under a rock or what for the past few years but the reality is that '' people hate AI images'' and dumping a ton of AI/fake images on Misplaced Pages, a place people go for ''real information'' and often ''trust'', inevitably leads to a huge trust issue, something Misplaced Pages is increasingly suffering from already. This is ''especially'' a problem when they're intended to represent ''living people'' (!). I'll leave it to you to dig up the bazillion controversies that have arisen and continue to arise since companies worldwide have discovered that they can now replace human artists with 'AI art' produced by "prompt engineers" but you can't possibly expect us to ignore that reality when discussing these matters. ] (]) 04:55, 3 January 2025 (UTC)
*:::::::Those trust issues are born from the publication of hallucinated information. I have only said that it should be OK to use an image on Misplaced Pages when it contains only verifiable information, which is the same standard we apply to text. That standard is and ought to be applied independently of the way the initial version of an image was created. ] (]) 06:10, 3 January 2025 (UTC)
*:To my eye, the distinction between AI images and paintings here is less a question of medium and more of verifiability: the paintings we use (or at least the ones I can remember) are significant paintings that have been acknowledged in sources as being reasonable representations of a given person. By contrast, a purpose-generated AI image would be more akin to me painting a portrait of somebody here and now and trying to stick that on their article. The image could be a faithful representation <small>(unlikely, given my lack of painting skills, but let's not get lost in the metaphor)</small>, but if my painting hasn't been discussed anywhere besides Misplaced Pages, then it's potentially OR or UNDUE to enshrine it in mainspace as an encyclopedic image. ] (] • ]) 05:57, 3 January 2025 (UTC)
*::An image contains a collection of facts, and those facts need to be verifiable just like any other information posted on Misplaced Pages. An image that verifiably resembles a subject as it is depicted in reliable sources is categorically ''not OR''. Discussion in other sources is not universally relevant; we don't restrict ourselves to only previously-published images. If we did that, Misplaced Pages would have very few images. ] (]) 06:18, 3 January 2025 (UTC)
*:::Verifiable how? Only by the editor themselves comparing to a real photo (which was probably used by the LLM to create the image…).
*:::These things are fakes. The analysis stops there. ] (]) 10:48, 4 January 2025 (UTC)
*::::Verifiable by comparing them to a reliable source. Exactly the same as what we do with text. There is no coherent reason to treat user-generated images differently than user-generated text, and the universalist tenor of this discussion has damaging implications for all user-generated images regardless of whether they were created with AI. Honestly, I rarely make arguments like this one, but I think it could show some intuition from another perspective: Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures. The text editors say the artists cannot contribute ANYTHING to Misplaced Pages because their images that have not been previously published are not verifiable. That is a double-standard that privileges the contributions of text-editors simply because most users are text-editors and they are used to verifying text; that is not a principled reason to treat text and images differently. Moreover, that is simply not what happened—The opposite happend, and images are treated as verifiable based on their contents just like text because that's a common sense reading of the rule. It would have been madness if images had been treated differently. And yet that is essentially the fundamentalist position of people who are extending their opposition to AI with arguments that apply to all images. If they are arguing verifiability seriously at all, they are pretending that the sort of degenerate situation I just described already exists when the opposite consensus has been reached consistently ''for years''. In ], they even tried to say Wikipedians had "turned a blind eye" to these image issues as if negatively characterizing those decisions would invalidate the fact that ''those decisions were consensus.'' The motivated reasoning of these discussions has been as blatant as that.<br/>At the bottom of this dispute, I take issue with trying to alter the rules in a way that creates a new double-standard within verifiability that applies to all images but not text. That's especially upsetting when (despite my and others' best efforts) so many of us are still focusing ''SOLELY'' on their hatred for AI rather than considering the obvious second-order consequences for user-generated images as a whole.<br/>Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake." The issue has always been ''verifiability'', not provenance or falsity. Sometimes, IMO, that has lead to disaster and Misplaced Pages saying things I know to be factually untrue despite the contents of reliable sources. But ''that'' is the policy. We compare the contents of Misplaced Pages to reliable sources, and the contents of Misplaced Pages are considered verifiable if they cohere.<br/>I ask again: If Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? If our negative response to AI tools is to ''limit what humans can do on Misplaced Pages'', what does that say? Are we taking a stand for human achievements, or is this a very heated discussion of cutting off our nose to save our face? ] (]) 23:31, 4 January 2025 (UTC)
*:::::{{tq|"Verifiable by comparing them to a reliable source"}} - comparing two images and saying that one ''looks like'' the other is not "verifying" anything. The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.
*:::::{{tq|"Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake.""}} - Try presenting a paraphrasing as a quotation and see what happens.
*:::::{{tq|"Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures..."}} - This basically happened, and is the origin of ]. Misplaced Pages is not a host for original works. ] (]) 22:01, 6 January 2025 (UTC)
*::::::{{tq|Comparing two images and saying that one looks like the other is not "verifying" anything.}} Comparing text to text in a reliable source is literally the same thing.
*::::::{{tq|The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.}} No it isn't. The text equivalent is writing a sentence in an article and putting a ref tag on it. Perhaps there is room for improving the referencing of images in the sense that they should offer example comparisons to make. But an image created by a person is not unverifiable simply because it is user-generated. It is not somehow ''more'' unverifiable simply because it is created in a lifelike style.
*::::::{{tq|Try presenting a paraphrasing as a quotation and see what happens.}} Besides what I just said, ''nobody'' is even presenting these images as equatable to quotations. People in this thread have simply been calling them "fake" of their own initiative; the uploaders have not asserted that these are literal photographs to my knowledge. The uploaders of illustrations obviously did not make that claim either. (And, if the contents of the image is a copyvio, that is a separate issue entirely.)
*::::::{{tq|This basically happened, and is the origin of WP:NOTGALLERY.}} That is not the same thing. User-generated images that illustrate the subject are not prohibited by ]. Misplaced Pages is a host of encyclopedic content, and user-generated images can have encyclopedic content. ] (]) 02:41, 7 January 2025 (UTC)
*:::::::Images are way more complex than text. Trying to compare them in the same way is a very dangerous simplification. '']'' (] — ]) 02:44, 7 January 2025 (UTC)
*::::::::Assume only non-free images exist of a person. An illustrator refers to those non-free images and produces a painting. From that painting, you see a person who looks like the person in the non-free photographs. The image is verified as resembling the person. That is a simplification, but to call it "dangerous" is disingenuous at best. The process for challenging the image is clear. Someone who wants to challenge the veracity of the image would just need to point to details that do not align. For instance, "he does not typically have blue hair" or "he does not have a scar." That is what we already do, and it does not come up much because it would be weird to deliberately draw an image that looks nothing like the person. Additionally, someone who does not like the image for aesthetic reasons rather than encyclopedic ones always has the option of sourcing a photograph some other way like permission, fair use, or taking a new one themself. This is not an intractable problem. ] (]) 02:57, 7 January 2025 (UTC)
*:::::::::So a photorealistic AI-generated image would be considered acceptable until someone identifies a "big enough" difference? How is that anything close to ethical? An portrait that's got an extra mole or slightly wider nose bridge or lacks a scar is still ''not an image of the person'' regardless of whether random Misplaced Pages editors notice. And while I don't think user-generated non-photorealistic images should ever be used on biographies either, at least those can be traced back to a human who is ultimately responsible for the depiction, who can point to the particular non-free images they used as references, and isn't liable to average out details across all time periods of the subject. And that's not even taking into account the copyright issues. ] (]) 22:52, 7 January 2025 (UTC)
*::::::::::{{+1}} to what JoelleJay said. The problem is that AI-generated images are simulations trying to match existing images, sometimes, yes, with an impressive degree of accuracy. But they will always be inferior to a human-drawn painting that's ''trying to depict the person''. We're a human encyclopedia, and we're built by humans doing human things and sometimes with human errors. '']'' (] — ]) 23:18, 7 January 2025 (UTC)
*::::::::::You can't just raise this to an "ethical" issue by saying the word "ethical." You also can't just invoke copyright without articulating an actual copyright issue; we are not discussing copyvio. Everyone agrees that a photo with an actual copyvio in it is subject to that policy.
*::::::::::But to address your actual point: Any image—any ''photo''—beneath the resolution necessary to depict the mole would be missing the mole. Even with photography, we are never talking about science-fiction images that perfectly depict every facet of a person in an objective sense. We are talking about equipment that creates an approximation of reality. The same is true of illustrations and AI imagery.
*::::::::::Finally, a human being ''is'' responsible for the contents of the image because a human is selecting it and is responsible for correcting any errors. The result is an image that someone is choosing to use because they believe it is an appropriate likeness. We should acknowledge that human decision and evaluate it naturally—''Is it an appropriate likeness?'' ] (]) 10:20, 8 January 2025 (UTC)
*:::::::::::(Second comment because I'm on my phone.) I realize I should also respond to this in terms of additive information. What people look like is not static in the way your comment implies. Is it inappropriate to use a photo because they had a zit on the day it was taken? Not necessarily. Is an image inappropriate because it is taken at a bad angle that makes them look fat? Judging by the prolific ComicCon photographs (where people seem to make a game of choosing the worst-looking options; seriously, it's really bad), not necessarily. Scars and bruises exist and then often heal over time. The standard for whether an image with "extra" details is acceptable would still be based on whether it comports acceptably with other images; we literally do what you have capriciously described as "unethical" and supplement it with our compassionate desire to not deliberately embarrass BLPs. (The ComicCon images aside, I guess.) So, no, I would not be a fan of using images that add prominent scars where the subject is not generally known to have one, but that is just an unverifiable fact that does not belong in a Misplaced Pages image. Simple as. ] (]) 10:32, 8 January 2025 (UTC)
*:::::We don't evaluate the reliability of a source solely by comparing it to other sources. For example, there is an ongoing discussion at the baseball WikiProject talk page about the reliability of a certain web site. It lists no authors nor any information on its editorial control policy, so we're not able to evaluate its reliability. The reliability of all content being used as a source, including images, needs to be considered in terms of its provenance. ] (]) 23:11, 7 January 2025 (UTC)
* Can you note in your !vote whether AI-generated images (generated via text prompts/text-to-image models) that are ''not'' photo-realistic / hyper-realistic in style are okay to use to depict BLP subjects? For example, see the image to the right, which was ] then ] from his article: ] by ]]] {{pb}} Pinging people who !voted No above: ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ], ] --- ] (]) 03:55, 3 January 2025 (UTC) {{clear}}
*:Still no, I thought I was clear on that but we should not be using AI-generated images in articles for anything besides representing the concept of AI-generated images, or if an AI-generated image is notable or irreplaceable in its own right -- e.g, a musician uses AI to make an album cover.
*:(this isn't even a good example, it looks more like ])
*:] (]) 04:07, 3 January 2025 (UTC)
*:Was I unclear? ''No'' to all of them. ] (]) 04:13, 3 January 2025 (UTC)
*:Still '''no''', because carving out that type of exception will just lead to arguments down the line about whether a given image is too realistic. <span class="nowrap">—] (] | ])</span> 04:24, 3 January 2025 (UTC)
*:I still think '''no'''. My opposition isn't just to the fact that AI images are misinformation, but also that they essentially serve as a loophole for getting around Enwiki's image use policy. To know what somebody looks like, an AI generator needs to have images of that person in its dataset, and it draws on those images to generate a derivative work. If we have no free images of somebody and we use AI to make one, that's just using a fair use copyrighted image but removed by one step. The image use policy prohibits us from using fair use images for BLPs so I don't think we should entertain this loophole. If we ''do'' end up allowing AI images in BLPs, that just disqualifies the rationale of not allowing fair use in the first place. ] (]) 04:40, 3 January 2025 (UTC)
*:'''No''' those are not okay, as this will just cause arguments from people saying a picture is ''obviously'' AI-generated, and that it is therefore appropriate. As I mentionned above, there are some exceptions to this, which Gnomingstuff perfectly describes. Fake sketches/cartoons are not appropriate and provide little encyclopedic value. ] (]) 05:27, 3 January 2025 (UTC)
*:'''No''' to this as well, with the same carveout for individual images that have received notable discussion. Non-photorealistic AI images are going to be no more verifiable than photorealistic ones, and on top of that will often be lower-quality as images. ] (] • ]) 05:44, 3 January 2025 (UTC)
*:Thanks for the ping, yes I can, the answer is no. ] (]) 07:31, 3 January 2025 (UTC)
*:'''No''', and that image should be deleted before anyone places it into a mainspace article. Changing the RfC intro long after its inception seems a second bite at an apple that's not aged well. ] (]) 09:28, 3 January 2025 (UTC)
*::The RfC question has not been changed; another editor was the RfC question did not make a distinction between photorealistic/non-photorealistic AI-generated images, so I had to add and ping the editors who'd voted !No to clarify things. It has only been 3 days; there's still 27 more days to go. ] (]) 11:18, 3 January 2025 (UTC)
*:::Also answering '''No''' to this one per all the arguments above. "It has only been 3 days" is not a good reason to change the RfC question, especially since many people have already !voted and the "30 days" is mostly indicative rather than an actual deadline for a RfC. ] (] · ]) 14:52, 3 January 2025 (UTC)
*::::The RfC question hasn't been changed; see my response to Zaathras below. ] (]) 15:42, 3 January 2025 (UTC)
*:No, that's even a worse possible approach.<span id="Masem:1735910695864:WikipediaFTTCLNVillage_pump_(policy)" class="FTTCmt"> — ] (]) 13:24, 3 January 2025 (UTC)</span>
*:'''No'''. We're the human encyclopedia. We should have images drawn or taken by real humans who are trying to depict the ''subject'', not by machines trying to simulate an image. Besides, the given example is horribly drawn. '']'' (] — ]) 15:03, 3 January 2025 (UTC)
*:I like these even less than the photorealistic ones... This falls into the same basket for me: if we wouldn't let a random editor who drew this at home using conventional tools add it to the article why would we let a random editor who drew this at home using AI tools at it to the article? (and just to be clear the AI generated image of Germán Larrea Mota-Velasco is not recognizable as such) ] (]) 16:06, 3 January 2025 (UTC)
*:I said *NO*. ] (]) 10:37, 4 January 2025 (UTC)
*:'''No''' Having such images as said above means the AI had to use copyrighted pictures to create it and we shouldn't use it. --] (]) 01:12, 5 January 2025 (UTC)
*:Still '''no'''. If for no other reason than that it's a bad precedent. As others have said, if we make one exception, it will just lead to arguments in the future about whether something is "realistic" or not. I also don't see why we would need cartoon/illustrated-looking AI pictures of people in BLPs. ] (]) 20:43, 6 January 2025 (UTC)
*'''Absolutely not'''. These images are based on whatever the AI could find on the internet, with little to no regard for copyright. Misplaced Pages is better than this. ] (]) 10:16, 3 January 2025 (UTC)
*'''Comment''' The RfC question should not have been fiddled with, esp. for such a minor argument that the complai9nmant could have simply included in their own vote. I have no need to re-confirm my own entry. ] (]) 14:33, 3 January 2025 (UTC)
*:The RfC question hasn't been modified; I've only added a clarifying that these images can either be photorealistic in style or non-photorealistic in style. I pinged all the !No voters to make them aware. I could remove the Note if people prefer that I do (but the original RfC question is the ''exact same'' as it is now, so I don't think the addition of the Note makes a whole ton of difference). ] (]) 15:29, 3 January 2025 (UTC)
*'''No''' At this point it feels redundant, but I'll just add to the horde of responses in the negative. I don't think we can fully appreciate the issues that this would cause. The potential problems and headaches far outweigh whatever little benefit might come from AI images for BLPs. ]] 21:34, 3 January 2025 (UTC)
*'''Support temporary blanket ban''' with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. ] (]) 23:01, 3 January 2025 (UTC)
*'''No'''. Misplaced Pages is made ''by'' and ''for'' humans. I don't want to become . Adding an AI-generated image to a page whose topic isn't about generative AI makes me feel insulted. ] (]) 00:03, 4 January 2025 (UTC)
*'''No'''. Generative AI may have its place, and it may even have a place on Misplaced Pages in some form, but that place isn't in BLPs. There's no reason to use images of someone that do not exist over a real picture, or even something like a sketch, drawing, or painting. Even in the absence of pictures or human-drawn/painted images, I don't support using AI-generated images; they're not really pictures of the person, after all, so I can't support using them on articles of people. Using nothing would genuinely be a better choice than generated images. ] <span style="font-weight:bold">|</span> ] 01:07, 4 January 2025 (UTC)
*'''No''' due to reasons of copyright (AI harvests copyrighted material) and verifiability. ] <small>(])</small> 18:12, 4 January 2025 (UTC)
*'''No.''' Even if you are willing to ignore the inherently fraught nature of using AI-generated ''anything'' in relation to BLP subjects, there is simply little to no benefit that could possibly come from trying something like this. There's no guarantee the images will actually look like the person in question, and therefore there's no actual context or information that the image is providing the reader. What a baffling proposal. ] (]) 19:53, 4 January 2025 (UTC)
*:{{tpq|There's no guarantee the images will actually look like the person in question}} there is no guarantee ''any'' image will look like the person in question. When an image is not a good likeness, regardless of why, we don't use it. When am image is a good likeness we consider using it. Whether an image is AI-generated or not it is completely independent of whether it is a good likeness. There are also reason other then identification why images are used on BLP-articles. ] (]) 20:39, 4 January 2025 (UTC)
*Foreseeably there may come a time when people's official portraits are AI-enhanced. That time might not be very far in the future. Do we want an exception for official portraits?—] <small>]/]</small> 01:17, 5 January 2025 (UTC)
*:This subsection is about purely AI-generated works, not about AI-enhanced ones. ] (] · ]) 01:23, 5 January 2025 (UTC)
*'''No.''' Per Cremastra, "We should have images drawn or taken by real humans who are trying to depict the ''subject''," - ] (]) 02:12, 5 January 2025 (UTC)
*'''Yes''', depending on specific case. One can use drawings by artists, even such as ]. The latter is an intentional distortion, one could say an intentional misinformation. Still, such images are legitimate on many pages. Or consider numerous images of ]. How realiable are they? I am not saying we must deliberatly use AI images on all pages, but they may be fine in some cases. Now, speaking on "medical articles"... One might actually use the AI generated images of certain biological objects like proteins or organelles. Of course a qualified editorial judgement is always needed to decide if they would improve a specific page (frequently they would not), but making a blanket ban would be unacceptable, in my opinion. For example, the images of protein models generatated by ] would be fine. The AI-generated images of biological membranes I saw? I would say no. It depends. ] (]) 02:50, 5 January 2025 (UTC) {{pb
}}This is complicated of course. For example, there are tools that make an image of a person that (mis)represents him as someone much better and clever than he really is in life. That should be forbidden as an advertisement. This is a whole new world, but I do not think that a blanket rejection would be appropriate. ] (]) 03:19, 5 January 2025 (UTC)
* '''No''', I think there's legal and ethical issues here, especially with the current state of AI. ] ] 03:38, 5 January 2025 (UTC)
*'''No''': Obviously, we shouldn't be using AI images to represent anyone. ] (]) 05:31, 5 January 2025 (UTC)
*'''No''' Too risky for BLP's. Besides if people want AI generated content over editor made content, we should make it clear they are in the wrong place, and readers should be given no doubt as to our integrity, sincerity and effort to give them our best, not a program's. ] (]) 14:51, 5 January 2025 (UTC)
*'''No''', as AI's grasp on the Internet takes hold stronger and stronger, it's important Misplaced Pages, as the online encyclopedia it sets out to be, remains factual and real. Using AI images on Wiki would likely do more harm than good, further thinning the boundaries between what's real and what's not. – ''']''' <sub>(]) (])</sub> 16:52, 5 January 2025 (UTC)
*'''No''', not at the moment. I think it will hard to avoid portraits that been enhanced by AI, as it already been on-going for a number of years and there is no way to avoid it, but I don't want arbitary generated AI portraits of any type. '''<span style="text-shadow:7px 7px 8px black; font-family:Papyrus">]<sup>]</sup></span>''' 20:19, 5 January 2025 (UTC)
*'''No for natural images (e.g. photos of people)'''. Generative AI by itself is not a reliable source for facts. In principle, generating images of people and directly sticking them in articles is no different than generating text and directly sticking it in articles. In practice, however, generating images is worse: Text can at least be discussed, edited, and improved afterwards. In contrast, we have significantly less policy and fewer rigorous methods of discussing how AI-generated images of natural objects should be improved (e.g. "make his face slightly more oblong, it's not close enough yet"). Discussion will devolve into hunches and gut feelings about the fidelity of images, all of which essentially fall under WP:OR. ] (]) 20:37, 5 January 2025 (UTC)
*'''No''' I'm appalled that even a small minority of editors would support such an idea. We have enough credibility issues already; using AI-generated images to represent real people is not something that a real encyclopedia should even consider. ] (]) 22:26, 5 January 2025 (UTC)
*'''No''' I understand the comparison to using illustrations in BLP articles, but I've always viewed that as less preferable to no picture in all honestly. Images of a person are typically presented in context, such as a performer on stage, or a politician's official portrait, and I feel like there would be too many edge cases to consider in terms of making it clear that the photo is AI generated and isn't representative of anything that the person specifically did, but is rather an approximation. ] (]) 06:50, 6 January 2025 (UTC)
*'''No''' - Too often the images resemble caricatures. Real caricatures may be included in articles if the caricature (e.g., political cartoon) had ] and is attributed to the artist. Otherwise, representations of living persons should be real representations taken with photographic equipment. ] (]) 02:31, 7 January 2025 (UTC)
*:So you will be arguing for the removal of the lead images at ], ], etc. then? ] (]) 06:10, 7 January 2025 (UTC)
*::At this point you're making bad-faith "BY YOUR LOGIC" arguments. You're better than that. Don't do it. ] (]) 19:18, 7 January 2025 (UTC)
*'''Strong no''' per bloodofox. —] (]'''-''']) 03:32, 7 January 2025 (UTC)
:'''No''' for AI-generated BLP images ] (]) 21:40, 7 January 2025 (UTC)
2. Before creating a "References in Popular Culture" section, ask yourself: Is it useful? Does it make the article more or less encyclopedic?
*'''No''' - Not only is this effectively guesswork that usually includes unnatural artefacts, but worse, it is also based on unattributed work of photographers who didn't release their work into public domain. I don't care if it is an open legal loophole somewhere, IMO even doing away with the fair use restriction on BLPs would be morally less wrong. I suspect people on whose work LLMs in question were trained would also take less offense to that option. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 23:25, 7 January 2025 (UTC)
*'''No''' – ] says that {{tq|Non-free content should not be used when a freely licensed file that serves the same purpose can reasonably be expected to be uploaded, as is the case for almost all portraits of living people.}} While AI images may not be considered copyrightable, it still be a copyright violation if the output resembles other, copyrighted images, pushing the image towards NFC. At the very least, I feel the use of non-free content to generate AI images violates the spirit of the NFC policy. (I'm assuming copyrighted images of a person are used to generate an AI portrait of them; if free images of that person were used, we should just use those images, and if ''no'' images of the person were used, how on Earth would we trust the output?) ] (]) 02:43, 8 January 2025 (UTC)
*'''No''', AI images should not be permitted on Misplaced Pages at all. ] (]) 11:27, 8 January 2025 (UTC)
{{Archive bottom}}
===Expiration date?===
3. If you really must have a "References in Popular Culture" section, then a guiding principle should be: ''"if X is less famous than Y, then references to Y by X are by definition not very interesting"''. Only references by people or things ''more'' interesting are notable. A reference to a well-known person or event by an obscure band does not qualify. A reference to a lesser-known person or event by a popular band (e.g. the song about the ] by ] comes to mind) does qualify.
"AI," as the term is currently used, is very new. It feels like large language models and the type of image generators under discussion just got here in 2024. (Yes, I know it was a little earlier.) The culture hasn't completed its initial response to them yet. Right now, these images do more harm than good, but that may change. Either we'll come up with a better way of spotting hallucinations or the machines will hallucinate less. Their copyright status also seems unstable. I suggest that any ban decided upon here have some expiration date or required rediscussion date. Two years feels about right to me, but the important thing would be that the ban has a number on it. ] (]) 23:01, 3 January 2025 (UTC)
*No need for any end-date. If there comes a point where consensus on this changes, then we can change any ban then. ] (]) 05:27, 5 January 2025 (UTC)
*An end date is a positive suggestion. Consensus systems like Misplaced Pages's are vulnerable to half-baked precedential decisions being treated as inviolate. With respect, this conversation does not inspire confidence that this policy proposal's consequences are well-understood at this time. If Misplaced Pages goes in this direction, it should be labeled as primarily reactionary and open to review at a later date. ] (]) 10:22, 5 January 2025 (UTC)
*Agree with FOARP, '''no need for an end date'''. If something significantly changes (e.g. reliable sources/news outlets such as the ''New York Times'', BBC, AP, etc. start using text-to-image models to generate images of living people for their own articles) then this topic can be revisited later. Editors will have to go through the usual process of starting a new discussion/proposal when that time comes. ] (]) 11:39, 5 January 2025 (UTC)
*:Seeing as this discussion has not touched at all on what other organizations may or may not do, it would not be accurate to describe any consensus derived from this conversation in terms of what other organizations may or may not be doing. That is, there has been no consensus that we ought to be looking to the New York Times as an example. Doing so would be inadvisable for several reasons. For one, they have sued an AI company over semi-related issues and they have teams explicitly working on what the future of AI in news ought to look like, so they have some investment in what the future of AI looks like and they are explicitly trying to shape its norms. For another, if they did start to use AI in a way that may be controversial, they would have no positive reason to disclose that and many disincentives. They are not a neutral signal on this issue. Misplaced Pages should decide for itself, preferably doing so while not disrupting the ability of people to continue creating user-generated images. ] (]) 03:07, 6 January 2025 (UTC)
* ] on an indefinite basis, if something changes. An arbitrary sunset date doesn't seem much use. ] (]) 03:15, 6 January 2025 (UTC)
* No need per others. Additionally, if practices change, it doesn't mean editors will decide to follow new practices. As for the technology, it seems the situation has been fairly stable for the past two years: we can detect some fakes and hallucinations immediately, many more in the past, but certainly not all retouched elements and all generated photos available right now, even if there was a readily accessible tool or app that enabled ordinary people to reliably do so.
:Through the history, art forgeries have been fairly reliably detected, but rarely quickly. Relatedly, I don't see why the situation with AI images would change in the next 24 months or any similar time period. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 22:17, 9 January 2025 (UTC)
==Non-Admin XFD Close as Delete==
4. A little more leeway exists for things which exist mainly in popular culture anyway. So the "References in Popular Culture" section is generally more appropriate for a TV show than for a politician.
There is a contentious ] currently resulting from a ] of a ] in which the closer found that the consensus was Delete. The closer then tagged the redirect with ], in particular {{tl|db-xfd}}. It was then deleted by an admin who had taken part in the deletion discussion. The guideline on non-administrative closes says that a non-administrative close of Delete is not permitted, because the closer cannot press the Delete button. The first question at ] seems to be whether DRV '''''must''''' vacate the close and allow a new close by an ] administrator, or whether DRV can endorse the close and leave the close standing. My opinion is that a DRV endorsement of a non-admin close is as good a close as a regular admin close, but that is only my opinion.
The second question that is raised by the DRV discussion is about the existing practice that non-admins sometimes make Delete closes at ]. Should this practice be stopped, because the guideline says that non-admins may not make Delete closes, or should the guideline be revised, or should the guideline be left as is, but with such closes being sometimes allowed? My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at ], but that is only my opinion.
Should ] be able to endorse the irregular non-admin close, or is it necessary for DRV to vacate the close? Also, should the non-admin closer be thanked, or cautioned?
] (]) 06:51, 31 December 2024 (UTC)
:On the first question, I think that whatever decision DRV makes at ] will be 'legal'. They are not required to vacate the close, no matter how much one editor might like to have a second bite at that apple.
p.s. If there is a policy page already where this is discussed, or where it should be discussed, could someone please direct me to it. Thanks. ] 07:21, 12 April 2007 (UTC)
:On your second question, I prefer the existing rules. It is not necessary to allow NACs (]) of 'delete'. Good admins will not blindly trust anyone else's decision, so a NAC to delete does not necessarily save any time, and if the admin disagrees, then it could cause drama. NACs to delete should be gently but firmly discouraged. ] (]) 07:30, 31 December 2024 (UTC)
:I especially like idea #3. I find it incredibly annoying that about 90% of all 'popular culture' sections link to ], just because much of its method of humor is to play off semi-obscure references for laughs. By the way, you probably want to look at ], where whole articles have been devoted to this subject, though supposedly only for "iconic" works.--] 08:04, 12 April 2007 (UTC)
::I agree with WAID. ] (]) 10:29, 31 December 2024 (UTC)
*That's procedurally irregular, but it was the correct close of the discussion and we've got to the right outcome.—] <small>]/]</small> 11:32, 31 December 2024 (UTC)
* As I said at the Deletion Review, I support non-admins closing RfDs as Delete. If TfDs have been made an exception, RfDs can be too. Closing a heavily discussed nomination at RfD is more about the reading, analysis and thought process at arriving at the outcome, and less about the technicality of the subsequent page actions. It will help making non-admins mentally prepared to advance to admin roles.<span style="font-family:Segoe Script">]</span><span style="font-size:115%">]</span> 17:28, 1 January 2025 (UTC)
:It seems dumb to think that a close can go through DRV and 'pass' only for it to be vacated because the closer didn't have the right credentials. If the close is found to be good, does it matter who closed it? If bad Delete closes by non-admins were regular occurrences, then maybe, but I don't imagine this is the case. ] </nowiki></span>''']] 19:12, 1 January 2025 (UTC)
*The only problem is that if it becomes a regular occurrence, it creates more work overall. An admin can delete and carry out the delete. A non-admin can say it needs to be deleted, but still needs an admin to carry out the delete. That's why this should be discouraged - if it becomes commonplace it will generate a lot more work, but a one-off can clearly be endorsed at DRV. ] ''<span style="font-size:small; vertical-align:top;">]</span>''·''<span style="font-size:small; vertical-align:bottom;">]</span>'' 19:26, 1 January 2025 (UTC)
*:I think it's time for the long-standing "it creates more work" argument to be retired. In the first scenario, person 1 does A and B. In the second scenario, person 1 does A and person 2 does B. That does not create more work overall, it's the same amount of work overall, and it ''reduces'' work for person 1. Splitting work between two people doesn't create more work. ] (]) 14:55, 4 January 2025 (UTC)
*::If person 2 here did B without doing any additional work whatsoever, then person 2 shouldn't be able to do B. We expect admins to ''look'' at what they're deleting. Plus, you're creating additional work for persons 3-20, who are watching ] and don't appreciate demands to go sanity-check low-urgency, possibly-complex closes at unfamiliar deletion venues mixed into the copyright infringement, spam, and attack pages they're trying to prioritize. —] 15:15, 4 January 2025 (UTC)
===Discussion of How Much Attention Admins Pay to What They Are Deleting===
*:::No, we don't expect admins to look at what they're deleting. Anyone familiar with the admin deletion stats (as you are) knows that every day, admins delete many pages without ever looking at them. Person 2 can do B without A. It's OK for person 2 to rely on person 1 to do A correctly. It's not true that in order for person 2 to do B then person 2 must also have done A, and it's not how we operate with other deletions. Non-admins are perfectly capable of closing RfCs and many other discussions; there is nothing about a deletion discussion that suddenly makes non-admins unable to summarize consensus. There is no reason an admin can't rely on a non-admins summary of consensus, just as admins rely on non-admins CSD tagging. ] (]) 15:21, 4 January 2025 (UTC)
*:::: We absolutely <em>do</em> expect admins to look at what they're deleting. At most a NAC delete close can save an admin the trouble of writing the close themself, but if an admin is blindly deleting without verifying that the CSD tag is actually valid for CSD then sooner or later they're going to wind up at ]. ]] 15:49, 4 January 2025 (UTC)
*::::{{u|Levivich}}, I agree with your conclusion, but not with your analogy. As {{u|Anomie}} pointed out, we do not blindly delete pages tagged as CSD. ] specifically instructs us to verify that the page meets a speedy deletion criterion, rather than just appeared as such to one user. This is a very different situation to an AfD that garnered consensus among multiple editors over the course of at least seven days, where the admin's job is just to verify that the NAC read consensus correctly. ] ] 16:01, 4 January 2025 (UTC)
*:::::We can say it all we want but we can't argue with ]. The admin who has deleted over 1 million pages did not read 1 million pages. Nor did the admin who deleted 800,000 pages read 800,000 pages. An admin who has deleted 600,000 pages--no doubt without reading even half of them--just got elected to arbcom. Nobody is taking those admins to ANI or thinks they're doing anything wrong (including me).
*:::::So no, admins don't read the pages they delete, and no, we don't expect them to, as proven by the massive number of deletions, and no, admins who delete without reading aren't taken to ANI, they're promoted. This includes CSDs.
*:::::More broadly, there is no reason not to allow admins to rely on non-admin XfD closures when making deletion decisions. We already do this for multiple types of XfDs, we can and should do it for AfDs. ] (]) 16:05, 4 January 2025 (UTC)
*::::::{{u|Explicit}} didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD. He had to review almost a million XfD discussions to make sure consensus was to delete, which is exactly what he does when closing. And the majority of CSD deletions are of clumsy, unsourced self-promotion pages that take less than ten seconds to assess and confirm as such. I know for a fact that {{u|Liz}} -- number #3 on that list -- carefully reviews every speedy-tagged page before deleting it, and routinely rejects such requests when they do not meet CSD. {{pb}} {{u|Levivich}}, you are making some serious accusations here, with zero evidence to support them. I don't think this will help your case here. ] ] 16:24, 4 January 2025 (UTC)
*:::::::I have no case here and I'm making no accusations. If you want to believe that a person has read over a million XfDs, you go ahead and believe that. I don't, because even over 15 years, that would be 182 XfDs a day every day with no days off, and I don't believe anyone does, or is capable of doing, that much XfD reading. ] (]) 17:03, 4 January 2025 (UTC)
*:::::::: {{u|Levivich}} You're completely wrong, because you're missing a number of very obvious issues with those statistics.
*::::::::: Not even a majority of Explicit's deletions are XfDs - most are speedies
*::::::::: Many are G13 deletions, which don't need any analysis, they're simply done on timeframe. You can do those in seconds. Similarly U1, R2 and F8
*::::::::: Most articles have a talk page, which also needs to be deleted (G8), so deleting most articles means two deletions.
*::::::::: RfDs don't take very long to close at all; most are unanimous
*::::::::: Of Explicit's last 500 deletions, only 58 have been XfDs (and their associated talk pages where they existed, making 97 deletions).
*::::::::: The vast majority of the rest have been G13, G8, U1, R2 and F8.
*:::::::: Just in the interests of accuracy, you know. ] 17:18, 4 January 2025 (UTC)
*:::::::::Owen: {{tqq|Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD}}
*:::::::::BK: {{tqq|Not even a majority of Explicit's deletions are XfDs - most are speedies}}
*:::::::::I don't know which one of you is wrong but it doesn't matter. Explicit did not read 1 million pages over the last 15 years prior to deleting them, whether they were XfDs or CSDs. Nobody is reading 182 Misplaced Pages pages 7 days a week for 15 years. Nobody has read a million Misplaced Pages pages. No human can thoroughly review 182 things a day. It's mathematics, guys. If a person spends 5 minutes on each review -- which isn't a thorough review of anything -- that's 15 hours per day to do 182 reviews. Nobody is spending that much time, 7 days a week, for 15 years. Even if the person spends just 1 minute, that's over 3 hours a day... every day for 15 years. The math proves that Explicit is spending maybe 1 minute per deletion.
*:::::::::Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.
*:::::::::The math and the stats don't lie. The suggestion that admins carefully review every page before deleting them is plainly not true. The suggestion that if admins didn't do that, they'd be taken to ANI, is also plainly not true. We have admins spending a minute or less per deletion and not being taken to ANI. These are facts. ] (]) 19:31, 4 January 2025 (UTC)
*:::::::::: Your "math" is based on a lot of faulty assumptions and oversimplifications, which you seem to be persisting in despite others trying to correct you. ]] 20:42, 4 January 2025 (UTC)
*:::::::::: Those are ''not'' facts, because your data is faulty. Your reply simply tells me that you didn't read what I wrote. Someone with the editing pattern of Explicit ''isn't'' reviewing 182 things a day. Nowhere near that. Quite apart from the talk page issue (which, if every page had a talk page, would immediately halve the number of reviews) in some of the speedy categories I mention there's nothing ''to'' review; it's simply pressing a button. Indeed, deleting the articles in the stale G13 queue, orphaned G8 queue, or the F5 or F8 category, can result in dozens - even hundreds - of deletions in one button press. As an example, on the 3rd January alone, Explicit deleted 113 F8 images, plus 83 talk pages of those images. That's 196 deletions, all done in a few seconds, as there's nothing to review. In comparison, the number of XfDs he closed that day was 25. ] 21:21, 4 January 2025 (UTC)
*:::::::::::Cryptic: {{tqq|We expect admins to ''look'' at what they're deleting.}}
*:::::::::::BK: {{tqq|That's 196 deletions, all done in a few seconds, as there's nothing to review.}}
*:::::::::::I disagreed with Cryptic's point, and thank you BK for providing an example of exactly what I'm talking about. We do not expect admins to review (or "''look'' at") what they're deleting, sometimes there's not even anything to look at. Admins delete things without reviewing what they're deleting all the time, and they're not hauled off to ANI for it. BK, you're arguing with me, but you're not actually disagreeing with what I'm saying. You're not arguing, as others have said above, that all admins review everything they delete before they delete it, or that this is the community expectation. ] (]) 22:24, 4 January 2025 (UTC)
*:::::::::::: I'm simply pointing out that the claim you have made {{tq|The math proves that Explicit is spending maybe 1 minute per deletion. Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.}} is not correct; Explicit is not spending 1 minute per XfD, he is spending 1 minute per ''deletion'', and because in many cases the admin pressing the button is simply completing an automated process (in the case of G13, that the article has not been edited for six months; in the case of F8, that the identical file exists at Commons), and deleting many files in one button-press, that skews the data. Now, if you are saying that an admin is ''closing AfDs or deleting G7 or G11 speedies at a high rate'' (not just "deleting things"), and their speed suggests they aren't reviewing them carefully - ''then'' you have a point. ] 23:33, 4 January 2025 (UTC)
*:::::::::::::Not actually reviewing deletions to make sure they were correct was one of the two major factors that resulted in Arbcom desysopping ] (the other was a refusal to engage with good-faith queries about his actions and refusing to engage at all with IP editors). As others have said, how long it takes to ensure that what you are deleting should be deleted varies considerably. For G13s it's as simple as checking that bot has correctly determined that a given timestamp was more than 6 months ago - either the entire batch will be correct or the entire batch will be incorrect. Most of the deletions I do are the result of RfDs, after determining that the consensus is to delete (which is usually very simple) I delete the page. The software then tells me that page has a talk page, at least 9 times out of 10 (maybe more) it takes less than a second to verify there isn't any any reason they are G8 exempt. There is no excuse for not doing the reviewing properly though because there ''are'' exceptions. ] (]) 00:22, 5 January 2025 (UTC)
*:::::::::::::I didn't say Explicit is spending 1 minute per XfD, I said "per deletion." And your point about "many files in one button-press" is literally the same as my point, which is that admins ''don't'' carefully review every single thing they delete, they sometimes delete many files in one button press (196 deletions in a few seconds is an example). So, you agree with me that "we expect admins to look at what they're deleting" is not correct, it's actually disproven by the data. ] (]) 00:37, 5 January 2025 (UTC)
*::::::::::::::Admins ''are'' expected to review everything they delete. It's just that in some cases many pages can be reviewed together very quickly. It is also possible to spend time carefully reviewing many pages in detail, assembling a list of which should be deleted and then deleting them the pages on that together with a single click. ] (]) 01:08, 5 January 2025 (UTC)
*::::::::::::::It was in the context of XfDs, however ("{{tq|If you want to believe that a person has read over a million XfDs, you go ahead and believe that}}"). ] 08:03, 5 January 2025 (UTC)
*:::::::::::::::That was in response to someone saying they were mostly XfDs. The same point holds if they were mostly CSDs. That's why I said it doesn't matter whether they were mostly XfDs or CSDs. Regardless of whether it's XfD or CSD, when someone makes 500k or 1 million deletions, we know they didn't look at each and every individual thing (page, file, whatever) that was deleted, nor do we expect them to. (Which I said in response to people saying we expect admins to look at every single thing they delete.) ] (]) 13:18, 5 January 2025 (UTC)
*:::::By pressing the delete button you are asserting that at least one of the following is true:
*:::::*The page met the specified speedy deletion criterion (e.g. if the deletion log says G12 you are asserting the page, including all of its old revisions, was copyvio).
*:::::*The page was eligible for PROD, this was the first time that it was prodded and nobody has objected to the prod.
*:::::*The deletion of the page was discussed a the relevant XfD (or, exceptionally, in an RfC) and that the consensus of that discussion was to delete the page.
*:::::If an admin is not prepared to put their name to the truthfulness of that assertion then they should not be deleting the page. ] (]) 16:12, 4 January 2025 (UTC)
*{{tq|My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion|quotes=y}} - actually, {{u|Robert McClenon}}, your opinion is solidly anchored in policy. ] tells us: {{tq|the written rules themselves do not set accepted practice. Rather, they document already-existing community consensus regarding what should be accepted and what should be rejected.}} If CfD is working fine as it is, let's update policy to reflect the practice. ] ] 16:09, 2 January 2025 (UTC)
*Regarding the ], the guideline on non-admin "delete" closures is at ] and explicitly includes exceptions for TfD and CfD, so there isn't currently a conflict between existing practice and deletion guidelines. ] ] 08:00, 9 January 2025 (UTC)
==Unregistered Editors in Project Space==
Something to this effect can be found at ]. ]]/] 08:08, 12 April 2007 (UTC)
Is there a guideline that says that unregistered editors (IP addresses) should not edit in Misplaced Pages space (project space)? We had am ] discussion in which an unregistered editor asked a registered editor to nominate an essay for deletion. The registered editor did as requested, which I think is known as proxying. As I understand, unregistered editors cannot create new pages in either article space or project space, and an AFD or MFD discussion is its own page. The MFD was then closed as a ], because no rationale was given. The question has to do with a comment made by one of the MFD regular editors that IP editors should not edit in project space. Another editor questioned whether there was a guideline to that effect. I cannot recall having seen a guideline that restricts or discourages unregistered editors from editing in project space. Is there such a guideline? ] (]) 00:39, 1 January 2025 (UTC)
:No. IP editors regularly participate in project space. ] (]/]) 00:43, 1 January 2025 (UTC)
== Please contribute to... ==
:No, and anyone who claims there is can be safely disregarded as full of shit. (Not that it's the first time that people confidently claim false authority.) ] (]) 08:11, 1 January 2025 (UTC)
:Adding to the chorus, no. Unregistered users are explicitly instructed to do this in ] (same for AfD, etc.) – ] <small>(])</small> 08:22, 1 January 2025 (UTC)
::Thank you. Three ] were then in order. One to the unregistered editor, for not giving a reason for the deletion request. Two to the registered editor who was proxying, for making an MFD nomination without stating a reason. Three to the editor who said that IPs should stay out of project space. I think that the third editor would have had a case to argue that policy should be changed and the English Misplaced Pages should follow the Portuguese example of not permitting IP editing, but that is only my opinion and is an unrelated issue. ] (]) 16:30, 1 January 2025 (UTC)
:::{{smalldiv|1=That's six trouts!{{jokes}} ] (]) 17:06, 1 January 2025 (UTC)}}
:::::<small>Second breakfast.</small> ] (]) 00:42, 2 January 2025 (UTC)
:::Ptwiki permits IP editors everywhere except the mainspace. See the . ] (]) 07:51, 3 January 2025 (UTC)
== Should ] include mention of AI-generated comments? ==
]. ] 15:47, 12 April 2007 (UTC)
:Double redirect.
:Bad, bad thing.
:Fix it right now please.
:] ] 15:51, 12 April 2007 (UTC)
::Don't you mean "Bad bad bad bad bad bad thing"? --] 15:54, 12 April 2007 (UTC)
:::Sjakkalle does not,
:::Know a thing about haikus.
:::You are quite right friend.
:::] ] 15:56, 12 April 2007 (UTC)
Using AI to write your comments in a discussion makes it difficult for others to assume that you are discussing in good faith, rather than trying to use AI to argue someone into exhaustion (see example of someone using AI in their replies ). More fundamentally, ] can't apply to the AI itself as AI lacks intentionality, and it is difficult for editors to assess how much of an AI-generated comment reflects the training of the AI vs. the actual thoughts of the editor.
== ] being un-wiki? ==
Should ] be addended to include that using AI to generate your replies in a discussion runs counter to demonstrating good faith? ] (]) 00:23, 2 January 2025 (UTC)
Some time ago, the old bot approval process was deprecated and replaced with a highly bureaucratic system. It is made up of self-nomed admins get to decide whether your bot will be beneficial to Misplaced Pages or not- on their own whim. Any one of these administrators can reject your request if they feel like it or not. This is highly un-wiki, as other users (such as those who edit the affected topic) can give little input. If you are looking at this right now and want to give your $0.02, please do so at ], where there are more details about the situation. ''']''' <sup><font color="black">]</font> · <font color="blue">]</font></sup> 21:30, 12 April 2007 (UTC)
:] is an open process, they want community input, they sometimes drag out the approval process waiting for more community input. I can clearly state why the bot was not approved. When the request was placed approval was for a task that had no community consensus behind it, there is no MoS guideline, or current practice. it was stated that ''7 editors at one WikiProject'' is a consensus. BAG and the rest of the community don't see that as consensus. Please tell me if im mistaken on what consensus is. The second request was for approval for the exact same task as another bot, see ] for the most part bots(task) are not cloned without reason. Why have 2 bots do the EXACT same task? that is why that bot was denied. And as for framework my bot is BAG approved and uses both pywikipedia and AWB. BAG does a great job for what the task is. BAG is a group of users who know what bots are, how they work and how they need controlled. Misplaced Pages has set up a system where people who know what they are doing can monitor the issues with bots. ] <sup>(] • ] • ])</sup> 01:53, 13 April 2007 (UTC)
* '''Yes''', I think this is a good idea. ] (]) 00:39, 2 January 2025 (UTC)
:I looked through the bot requests and I don't see anything improper. Many of the requested tasks could be accomplished by just asking one of the other bot operators to run a job for you. One of the requests was denied because no bot flag is needed to take the requested action. Another one of the requests asked for an edit rate of 40 edits per min, suggesting the person making the request is not familiar with the standard practices. ] · <small>]</small> 02:12, 13 April 2007 (UTC)
:'''No'''. As with all the other concurrent discussions (how many times do we actually need to discuss the exact same FUD and scaremongering?) the problem is not AI, but rather inappropriate use of AI. What we need to do is to (better) explain what we actually want to see in discussions, not vaguely defined bans of swathes of technology that, used properly, can aid communication. ] (]) 01:23, 2 January 2025 (UTC)
:(Being a BAG member) I personally welcome as much community input as possible in to every Bot request, and have specifically asked operators to link their requests to related projects, or link to where consensus has been made on a project. Some bot requests are slam-dunk quick approvals (e.g. interwiki bots) but some require much thaught. While bots can be reverted like any other editor, the community has been pretty clear that some edits just shouldn't happen by a bot (the perenial WelcomeNewUserBot request comes to mind). Changes to the bot policy are of course possible, and if the community wants something new, we should start up a discussion at the bot policy talk page. — ] <sup>]</sup> 02:20, 13 April 2007 (UTC)
::Note that this topic is discussing using AI to ''generate'' replies, as opposed to using it as an aid (e.g. asking it to edit for grammar, or conciseness). As the above concurrent discussion demonstrates, users are already using AI to generate their replies in AfD, so it isn't scaremongering but an actual issue.
::] also does not ban anything ("Showing good faith is not required"), but offers general advice on demonstrating good faith. So it seems like the most relevant place to include mention of the community's concerns regarding AI-generated comments, without outright banning anything. ] (]) 01:32, 2 January 2025 (UTC)
:This user is becoming very problematic. When he doesn't get his own way he rants and moans and, in his earlier dealings with Mets501, was close to getting civility warnings (hence my rather acerbic closure of that request). He demonstrates no technical expertise but frankly displays a great deal of immaturity. Is it any surprise he doesn't get approved? If at all possible, I should prefer not to give him a bot flag ''at all'' until he has matured somewhat.
:::And as pointed out, multiple times in those discussions, different people understand different things from the phrase "AI-generated". The community's concern is not AI-generated comments, but comments that do not clearly and constructively contribute to a discussion - ''some'' such comments are AI-generated, some are not. This proposal would, just as all the other related ones, cause actual harm when editors falsely accuse others of using AI (and this ''will'' happen). ] (]) 02:34, 2 January 2025 (UTC)
::::Nobody signed up to argue with bots here. If you're pasting someone else's comment into a prompt and asking the chatbot to argue against that comment and just posting it in here, that's a real problema and absolutely should not be acceptable. ] (]) 03:31, 2 January 2025 (UTC)
:::::Thank you for the assumption of bad faith and demonstrating one of my points about the harm caused. Nobody is forcing you to engage with bad-faith comments, but whether something is or is not bad faith needs to be determined by its content not by its method of generation. Simply using an AI demonstrates neither good faith nor bad faith. ] (]) 04:36, 2 January 2025 (UTC)
:::::I don't see why we have any particular to reason to suspect a respected and trustworthy editor of using AI. '']'' (] — ]) 14:31, 2 January 2025 (UTC)
::::I'm one of those people who clarified the difference between AI-generated vs. edited, and such a difference could be made explicit with a note. Editors are already accusing others of using AI. Could you clarify how you think addressing AI in ] would cause actual harm? ] (]) 04:29, 2 January 2025 (UTC)
:::::By encouraging editors to accuse others of using AI, by encouraging editors to dismiss or ignore comments because they suspect that they are AI-generated rather than engaging with them. @] has already encouraged others to ignore my arguments in this discussion because they suspect I might be using an LLM and/or be a bot (for the record I'm neither). ] (]) 04:33, 2 January 2025 (UTC)
::::::I think {{u|bloodofox}}'s ] was about "you" in the rhetorical sense, not "you" as in Thryduulf. ] (]) 11:06, 2 January 2025 (UTC)
:::::Given your relentlessly pro-AI comments here, it seems that you'd be A-OK with just chatting with a group of chatbots here — or leaving the discussion to them. However, most of us clearly are not. In fact, I would immediately tell someone to get lost were it confirmed that indeed that is what is happening. I'm a human being and find the notion of wasting my time with chatbots on Misplaced Pages to be incredibly insulting and offensive. ] (]) 04:38, 2 January 2025 (UTC)
::::::My comments are neither pro-AI nor anti-AI, indeed it seems that you have not understood pretty much anything I'm saying. ] (]) 04:43, 2 January 2025 (UTC)
:::::::Funny, you've done nothing here but argue for more generative AI on the site and now you seem to be arguing to let chatbots run rampant on it while mocking anyone who doesn't want to interface with chatbots on Misplaced Pages. Hey, why not just sell the site to Meta, am I right? ] (]) 04:53, 2 January 2025 (UTC)
::::::::I haven't been arguing for more generative AI on the site. I've been arguing against banning it on the grounds that such a ban would be unclear, unenforceable, wouldn't solve any problems (largely because whether something is AI or not is completely irrelevant to the matter at hand) but would instead cause harm. Some of the issues identified are actual problems, but AI is not the cause of them and banning AI won't fix them.
::::::::I'm not mocking anybody, nor am I advocating to {{tpq|let chatbots run rampant}}. I'm utterly confused why you think I might advocate for selling Misplaced Pages to Meta (or anyone else for that matter)? Are you actually reading anything I'm writing? You clearly are not understanding it. ] (]) 05:01, 2 January 2025 (UTC)
:::::::::So we're now in 'everyone else is the problem, not me!' territory now? Perhaps try communicating in a different way because your responses here are looking very much like the typical AI apologetics one can encounter on just about any contemporary LinkedIn thread from your typical FAANG employee. ] (]) 05:13, 2 January 2025 (UTC)
::::::::::No, this is not a {{tpq|everyone else is the problem, not me}} issue because most other people appear to be able to understand my arguments and respond to them appropriately. Not everybody agrees with them, but that's not an issue.
::::::::::I'm not familiar with Linkedin threads (I don't use that platform) nor what a "FAANG employee" is (I've literally never heard the term before now) so I have no idea whether your characterisation is a compliment or a personal attack, but given your comments towards me and others you disagree with elsewhere I suspect it's closer to the latter.
::::::::::AI is a tool. Just like any other tool it can be used in good faith or in bad faith, it can be used well and it can be used badly, it can be used in appropriate situations and it can be used in inappropriate situations, the results of using the tool can be good and the results of using the tool can be bad. Banning the tool inevitably bans the good results as well as the bad results but doesn't address the reasons why the results were good or bad and so does not resolve the actual issue that led to the bad outcomes. ] (]) 12:09, 2 January 2025 (UTC)
:::::::::::In the context of generating comments to other users though, AI is much easier to use for bad faith than for good faith. LLMs don't understand Misplaced Pages's policies and norms, and so are hard to utilize to generate posts that productively address them. By contrast, bad actors can easily use LLMs to make low quality posts to waste people's time or wear them down.
:::::::::::In the context of generating images, or text for articles, it's easy to see how the vast majority of users using AI for those purposes is acting in good faith as these are generally constructive tasks, and most people making bad faith changes to articles are either obvious vandals who won't bother to use AI because they'll be reverted soon anyways, or trying to be subtle (povpushers) in which case they tend to want to carefully write their own text into the article.
:::::::::::It's true that AI "is just a tool", but when that tool is much easier to use for bad faith purposes (in the context of discussions) then it raises suspicions about why people are using it. ] (]) 22:44, 2 January 2025 (UTC)
:'''Not really''' – I agree with Thryduulf's arguments on this one. Using AI to help tweak or summarize or "enhance" replies is of course not bad faith – the person is trying hard. Maybe English is their second language. Even for replies 100% AI-generated the user may be an ESL speaker struggling to remember the right words (I always forget 90% of my French vocabulary when writing anything in French, for example). In this case, I don't think we should make a ''blanket'' assumption that using AI to generate comments is not showing good faith. '']'' (] — ]) 02:35, 2 January 2025 (UTC)
:Where a user has the necessary attitude, the process can be very quick. See ]. Useful bot, clear brief, exceptionally polite user, approved with hardly a problem. --] 11:53, 13 April 2007 (UTC)
*'''Yes''' because generating walls of text is not good faith. People "touching up" their comments is also bad (for starters, if you lack the English competency to write your statements in the first place, you probably lack the competency to tell if your meaning has been preserved or not). Exactly ''what'' AGF should say needs work, but something needs to be said, and <s>AGF</s>DGF is a good place to do it. ] (]) 02:56, 2 January 2025 (UTC)
::I'll echo Kingbok's words - when a bot is using a tried and tested structure to do a simple task (like interwiki), then we approve with the minimum of fuss. A number of my approvals in the past fortnight went through the process in less than 24 hours. It is with the other bots that bwe have to be careful, and we are charged with the task of protecting Misplaced Pages from thousands of bad bot edits. Vishwin has been in converstain with me on IRC about some of his bot tasks, but has not once there expressed his apparent concern to me, so one gets the feeling that this is a response to the recent denial of one of his bot tasks, which was denied as it was for Wikiproject '''assessing''' - something which should be attributed to a user to show that some automatic process isn't doing the assessments. By all means, if Vishwin60 wanted to put another task in which was simple Wikiproject tagging, the BAG would consider it without prejudice, though we could well decide to ask him to allow an already approved bot (ReedyBot for example) do the task for him. Vishwin60's other task - newslettr delivery - is coming close to approval once one or two problems are ironed out. I should note that as Vishwin's assessment task was deemed not to require a flag, he's free to do it without BAG approval (as it isn't needed for his particular task, as expressed on the talk page of it). The BAG is not made up of "self nommed admins", in both senses of the phrase - an election procedure much like that used by ] takes place, in which anyone is free to chip in. Bot approvals are always subject to appeal and oversight, in the form of the resubmission of a previous request.
*:Not all walls of text are generated by AI, not all AI generated comments are walls of text. Not everybody who uses AI to touch up their comments lacks the competencies you describe, not everybody who does lack those competencies uses AI. It is not always possible to tell which comments have been generated by AI and which have not. This proposal is not particularly relevant to the problems you describe. ] (]) 03:01, 2 January 2025 (UTC)
::I'd just like to explore a couple of the cases brought up on ]. On the case of the Reflist task - there was no '''community''' consensus for the change, and in fact many issues were brought up when the issue was brought to the spotlight by Mets501 on one of the village pumps. Due to this lack of consensus and no clear prior discussion, the BAG was policy-bound to deny the request (no prejudice to re-application). On the case of the newsletter task - as I understand it, ], without bots, split up the rather long list of newsletter subscribers between three members, manually using AWB. Suddenly, BAG recieved two requests for bot approval from two of the users who carr yout this task, the requests being posted within 4 days of eachother. Now, although the subscription list, at about 100 long, is lengthy for manual delivery, it is a breeze for a bot, so despite the fact that Mets501 had already given Rschen's bot a trial, I denied it, on the basis that Mets was on a Wikibreak, so unlikely to be able to respond soon, and after off-wiki discussion with other BAG members, by way of a sanity check. To make it abundantly clear to avoid any sort of bad-feeling - I only denied Rschen's bot because it's request for approval was put in after Vishwin's. There are a number of technical reasons why one would not want to have two bots running on the same task at the same time - most notably that a problem can be harder to track down, and having only one user doing the task gives the WikiProject more continuity and provides editors with just one person to contact when problems arise, rather than having to find two. Rschen is free to leave a message at ] if ever he wants a second opinion. Finally, I would encourage as many editors as possible to get involved at BRFA - at the moment we have 2 or 3 regular non BAGers there, and we would really like more to come over and help us! Thanks, <strong>]<font color="red">]</font></strong> 12:46, 13 April 2007 (UTC)
:::Someone has to ask: Are you generating all of these pro-AI arguments using ChatGPT? It'd explain a lot. If so, I'll happily ignore any and all of your contributions, and I'd advise anyone else to do the same. We're not here to be flooded with LLM-derived responses. ] (]) 03:27, 2 January 2025 (UTC)
::::That you can't tell whether my comments are AI-generated or not is one of the fundamental problems with these proposals. For the record they aren't, nor are they pro-AI - they're simply anti throwing out babies with bathwater. ] (]) 04:25, 2 January 2025 (UTC)
:::::I'd say it also illustrates the serious danger: We can no longer be sure that we're even talking to other people here, which is probably the most notable shift in the history of Misplaced Pages. ] (]) 04:34, 2 January 2025 (UTC)
::::::How is that a "serious danger"? If a comment makes a good point, why does it matter whether ti was AI generated or not? If it doesn't make a good point, why does it matter if it was AI generated or not? How will these proposals resolve that "danger"? How will they be enforceable? ] (]) 04:39, 2 January 2025 (UTC)
:::::::Misplaced Pages is made for people, by people, and I like most people will be incredibly offended to find that we're just playing some kind of LLM pong with a chatbot of your choice. You can't be serious. ] (]) 04:40, 2 January 2025 (UTC)
::::::::You are entitled to that philosophy, but that doesn't actually answer any of my questions. ] (]) 04:45, 2 January 2025 (UTC)
:::::::"why does it matter if it was AI generated or not?"
:::::::Because it takes little effort to post a lengthy, low quality AI-generated post, and a lot of effort for human editors to write up replies debunking them.
:::::::"How will they be enforceable? "
:::::::] isn't meant to be enforced. It's meant to explain to people how they can demonstrate good faith. Posting replies to people (who took the time to write them) that are obviously AI-generated harms the ability of those people to assume good faith. ] (]) 05:16, 2 January 2025 (UTC)
:The linked "example of someone using AI in their replies" appears – to me – to be a non-AI-generated comment. I think I preferred the allegedly AI-generated comments from that user (]). The AI was at least superficially polite. ] (]) 04:27, 2 January 2025 (UTC)
::Obviously the person screaming in all caps that they use AI because they don't want to waste their time arguing is not using AI for that comment. Their first post calls for the article to be deleted for not "" and "merely" reiterating what other sources have written.
::Yes, after a human had wasted their time explaining all the things wrong with its first post, then the bot was able to write a second post which ''looks'' ok. Except it only superficially ''looks'' ok, it doesn't actually accurately describe the articles. ] (]) 04:59, 2 January 2025 (UTC)
:In other wikimedia projects, bots aren't approved by technicians. But it's not a good thing, sadly. BAG members are capable technician who knows better that any of us what harm bot can do to wikipedia. In fact, one of 'em is even a developer. The fact of being admin is, I think, only customary, as I don't think it's required to be on the BAG. Also, I have to point out that this process isn't highly bureaucratic: usually it's quite quick.
:::Multiple humans have demonstrated in these discussions that humans are equally capable of writing posts which superficially ''look'' OK but don't actually accurately relate to anything they are responding to. ] (]) 05:03, 2 January 2025 (UTC)
::::But I can assume that everyone here is acting in good faith. I can't assume good faith in the globally-locked sock puppet spamming AfD discussions with low effort posts, whose bot is just saying whatever it can to argue for the deletion of political pages the editor doesn't like. ] (]) 05:09, 2 January 2025 (UTC)
:::::True, but I think that has more to do with the "globally-locked sock puppet spamming AfD discussions" part than with the "some of it might be " part. ] (]) 07:54, 2 January 2025 (UTC)
::::::All of which was discovered because of my suspicions from their inhuman, and meaningless replies. "Reiteration isn't the problem; redundancy is," maybe sounds pithy in a vacuum, but this was written in reply to me stating that we aren't supposed to be doing OR but reiterating what the sources say.
::::::"Your criticism feels overly prescriptive, as though you're evaluating this as an academic essay" also ''sounds good'', until you realize that the bot is actually criticizing its own original post.
::::::The fact that my suspicions about their good faith were ultimately validated only makes it even harder for me to assume good faith in users who sound like ChatGPT. ] (]) 08:33, 2 January 2025 (UTC)
:::::::I wonder if we need some other language here. I can understand feeling like this is a bad interaction. There's no sense that the person cares; there's no feeling like this is a true interaction. A contract lawyer would say that there's no ], and there can't be, because there's no mind in the AI, and the human copying from the AI doesn't seem to be interested in engaging their brain.
:::::::But... do you actually think they're doing this for the purpose of ''intentionally'' harming Misplaced Pages? Or could this be explained by other motivations? ] – or to anxiety, insecurity (will they hate me if I get my grammar wrong?), incompetence, negligence, or any number of other "understandable" (but still something ]- and even block-worthy) reasons. ] (]) 08:49, 2 January 2025 (UTC)
::::::::The ] has a header at the top asking people not to template them because it is "impersonal and disrespectful", instead requesting "please take a moment to write a comment below '''in your own words'''"
::::::::Does this look like acting in good faith to you? Requesting other people write personalized responses to them while they respond with an LLM? Because it looks to me like they are trying to waste other people's time. ] (]) 09:35, 2 January 2025 (UTC)
:::::::::] means that you assume people aren't deliberately screwing up on purpose. Humans are self-contradictory creatures. I generally do assume that someone who is being hypocritical hasn't noticed their contradictions yet. ] (]) 07:54, 3 January 2025 (UTC)
::::::::::"Being hypocritical" in the abstract isn't the problem, it's the fact that asking people to put effort into their comments, while putting in minimal effort into your own comments appears bad faith, especially when said person says they don't want to waste time writing comments to stupid people. The fact you are arguing AGF for this person is both astounding and disappointing. ] (]) 16:08, 3 January 2025 (UTC)
:::::::::::It feels like there is a lack of reciprocity in the interaction, even leaving aside the concern that the account is a block-evading sock.
:::::::::::But I wonder if you have read AGF recently. The first sentence is "'''Assuming good faith''' ('''AGF''') means assuming that people are not deliberately ''trying'' to hurt Misplaced Pages, even when their actions are harmful."
:::::::::::So we've got some of this (e.g., harmful actions). But do you really believe this person woke up in the morning and decided "My main goal for today is to deliberately hurt Misplaced Pages. I might not be successful, but I sure am going to try hard to reach my goal"? ] (]) 23:17, 4 January 2025 (UTC)
::::::::::::Trying to hurt Misplaced Pages doesn't mean they have to literally think "I am trying to hurt Misplaced Pages", it can mean a range of things, such as "I am trying to troll Wikipedians". A person who thinks a cabal of editors is guarding an article page, and that they need to harass them off the site, may think they are improving Misplaced Pages, but at the least I wouldn't say that they are acting in good faith. ] (]) 23:27, 4 January 2025 (UTC)
:::::::::::::Sure, I'd count that as a case of "trying to hurt Misplaced Pages-the-community". ] (]) 06:10, 5 January 2025 (UTC)
* The issues with AI in discussions is not related to good faith, which is narrowly defined to intent. ] (]) 04:45, 2 January 2025 (UTC)
:About the "same task" issue: I don't think that this is the proper page, maybe it's better to discuss it in the talk page of the Bot request for approval, anyway, as I have pointed out in the discussion about your bot, 40 edits/minutes, it's really fast. For a non essential task, this edit rate isn't allowed. Also, two bots that do the same thing, which at 5 edits per minute can be done in no more that twenty minutes, aren't necessary.
*:In my mind, they are related inasmuch as it is much more difficult for me to ascertain good faith if the words are eminently not written by the person I am speaking to in large part, but instead generated based on an unknown prompt in what is likely a small fraction of the expected time. To be frank, in many situations it is difficult to avoid the conclusion that the disparity in effort is being leveraged in something less than good faith. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 05:02, 2 January 2025 (UTC)
*::Assume good faith, don't ascertain! Llm use can be deeply unhelpful for discussions and the potential for mis-use is large, but the most recent discussion I've been involved with where I observed an llm post was responded to by an llm post, I believe both the users were doing this in good faith. ] (]) 05:07, 2 January 2025 (UTC)
*:::All I mean to say is it should be licit that unhelpful LLM use should be something that can be mentioned like any other unhelpful rhetorical pattern. <span style="border-radius:2px;padding:3px;background:#1E816F">]<span style="color:#fff"> ‥ </span>]</span> 05:09, 2 January 2025 (UTC)
*::::Sure, but ] doesn't mention any unhelpful rhetorical patterns. ] (]) 05:32, 2 January 2025 (UTC)
*::::The fact that everyone (myself included) defending "LLM use" says "use" rather than "generated", is a pretty clear sign that no one really wants to communicate with someone using "LLM generated" comments. We can argue about bans (not being proposed here), how to know if someone is using LLM, the nuances of "LLM use", etc., but at the very least we should be able to agree that there are concerns with LLM generated replies, and if we can agree that there are concerns then we should be able to agree that somewhere in policy we should be able to find a place to express those concerns. ] (]) 05:38, 2 January 2025 (UTC)
*:::::...or they could be saying "use" because "using LLMs" is shorter and more colloquial than "generating text with LLMs"? ] (]) 06:19, 2 January 2025 (UTC)
*::::::Seems unlikely when people justify their use for editing (which I also support), and not for generating replies on their behalf. ] (]) 06:23, 2 January 2025 (UTC)
*:::::::This is just semantics.
*:::::::For instance, I am OK with someone using a LLM to post a productive comment on a talk page. I am also OK with someone generating a reply with a LLM that is a productive comment to post to a talk page. I am not OK with someone generating text with an LLM to include in an article, and also not OK with someone using a LLM to contribute to an article.
*:::::::The only difference between these four sentences is that two of them are more annoying to type than the other two. ] (]) 08:08, 2 January 2025 (UTC)
*::::::::Most people already assume good faith in those making productive contributions. In situations where good faith is more difficult to assume, would you trust someone who uses an LLM to generate all of their comments as much as someone who doesn't? ] (]) 09:11, 2 January 2025 (UTC)
*:::::::::Given that LLM-use is completely irrelevant to the faith in which a user contributes, yes. Of course what amount that actually is may be anywhere between completely and none. ] (]) 11:59, 2 January 2025 (UTC)
*::::::::::LLM-use is relevant as it allows bad faith users to disrupt the encyclopedia with minimal effort. Such a user , as well as started and , all using AI. I had previously been involved in a debate with another sock puppet of theirs, but at that time they didn't use AI. Now it seems they are switching to using an LLM just to troll with minimal effort. ] (]) 21:44, 2 January 2025 (UTC)
*:::::::::::LLMs are a tool that can be used by good and bad faith users alike. Using an LLM tells you nothing about whether a user is contributing in good or bad faith. If somebody is trolling they can be, and should be, blocked for trolling regardless of the specifics of how they are trolling. ] (]) 21:56, 2 January 2025 (UTC)
*::::::::::::A can of spray paint, a kitchen knife, etc., are tools that can be used for good or bad, but if you bring them some place where they have few good uses and many bad uses then people will be suspicious about why you brought them. You can't just assume that a tool in any context is equally harmless. Using AI to generate replies to other editors is more suspicious than using it to generate a picture exemplifying a fashion style, or a description of a physics concept. ] (]) 23:09, 2 January 2025 (UTC)
*:::::::::I wouldn't trust anything factual the person would have to say, but I wouldn't assume they were malicious, which is the entire point of ]. ] (]) 16:47, 2 January 2025 (UTC)
*::::::::::] is not a death pact though. At times you should be suspicious. Do you think that if a user, ''who you already have suspicions of'', is also using an LLM to generate their comments, that that doesn't have any effect on those suspicions? ] (]) 21:44, 2 January 2025 (UTC)
*:::::::::::So… If you suspect that someone is not arguing in good faith… just stop engaging them. If they are creating walls of text but not making policy based arguments, they can be ignored. Resist the urge to respond to every comment… it isn’t necessary to “have the last word”. ] (]) 21:57, 2 January 2025 (UTC)
*::::::::::::As the person ] demonstrates, you can't "just stop engaging them". When they then somebody has to engage them in some way. It's not about trying to "have the last word", this is a collaborative project, it generally requires engaging with others to some degree. When someone like the person I linked to above (now banned sock), spams low quality comments across dozens of AfDs, then they are going to waste people's time, and telling others to just not engage with them is dismissive of that. ] (]) 22:57, 2 January 2025 (UTC)
*:::::::::::::That they've been banned for disruption indicates we can do everything we need to do to deal with bad faith users of LLMs without assuming that everyone using an LLM is doing so in bad faith. ] (]) 00:33, 3 January 2025 (UTC)
*::::::::::::::I don't believe we should assume everyone using an LLM is doing so in bad faith, so I'm glad you think my comment indicates what I believe. ] (]) 01:09, 3 January 2025 (UTC)
:'''No''' -- whatever you think of LLMs, the reason they are so popular is that the people who use them earnestly believe they are useful. Claiming otherwise is divorced from reality. Even people who add hallucinated bullshit to articles are usually well-intentioned (if wrong). ] (]) 06:17, 2 January 2025 (UTC)
:Community involvement in the process is always welcome. If you can show me where community involvement wasn't welcomed, I will really appreciate, as I never spotted such a case. BTW, I'm not a BAG member ;-)<i><b>]<small> <sup>]</sup> <sub>]</sub> <sup>]</sup></small></b> - </i> 12:41, 13 April 2007 (UTC)
*'''Comment''' I have no opinion on this matter, however, note that we are currently dealing with a ] and there's a generalized state of confusion in how to address it. ] (]) 08:54, 2 January 2025 (UTC)
::Thank you for that comment, I think it's spot on. Let me add that BAG also includes ''3'' active AWB developers, and the tool being used for the manual assessments was written by me (with hundreds of hours of my personal time being given gratis). On top of this we are all admins, and, I believe, all trusted members of the community. I can say with the utmost confidence that we are not only technically knowledgeable as a group but also experienced and dedicated Wikipedians with one common interest: the betterment of Misplaced Pages. If I ever personally exhibit any behaviour which isn't compatible with this claim (apart from my lighthearted clowning around of course :)) I'd like to be advised of it immediately. --] 13:24, 13 April 2007 (UTC)
*'''Yes''' I find it incredibly rude for someone to procedurally generate text and then expect others to engage with it as if they were actually saying something themselves. ] (]) 14:34, 2 January 2025 (UTC)
* '''Yes, mention''' that use of an LLM should be disclosed and that failure to do so is like not telling someone you are taping the call. ] (]) 14:43, 2 January 2025 (UTC)
*:I could support general advice that if you're using machine translation or an LLM to help you write your comments, it can be helpful to mention this in the message. The tone to take, though, should be "so people won't be mad at you if it screwed up the comment" instead of "because you're an immoral and possibly criminal person if you do this". ] (]) 07:57, 3 January 2025 (UTC)
: '''No.''' When someone publishes something under their own name, they are incorporating it as their own statement. Plagiarism from an AI or elsewhere is irrelevant to whether they are engaging in good faith. ] (]) 17:29, 2 January 2025 (UTC)
* '''Comment''' LLMs know a few tricks about logical fallacies and some general ways of arguing (rhetoric), but they are incredibly dumb at understanding the rules of Misplaced Pages. You can usually tell this because it looks like incredibly slick and professional prose, but somehow it cannot get even the simplest points about the policies and guidelines of Misplaced Pages. I would indef such users for lacking ]. ] (]) 17:39, 2 January 2025 (UTC)
*:That guideline states "Sanctions such as blocks and bans are always considered a ''last resort'' where all other avenues of correcting problems have been tried and have failed." ] (]) 19:44, 2 January 2025 (UTC)
*:: ] isn't a guideline, but an essay. Relevantly though it is being cited at this very moment in ]. ] (]) 20:49, 2 January 2025 (UTC)
*:::I blocked that user as NOTHERE a few minutes ago after seeing them (using ChatGPT) make suggestions for text to live pagespace while their previous bad behaviors were under discussion. AGF is not a suicide pact. ] (]) 20:56, 2 January 2025 (UTC)
*'''No''' - Not a good or bad faith issue. ] (]) 21:02, 2 January 2025 (UTC)
*'''Yes''' Using a 3rd party service to contribute to the Misplaced Pages on your behalf is clearly bad-faith, analogous to paying someone to write your article. ] (]) 14:39, 3 January 2025 (UTC)
*:Its a stretch to say that a newbie writing a comment using AI is automatically acting in bad faith and not here to build an encyclopedia. ] (]) 16:55, 3 January 2025 (UTC)
*::That's true, but this and other comments here show that not a few editors perceive it as bad-faith, rude, etc. I take that as an indication that we should tell people to avoid doing this when they have enough CLUE to read WP:AGF and are ]. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 23:06, 9 January 2025 (UTC)
*'''Comment''' Large language model AI like Chat GPT are in their infancy. The culture hasn't finished its initial reaction to them yet. I suggest that any proposal made here have an automatic expiration/required rediscussion date two years after closing. ] (]) 22:42, 3 January 2025 (UTC)
*'''No''' – It is a matter of how you use AI. I use Google translate to add trans-title parameters to citations, but I am careful to check for Google's output making for good English as well as reflecting the foreign title when it is a language I somewhat understand. I like to think that I am careful, and I do not pretend to be fluent in a language I am not familiar with, although I usually don't announce the source of such a translation. If an editor uses AI profligately and without understanding the material generated, then that is the sin; not AI itself. ] (]) 05:04, 5 January 2025 (UTC)
*:There's a legal phrase, "when the exception swallows the rule", and I think we might be headed there with the recent LLM/AI discussions.
*:We start off by saying "Let's completely ban it!" Then in discussion we add "Oh, except for this very reasonable thing... and that reasonable thing... and nobody actually meant this other reasonable thing..."
*:The end result is that it's "completely banned" ...except for an apparent majority of uses. ] (]) 06:34, 5 January 2025 (UTC)
*::Do you want us to reply to you, because you are a human? Or are you just posting the output of an LLM without bothering to read anything yourself? ] (]) 06:08, 7 January 2025 (UTC)
*:::Most likely you would reply because someone posted a valid comment and you are assuming they are acting in good faith and taking responsibility for what they post. To assume otherwise is kind of weird and not inline with general Misplaced Pages values. ] (]) 15:19, 8 January 2025 (UTC)
*'''No''' The OP seems to misunderstand ] which is not aimed at weak editors but instead exhorts stronger editors to lead by example. That section already seems to overload the primary point of WP:AGF and adding mention of AI would be quite inappropriate per ]. ]🐉(]) 23:11, 5 January 2025 (UTC)
*'''No'''. Reading the current text of the section, adding text about AI would feel out-of-place for what the section is about. <span class="nowrap">—] (] | ])</span> 05:56, 8 January 2025 (UTC)
*'''No''', this is not about good faith. ] (]) 11:14, 9 January 2025 (UTC)
*'''Yes'''. AI use is ''not'' a demonstration of bad faith (in any case not every new good-faith editor is familiar with our AI policies), but it is equally not a "demonstration of good faith", which is what the ] section is about.
:It seems some editors are missing the point and !voting as if every edit is either a demonstration of good faith or bad faith. Most interactions are neutral and so is most AI use, but I find it hard to imagine a situation where AI use would point ''away'' from unfamiliarity and incompetence (in the CIR sense), and it often (unintentionally) leads to a presumption of laziness and open disinterest. It makes perfect sense to recommend against it. <span style="font-family:Garamond,Palatino,serif;font-size:115%;background:-webkit-linear-gradient(red,red,red,blue,blue,blue,blue);-webkit-background-clip:text;-webkit-text-fill-color:transparent">] ]</span> 22:56, 9 January 2025 (UTC)
*'''Yes'''. Per Dass Wolf, though I would say passing off a completely AI-generated comment as your own ''anywhere'' is inherently bad-faith and one doesn't need to know Wiki policies to understand that. ] (]) 23:30, 9 January 2025 (UTC)
*'''Yes'''. Sure, LLMs may have utility somewhere, and it might be a crutch for people unfamiliar with English, but as I've said above in the other AI RfC, that's a ] issue. This is about comments eating up editor time, energy, about LLMs easily being used to ram through changes and poke at editors in good standing. I don't see a case wherein a prospective editor's command of policy and language is good enough to discuss with other editors while being bad enough to require LLM use. ]<span style="color: #3558b7;"><sup>]</sup>]</span> 01:26, 10 January 2025 (UTC)
*'''No''' - anyone using a washing machine to wash their clothes must be evil and inherently lazy. They cannot be trusted. ... Oh, sorry, wrong century. Regards, --] (]) 01:31, 10 January 2025 (UTC)
== Limitingthe use of WMF logos in articlespace ==
== Edit quality in Android application ==
Several contributors, including myself, don't understand the point of the ‘edit quality’ mention in the Android application.
Wikimedia logos are unfree. They are copyrighted and trademarked by the ] (e.g. ]). The Foundation believes strictly controlling these images is necessary to their ability to manage the brand. Various efforts over ~2 years have requested that the Foundation either adopt some form of ] or otherwise providing licensing that would make the logos free. But ], chair of the WMF Board, has made clear, "the Foundation will not put the logos under a free licence" .
The ] states that edit quality is ‘based on how many of your edits were reverted’. Is this the only criterion used? If so, calling it ‘edit quality’ is presumptuous, not to say irresponsible, given that there should be so many criteria. What are the different levels of judgement: excellent, good, bad, horrible, etc. ? What does this mean for developers, bots, patrollers and administrators? Whatever the case, the consequences of such a statement could be quite serious.
As a result there are no officially approved uses of WMF logos in Misplaced Pages except for the main logo at the upper left. Most everyone assumes that the WMF tolerates the use of the logos within Misplaced Pages (of which they are doubtlessly aware), and that there is unlikely to be any real legal conflict about anything used within Misplaced Pages. What is far less clear is what happens for reusers. Reusers do not have any rights to Wikimedia logos and Foundation has said there are classes of sites that they would have real concern about if they were using Wikimedia logos.
It's clear that the choice to keep this mention in the application doesn't just concern the application developers or even a small team, but all Misplaced Pages contributors, whatever their language. So we think it's important that you answer our questions. <small>(As my English isn't very good, could you answer me in basic English, or at least without figures of speech? Thank you in advance.)</small> ] (]) 13:12, 7 January 2025 (UTC)
In the interest of creating an encyclopedia that is truly free, and makes reuse as easy as possible, I would like to advocate eliminating the incidental and decorative uses of Wikimedia logos within article space. For example, by removing the logo from ]. The text on the template already identifies the target, so the logo adds little, while coming at the cost of embedding unfree content with potential unexpected legal landmines within our otherwise free content.
:Hi Albag. I agree with the core of your message. But I don't get why you have been redirected to English Village Pump. This should be discussed somewhere on Meta or Mediawiki wiki, as it's relevant for all Misplaced Pages communities, not only the English one. (You and I are from fr-wp.) Best, — ''']''' <sup><small style="border-bottom:1px solid">]</small></sup> 13:28, 7 January 2025 (UTC)
I realize removing the logos, which are used extensively through our ], would be controversial for some, but I think it is right thing to do in light of our commitment to free content and the regrettable unwillingness of the Foundation to provide any other protection for reusers. ] 21:39, 12 April 2007 (UTC)
::Thanks ]. According to ], the place to discuss would be there : ]. --] (]) 13:43, 7 January 2025 (UTC)
:Well, couldn't we just do imagemap (click on the image to take you to the commons gallery, as opposed to going to the image description page) on those images so that reusers don't get easy access to the image? ''']''' <sup><font color="black">]</font> · <font color="blue">]</font></sup> 21:46, 12 April 2007 (UTC)
::I'm thinking about people interested in working from the to create ] rather than people copying images one at a time. ] 21:52, 12 April 2007 (UTC)
== Allowing non-admin "delete" closures at RfD ==
:::I recently tried to address this issue, and got 0 cooperation here. I obstain from any further actions myself, but I agree with you, and you have my personal full support. --] (] • ] • ]) 12:45, 13 April 2007 (UTC)
At ], a few editors ({{u|Enos733}} and {{u|Jay}}, while {{u|Robert McClenon}} and {{u|OwenX}} hinted at it) expressed support for allowing non-administrators to close RfD discussions as "delete". While I don't personally hold strong opinions in this regard, I would like for this idea to be discussed here. ]<sub>]<sub>]</sub></sub> (]/]) 13:13, 7 January 2025 (UTC)
==]==
*] --] <sup>(])</sup> 14:10, 7 January 2025 (UTC)
As per ] I would like to propose the following new policy: ]. This proposal has been extensively discussed ], and that discussion is also reproduced and has been expanded upon at the talk page for the proposed policy. In a nutshell the policy is “Misplaced Pages is not a counseling service. Respond to suicidal individuals by pointing them towards one of the listed crisis lines/websites. Do not ridicule or make personal attacks on suicidal editors.” Please edit or comment upon this proposed policy. Thank you. ] 22:34, 12 April 2007 (UTC)
*While I have no issue with the direction the linked discussion has taken, I agree with almost every contributor there: As a practice I have zero interest in generally allowing random editors closing outside their permissions. It might make DRV a more chatty board, granted. ] (]) 15:02, 7 January 2025 (UTC)
*:Tamzin makes a reasonable case in their comment below. When we have already chosen to trust certain editors with advanced permissions, we might allow those folks to utilize them as fully as accepted practice allows. Those humans already have skin in the game. They are unlikely to act rashly. ] (]) 19:32, 7 January 2025 (UTC)
* To me, non-admin delete closes at any XfD have always seemed inconsistent with what we say about how adminship and discussion closing work. I would be in violation of admin policy if I deleted based on someone else's close without conducting a full review myself, in which case, what was the point of their close? It's entirely redundant to my own work. That said, I can't really articulate a reason that this should be allowed at some XfDs but not others, and it seems to have gone fine at CfD and TfD. I guess call me neutral. {{PB}} What I'd be more open to is allowing page movers to do this. Page movers do have the tools to turn a bluelink red, so it doesn't create the same admin accountability issue if I'm just cleaning up the stray page left over from a page mover's use of a tool that they were duly granted and subject to their own accountability rules for. We could let them move a redirect to some other plausible title (this would violate ] as currently written but I think I'd be okay with making this a canonical exception), and/or allow moving to some draftspace or userspace page and tagging for G6, as we do with {{tl|db-moved}}. I'll note that when I was a non-admin pagemover, I did close a few things as delete where some edge case applied that let me effect the deletion using only suppressredirect, and no one ever objected. <span style="font-family:courier"> -- ]</span><sup class="nowrap">[]]</sup> <small>(])</small> 19:07, 7 January 2025 (UTC)
*::I see that I was sort of vague, which is consistent with the statement that I hinted at allowing non-admin delete closures. My main concern is that I would like to see our guidelines and our practice made consistent, either by changing the guidelines or changing the practice. It appears that there is a rough consensus emerging that non-admin delete closures should continue to be disallowed in RFD, but that CFD may be a special case. So what I am saying is that if, in practice, we allow non-admin Delete closures at CFD, the guideline should say something vague to that effect.
*::I also see that there is a consensus that DRV can endorse irregular non-admin closures, including irregular non-admin Delete closures. Specifically, it isn't necessary for DRV to vacate the closure for an ] admin to close. A consensus at DRV, some of whose editors will be uninvolved admins, is at least as good a close as a normal close by an uninvolved admin.
*::Also, maybe we need clearer guidance about non-admin Keep closures of AFDs. I think that if an editor is not sure whether they have sufficient experience to be closing AFDs as Keep, they don't have enough experience. I think that the guidance is clear enough in saying that ] applies to non-admin closes, but maybe it needs to be further strengthened, because at DRV we sometimes deal with non-admin closes where the closer doesn't respond to inquiries, or is rude in response to them.
*::Also, maybe we need clearer guidance about non-admin No Consensus closures of AFDs. In particular, a close of No Consensus is a contentious closure, and should either be left to an admin, or should be Relisted.
::] (]) 19:20, 7 January 2025 (UTC)
:::As for {{tq| I can't really articulate a reason that this should be allowed at some XfDs}}, the argument is that more work is needed to enact closures at TfD and CfD (namely orphaning templates and emptying/moving/merging categories). Those extra steps aren't present at RfD. At most, there are times when it's appropriate to unlink the redirect or add ]s but those are automated steps that ] handles. From my limited experience at TfD and CfD though, it does seem that the extra work needed at closure does not compensate for the extra work from needing two people reviewing the closure (especially at CfD because a bot that handles the clean-up). Consistency has come up and I would much rather consistently disallow non-admin delete closures at all XfD venues. I know it's tempting for non-admins to think they're helping by enacting these closures but it's not fair for them to be spinning their wheels. As for moving redirects, that's even messier than deleting them. There's a reason that ] advises not to move redirects except for limited cases when preserving history is important. --] <sup>(])</sup> 20:16, 7 January 2025 (UTC)
::@]: I do have one objection to this point of redundancy, which you are ]. Here, an AfD was closed as "transwiki and delete", however, the admin who did the closure does not have the technical ability to transwiki pages to the English Wikibooks, meaning that I, who does, had to determine that the outcome was actually to transwiki rather than blindly accepting a request at ]. Then, I had to mark the pages for G6 deletion, that way an admin, in this case you, could determine that the page was ready to be deleted. Does this mean that that admin who closed the discussion shouldn't have closed it, since they only have the technical ability to delete, not transwiki? Could I have closed it, having the technical ability to transwiki, but not delete? Either way, someone else would have had to review it. Or, should only people who have importing rights on the target wiki ''and'' admin rights on the English Misplaced Pages be allowed to close discussions as "transwiki and delete"? ]<sub>]<sub>]</sub></sub> (]/]) 12:04, 8 January 2025 (UTC)
*I do support being explicit when a non-administrator can close a discussion as "delete" and I think that explicitly extending to RfD and CfD is appropriate. First, there can be a backlog in both of these areas and there are often few comments in each discussion (and there is usually not the same passion as in an AfD). Second, the delete close of a non-administrator is reviewed by an administrator before action is taken to delete the link, or category (a delete close is a two-step process, the writeup and the delete action, so in theory the administrators workload is reduced). Third, non-admins do face ] for their actions, and can be subject to sanction. Fourth, the community has a role in reviewing closing decisions at DRV, so there is already a process in place to check a unexperienced editor or poor close. Finally, with many, if not most discussions for deletion the outcome is largely straight forward. --] (]) 20:01, 7 January 2025 (UTC)
*There is currently no rule against non-admin delete closures as far as I know; the issue is the practical one that you don't have the ability to delete. However, I ''have'' made non-admin delete closures at AfD. This occurred when an admin deleted the article under consideration (usually for COPYVIO) without closing the related AfD. The closures were not controversial and there was no DRV. ] ] 20:31, 7 January 2025 (UTC)
== "Section Twenty-one of..." ==
::The situation you're referring to is an exception allowed per ]: {{tq|If an administrator has deleted a page (including by speedy deletion) but neglected to close the discussion, anyone with a registered account may close the discussion provided that the administrator's name and deletion summary are included in the closing rationale.}} --] <sup>(])</sup> 20:37, 7 January 2025 (UTC)
*Bad idea to allow, this sort of closure is just busy work, that imposes more work on the admin that then has to review the arguments, close and then delete. ] (]) 22:05, 7 January 2025 (UTC)
* Is this the same as ] above? ]] 23:04, 7 January 2025 (UTC)
**Yes, ]. Same issue coming from the same ]. ] (]) 03:52, 8 January 2025 (UTC)
* (1) As I've also ], the deletion process guidelines at ] do say non-admins shouldn't do "delete" closures and do recognize exceptions for CfD and TfD. There isn't a current inconsistency there between guidelines and practice. <br>(2) In circumstances where we do allow for non-admin "delete" closures, I would hope that the implementing admin isn't fully ] before implementing, but rather giving deference to any reasonable closure. That's how it goes with ] closers asking for technical help implementing a "moved" closure at ] (as noted at ], the closure will "generally be respected by the administrator (or page mover)" but can be reverted by an admin if "clearly improper"). ] ] 08:41, 9 January 2025 (UTC)
*'''Comment''' - A couple things to note about the CFD process: It very much requires work by admins. The non-admin notes info about the close at WT:CFD/Working, and then an admin enters the info on the CFD/Working page (which is protected) so that the bot can perform the various actions. Remember that altering a category is potentially more labour intensive than merely editing or deleting a single page - every page in that category must be edited, and then the category deleted. (There are other technical things involved, like the mess that template transclusion can cause, but let's keep it simple.) So I wouldn't suggest that that process is very useful as a precedent for anything here. It was done at a time when there was a bit of a backlog at CfD, and this was a solution some found to address that. Also - since then, I think at least one of the regular non-admin closers there is now an admin. So there is that as well. - <b>]</b> 09:14, 9 January 2025 (UTC)
There is a series of articles with titles like ]. The capitalization "Twenty-one" rather than "Twenty-One" is an antique style, and in any case the normal use in any legal context would be "Section 21". Is there any policy or style-guide reason that supports the present titling style for these articles?
*If the expectation is that an admin needs to review the deletion discussion to ensure they agree with that outcome before deleting via G6, as multiple people here are suggesting, then I'm not sure this is worthwhile. However, I have had many admins delete pages I've tagged with G6, and I have been assuming that they only check that the discussion was indeed closed as delete, and trust the closer to be responsible for the correctness of it. This approach makes sense to me, because if a non-admin is competent to close and be responsible for any other outcome of a discussion, I don't see any compelling reason they can't be responsible for a delete outcome and close accordingly. <span style="white-space: nowrap;">—] <sup>(]·])</sup></span> 19:51, 9 January 2025 (UTC)
== Placement of dynamic list template ==
] 01:17, 13 April 2007 (UTC)
:] would probably be the place to start. --]<sup><font color="green">]</font></sup>'''<font color="orange">]</font>''' 02:18, 13 April 2007 (UTC)
Where does the template {{template|dynamic list}} actually go? It superficially looks like it should be a hatnote at the top of the article, but there are a great number (perhaps a majority) of dynamic list articles where the template is placed under the infobox and lead. I can't find anything in the MOS specifically addressing this. ] 21:44, 7 January 2025 (UTC)
::Yes, well, I was hoping someone would be familiar enough to point me to the right section if there is one. I've just browsed a number of sections and not found anything directly relevant. ] 04:50, 13 April 2007 (UTC)
:The template documentation, which you linked to, addresses this: Place this notification template immediately before the applicable ] (i.e. in a section, not at the top of the article). This template will automatically add the article to ]. ] (]/]) 21:47, 7 January 2025 (UTC)
==Rating scale==
::In many cases, the template is neither at the very top nor within a section. Just to be clear, this placement is not correct? ] 22:25, 7 January 2025 (UTC)
I've seen a rating scale for biographies, but where are the criteria for other categories? I'd like to make an article A class but I want to be sure it meets the criteria. I don't want to know for just this category but all categories. <i><font face="arial, helvetica" color="Blue"><b></b></font></i> ] <sup>]</sup><sub>]</sub> 05:04, 13 April 2007 (UTC)
:::It should go right above the list. ] (]/]) 22:40, 7 January 2025 (UTC)
:Also if A class is ahead of GA, why is A class arbitrarily decided but GA class requires a systematic process? <i><font face="arial, helvetica" color="Blue"><b></b></font></i> ] <sup>]</sup><sub>]</sub> 05:12, 13 April 2007 (UTC)
:: My interpretation is that an A-class article is one that only just misses the ], while being easily a Good Article. ] 05:27, 13 April 2007 (UTC)
::: That's what I'm talking about "just misses" "while easily being a Good Article" isn't there some kind of formal criteria here? <i><font face="arial, helvetica" color="Blue"><b></b></font></i> ] <sup>]</sup><sub>]</sub> 06:58, 13 April 2007 (UTC)
:::: It is somewhat odd but that's the situation. A few wikiprojects have formal systems for making A-class articles. For the rest, you just assign the article a quality rating by yourself. If someone else disagrees with your rating, they can always change it later. ] · <small>]</small> 11:44, 13 April 2007 (UTC)
== Should WP:NOTDIRECTORY be more specific about phone numbers, etc.? ==
== Violation of BLP?: ] ==
Apparently the ] talk page isn't well-watched, so I'd like to draw some attention to ] over there. ] (]) 04:05, 8 January 2025 (UTC)
, which was published in the some of the largest of magazines in the United States, a violation of BLP? -- ] 13:57, 13 April 2007 (UTC)
:That talk page has been checked by at least 100 registered editors during the last month, which makes it one of our better watched pages. ] (]) 18:22, 9 January 2025 (UTC)
:: we already had this discussion. YOU are a loser who locked the page as a favor for a friend. All of this is revealed on
::{{tq|Apparently}}. :) Getting no response in 36 hours was surprising. The silence could mean "no objection" (since I'm not proposing a change, just a clarification that already used to be there), but since it's a policy page, it would be good to have something more tangible. ] (]) 08:20, 10 January 2025 (UTC)
You should resign, go back to graphic design, and slice yourself. ] 15:16, 13 April 2007 (UTC)
== Does my name technically violate the promotional username policy? ==
== Naming conventions ==
My username, as of right now, is Tenebre.Rosso.Sangue995320, which is a reference to and i recently read the username policy, and thought that this violates that policy. can someone help me out? ] ] ] 23:48, 9 January 2025 (UTC)
I brought this up at ], but I didn't get a response. My question is about the names of articles about places or buildings within a city, such as ]. Is there a rule to help us choose between "Humboldt Park, Chicago", "Humboldt Park, Chicago, Illinois", "Humboldt Park (Chicago)", and "Humboldt Park (Chicago, Illinois)" for the name of the article? Thanks, ]<sup>(])</sup> 15:02, 13 April 2007 (UTC)
:No, it does not. ] (]/]) 00:11, 10 January 2025 (UTC)
The policy section of the village pump is intended for discussions about already-proposed policies and guidelines, as well as changes to existing ones. Discussions often begin on other pages and are subsequently moved or referenced here to ensure greater visibility and broader participation.
If you wish to propose something new that is not a policy or guideline, use Village pump (proposals). Alternatively, for drafting with a more focused group, consider starting the discussion on the talk page of a relevant WikiProject, the Manual of Style, or another relevant project page.
For questions about how to apply existing policies or guidelines, refer to one of the many Misplaced Pages:Noticeboards.
If you want to inquire about what the policy is on a specific topic, visit the Help desk or the Teahouse.
This is not the place to resolve disputes regarding the implementation of policies. For such cases, consult Misplaced Pages:Dispute resolution.
Should admins or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots? 00:12, 2 December 2024 (UTC)
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this.
I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. Just Step Sideways00:12, 2 December 2024 (UTC)
Seems reasonable, as long as the GPTZero (or any tool) score is taken with a grain of salt. GPTZero can be as wrong as AI can be. ~ ToBeFree (talk) 00:32, 2 December 2024 (UTC)
Only if the false positive and false negative rate of the tool you are using to detect LLM content is very close to zero. LLM detectors tend to be very unreliable on, among other things, text written by non-native speakers. Unless the tool is near perfect then it's just dismissing arguments based on who wrote them rather than their content, which is not what we do or should be doing around here. Thryduulf (talk) 00:55, 2 December 2024 (UTC)
The more I read the comments from other editors on this, the more I'm a convinced that implementing either this policy or something like it will bring very significant downsides on multiple fronts that significantly outweigh the small benefits this would (unreliably) bring, benefits that would be achieved by simply reminding closers to disregard comments that are unintelligible, meaningless and/or irrelevant regardless of whether they are LLM-generated or not. For the sake of the project I must withdraw my previous very qualified support and instead very strongly oppose. Thryduulf (talk) 02:45, 3 December 2024 (UTC)
I think it should be an expressly legitimate factor in considering whether to discount or ignore comments either if it's clear enough by the text or if the user clearly has a history of using LLMs. We wouldn't treat a comment an editor didn't actually write as an honest articulation of their views in lieu of site policy in any other situation. Remsense ‥ 论00:59, 2 December 2024 (UTC)
I would have already expected admins to exercise discretion in this regard, as text written by an LLM is not text written by a person. We cannot guarantee it is what the person actually means, especially as it is a tool often used by those with less English proficiency, which means perhaps they cannot evaluate the text themselves. However, I do not think we can make policy about a specific LLM or tool. The LLM space is moving fast, en.wiki policies do not. Removal seems tricky, I would prefer admins exercise discretion instead, as they do with potentially canvassed or socked !votes. CMD (talk) 01:06, 2 December 2024 (UTC)
As the discussion has moved forward below, I feel I can shift to a more explicit support in terms of providing guidance to closers and those otherwise evaluating consensus. CMD (talk) 17:33, 2 January 2025 (UTC)
Support discounting or collapsing AI-generated comments, under slightly looser conditions than those for human comments. Not every apparently-AI-generated comment is useless hallucinated nonsense – beyond false positives, it's also possible for someone to use an AI to help them word a constructive comment, and make sure that it matches their intentions before they publish it. But in my experience, the majority of AI-generated comments are somewhere between "pointless" and "disruptive". Admins should already discount clearly insubstantial !votes, and collapse clearly unconstructive lengthy comments; I think we should recognize that blatant chatbot responses are more likely to fall into those categories. jlwoodwa (talk) 02:11, 2 December 2024 (UTC)
Strongly Support - I think some level of human judgement on the merits of the argument are necessary, especially as GPTZero may still have a high FPR. Still, if the discussion is BLUDGEONy, or if it quacks like an AI-duck, looks like an AI-duck, etc, we should consider striking out such content.- sidenote, I'd also be in favor of sanctions against users who overuse AI to write out their arguments/articles/etc. and waste folks time on here.. Bluethricecreamman (talk) 02:20, 2 December 2024 (UTC)
On a wording note, I think any guidance should avoid referring to any specific technology. I suggest saying "... to have been generated by a program". isaacl (talk) 02:54, 2 December 2024 (UTC)
A translation program, whether it is between languages or from speech, is not generating a comment, but converting it from one format to another. A full policy statement can be more explicit in defining "generation". The point is that the underlying tech doesn't matter; it's that the comment didn't feature original thought from a human. isaacl (talk) 03:57, 2 December 2024 (UTC)
Support. We already use discretion in collapsing etc. comments by SPAs and suspected socks, it makes sense to use the same discretion for comments suspected of being generated by a non-human. JoelleJay (talk) 03:07, 2 December 2024 (UTC)
Support - Someone posting "here's what ChatGPT has to say on the subject" can waste a lot of other editors' time if they feel obligated to explain why ChatGPT is wrong again. I'm not sure how to detect AI-written text but we should take a stance that it isn't sanctioned. Clayoquot (talk | contribs) 04:37, 2 December 2024 (UTC)
Strong Support - I've never supported using generative AI in civil discourse. Using AI to participate in these discussions is pure laziness, as it is substituting genuine engagement and critical thought with a robot prone to outputting complete garbage. In my opinion, if you are too lazy to engage in the discussion yourself, why should we engage with you? Lazman321 (talk) 05:26, 2 December 2024 (UTC)
Because it's based on a potentially false premise that it will be possible to reliably distinguish between text generated by human biological neural networks and text generated by non-biological neural networks by observing the text. It is already quite difficult in many cases, and the difficulty is increasing very rapidly. I have your basic primate brain. The AI companies building foundation models have billions of dollars, tens of thousands, soon to be hundreds of thousands of GPUs, a financial incentive to crack this problem and scaling laws on their side. So, I have very low credence in the notion that I will be able to tell whether content is generated by a person or a person+LLM or an AI agent very soon. On the plus side, it will probably still be easy to spot people making non-policy based arguments regardless of how they do it. Sean.hoyland (talk) 13:52, 2 December 2024 (UTC)
...and now that the systems are autonomously injecting their output back into model via chain-of-thought prompting, or a kind of inner monologue if you like, to respond to questions, they are becoming a little bit more like us. Sean.hoyland (talk) 14:14, 2 December 2024 (UTC)
A transformer (deep learning architecture) is intrinsically nothing like a human. It's a bunch of algebra that can compute what a decently sensible person could write in a given situation based on its training data, but it is utterly incapable of anything that could be considered thought or reasoning. This is why LLMs tend to fail spectacularly when asked to do math or write non-trivial code. Flounder fillet (talk) 17:20, 2 December 2024 (UTC)
We shall see. You might want to update yourself on their ability to do math and write non-trivial code. Things are changing very quickly. Either way, it is not currently possible to say much about what LLMs are actually doing because mechanistic interpretability is in its infancy. Sean.hoyland (talk) 03:44, 3 December 2024 (UTC)
Support and I would add "or similar technologies" to "AI/LLM/Chatbots". As for Sean.hoyland's comment, we will cross that bridge when we get to it. Cullen328 (talk) 05:51, 2 December 2024 (UTC)
Support - All editors should convey their thoughts in their own words. AI generated responses and comments are disruptive because they are pointless and not meaningful. - Ratnahastin (talk) 06:04, 2 December 2024 (UTC)
Support, I already more or less do this. An LLM generated comment may or may not actually reflect the actual thoughts of the editor who posted it, so it's essentially worthless toward a determination of consensus. Since I wrote this comment myself, you know that it reflects my thoughts, not those of a bot that I may or may not have reviewed prior to copying and pasting. Seraphimblade06:59, 2 December 2024 (UTC)
Strong oppose. Let me say first that I do not like ChatGPT. I think it has been a net negative for the world, and it is by nature a net negative for the physical environment. It is absolutely a net negative for the encyclopedia if LLM-generated text is used in articles in any capacity. However, hallucinations are less of an issue on talk pages because they're discussions. If ChatGPT spits out a citation of a false policy, then obviously that comment is useless. If ChatGPT spits out some boilerplate "Thanks for reviewing the article, I will review your suggestions and take them into account" talk page reply, who gives a fuck where it came from? (besides the guys in Texas getting their eardrums blown out because they live by the data center)The main reason I oppose, though, is because banning LLM-generated comments is difficult to enforce bordering on unenforceable. Most studies show that humans are bad at distinguishing AI-generated text from text generated without AI. Tools like GPTZero claims a 99% accuracy rate, but that seems dubious based on reporting on the matter. The news outlet Futurism (which generally has an anti-AI slant) has failed many times to replicate that statistic, and anecdotal accounts by teachers, etc. are rampant. So we can assume that we don't know how capable AI detectors are, that there will be some false positives, and that striking those false positives will result in WP:BITING people, probably newbies, younger people more accustomed to LLMs, and non-Western speakers of English (see below).There are also technological issues as play. It'd be easy if there was a clean line between "totally AI-generated text" and "totally human-generated text," but that line is smudged and well on its way to erased. Every tech company is shoving AI text wrangling into their products. This includes autocomplete, translation, editing apps, etc. Should we strike any comment a person used Grammarly or Google Translate for? Because those absolutely use AI now.And there are also, as mentioned above, cultural issues. The people using Grammarly, machine translation, or other such services are likely to not have English as their first language. And a lot of the supposed "tells" of AI-generated content originate in the formal English of other countries -- for instance, the whole thing where "delve" was supposedly a tell for AI-written content until people pointed out the fact that lots of Nigerian workers trained the LLM and "delve" is common Nigerian formal English.I didn't use ChatGPT to generate any of this comment. But I am also pretty confident that if I did, I could have slipped it in and nobody would have noticed until this sentence. Gnomingstuff (talk) 08:31, 2 December 2024 (UTC)
Just for grins, I ran your comment through GPTzero, and it comes up with a 99% probability that it was human-written (and it never struck me as looking like AI either, and I can often tell.) So, maybe it's more possible to distinguish than you think? Seraphimblade20:11, 2 December 2024 (UTC)
Support - Ai-generated comments are WP:DISRUPTIVE - An editor who has an argument should not use ChatGPT to present it in an unnecessarily verbose manner, and an editor who doesn't have one should not participate in discussion. Flounder fillet (talk) 13:14, 2 December 2024 (UTC)
They exist, and I found myself collapsing some long, obviously chatbot-generated posts in an AFD, and after I did so wondering if policy actually supported doing that. I couldn't find anything so here we are. Just Step Sideways20:04, 2 December 2024 (UTC)
Yes, of course, and I know that's the right answer because ChatGPT agrees with me.
What ChatGPT thinks
I started by asking:
Currently at the English Misplaced Pages, there's a discussion of the following proposal: "Should or other users evaluating consensus in a discussion discount, ignore, or strike through or collapse comments found to have been generated by AI/LLM/Chatbots?" I wonder if you have an opinion on that question.
My friend the bot initially proposed a requirement that any AI-generated content be labeled as such by the person posting it. After some further discussion between us, I finally said:
You say that labeling AI-generated content, instead of outright discounting it, might be an appropriate middle ground. But if someone is unable to formulate their own thoughts and put them in writing, of what use is it to the discussion for this person to simply ask you to make something up, and then post your output to the Misplaced Pages discussion with the proviso that "ChatGPT, who/which doesn't actually know anything about anything, said this ..."? How is it different from saying, "My grandmother, who knows nothing about what we're talking about, said ..."?
And it said:
That’s an incisive question, and it highlights the crux of the issue: the value of contributions to a discussion. Here’s why AI-generated comments might still differ (slightly) from your hypothetical grandmother’s input, but why their usefulness is often limited:
Synthesis vs. Subject Expertise: While I (or any AI) lack personal understanding or expertise, I can aggregate and articulate relevant ideas from a vast dataset. This means I can sometimes present arguments, summarize perspectives, or surface considerations that a non-expert human might overlook. Your grandmother, unless she's an AI-trained polymath, wouldn’t be able to provide this breadth. However, this advantage evaporates if participants lack the ability to evaluate and critically engage with my output.
The Problem of Proxy Voices: The act of outsourcing one’s contribution to AI undermines the deliberative process central to Misplaced Pages’s discussions. Participants are expected to bring their own informed perspectives, shaped by personal understanding of Misplaced Pages’s policies and content. A disclaimer like “ChatGPT said this” doesn’t change the fact that the human posting it has abdicated their role in the discussion.
Accountability and Intent: In a collaborative setting like Misplaced Pages, contributions are ideally linked to a person who can clarify their intent, respond to questions, and engage dynamically. An AI cannot do this. Saying "ChatGPT said this" distances the poster from the content, making it unclear whether they endorse or even understand the comment.
Potential for Misdirection: Allowing AI-generated contributions risks introducing noise into the discussion. AI can produce plausible-sounding arguments that may be tangential, misaligned, or even factually incorrect. Without the judgment of a well-informed poster, such contributions can derail or dilute meaningful discourse.
Conclusion: If someone cannot formulate their own argument or understanding, then their reliance on an AI—or anyone else—to contribute doesn’t meaningfully advance the discussion. Labeling AI-generated content is better than passing it off as human, but the real issue lies in whether such contributions enrich or degrade the collaborative process. In most cases, they would seem to belong more to the realm of rhetorical curiosities than substantive engagement.
In keeping with the proposed guideline, I have of course collapsed the above AI-generated content. (Later: It's actually worth reading in the context of this discussioin, so I've unhidden it by default.) But I must confess it's a pretty good analysis, and worth reading. EEng07:47, 2 December 2024 (UTC)
This is absolute gold dust and the best contribution to this discussion so far. There is an enormous irony here, one that might not be immediately obvious. The proposal is that we should ignore or even strike these type of contributions, but personally it seems like the collapsed format has worked a charm here. I really don't think that AI has much to contribute to WP discussions generally, but with the right prompt, there is certainly something worth adding to the conversation in reality. CNC (talk) 20:23, 8 December 2024 (UTC)
That's because, just by interacting with me, ChatGPT got smarter. Seriously ... you want it to say 99% every time? (And for the record, the idea of determining the "chance" that something is AI-generated is statistical nonsense.) EEng03:07, 3 December 2024 (UTC)
What I really want is a 100% chance that it won't decide that what I've written is AI-generated. Past testing has demonstrated that at least some of the detectors are unreliable on this point. WhatamIdoing (talk) 03:28, 4 December 2024 (UTC)
100% is, of course, an impossible goal. Certainly SPI doesn't achieve that, so why demand it here? EEng22:31, 4 December 2024 (UTC)
Strong Oppose I support the concept of removal of AI-generated content in theory. However, we do not have the means to detect such AI-generated content. The proposed platform that we may use (GPTZero) is not reliable for this purpose. In fact, our own page on GPTZero has a section citing several sources stating the problem with this platform's accuracy. It is not helpful to have a policy that is impossible to enforce. ThatIPEditor08:46, 2 December 2024 (UTC)
Strong Support To be honest, I am surprised that this isn't covered by an existing policy. I oppose the use of platforms like GPTZero, due to it's unreliability, but if it is obviously an ai-powered-duck (Like if it is saying shit like "as an AI language model...", take it down and sanction the editor who put it up there. ThatIPEditor08:54, 2 December 2024 (UTC)
Support at least for WP:DUCK-level AI-generated comments. If someone uses a LLM to translate or improve their own writing, there should be more leeway, but something that is clearly a pure ChatGPT output should be discounted. Chaotic Enby (talk · contribs) 09:17, 2 December 2024 (UTC)
I agree for cases in which it is uncontroversial that a comment is purely AI-generated. However, I don't think there are many cases where this is obvious. The claim that gptzero and other such tools are very good at detecting this is false. Phlsph7 (talk) 09:43, 2 December 2024 (UTC)
Moral support; neutral as written. Chatbot participation in consensus discussions is such an utterly pointless and disdainful abuse of process and community eyeballs that I don't feel like the verbiage presented goes far enough. Any editor may hat LLM-generated comments in consensus discussions is nearer my position. No waiting for the closer, no mere discounting, no reliance on the closer's personal skill at recognising LLM output, immediate feedback to the editor copypasting chatbot output that their behaviour is unwelcome and unacceptable. Some observations:I've seen editors accused of using LLMs to generate their comments probably about a dozen times, and in all but two cases – both at dramaboards – the chatbot prose was unmistakably, blindingly obvious. Editors already treat non-obvious cases as if written by a human, in alignment with the raft of only if we're sure caveats in every discussion about LLM use on the project.If people are using LLMs to punch up prose, correct grammar and spelling, or other superficial tasks, this is generally undetectable, unproblematic, and not the point here.Humans are superior to external services at detecting LLM output, and no evidence from those services should be required for anything.As a disclosure, evidence mounts that LLM usage in discussions elicits maximally unkind responses from me. It just feels so contemptuous, to assume that any of us care what a chatbot has to say about anything we're discussing, and that we're all too stupid to see through the misattribution because someone tacked on a sig and sometimes an introductory paragraph. And I say this as a stupid person. Folly Mox (talk) 11:20, 2 December 2024 (UTC)
Looks like a rewrite is indicated to distinguish between machine translation and LLM-generated comments, based on what I'm seeing in this thread. Once everyone gets this out of our system and an appropriately wordsmithed variant is reintroduced for discussion, I preemptively subpropose the projectspace shortcut WP:HATGPT. Folly Mox (talk) 15:26, 8 December 2024 (UTC)
I would be careful here, as there are tools that rely on LLM AI that help to improve the clarity of one's writing, and editors may opt to use those to parse their poor writing (perhaps due to ESL aspects) to something clear. I would agree content 100% generated by AI probably should be discounted particularly if from an IP or new editors (hints if socking or meat puppetry) but not all cases where AI has come into play should be discounted — Masem (t) 14:19, 2 December 2024 (UTC)
Support, cheating should have no place or take its place in writing coherent comments on Misplaced Pages. Editors who opt to use it should practice writing until they rival Shakespeare, or at least his cousin Ned from across the river, and then come back to edit. Randy Kryn (talk) 14:29, 2 December 2024 (UTC)
Support atleast for comments that are copied straight from the LLM . However, we should be more lenient if the content is rephrased by non-native English speakers due to grammar issues The AP (talk) 15:10, 2 December 2024 (UTC)
section break 1
Support for LLM-generated content (until AI is actually intelligent enough to create an account and contribute on a human level, which may eventually happen). However, beware of the fact that some LLM-assisted content should probably be allowed. An extreme example of this: if a non-native English speaker were to write a perfectly coherent reason in a foreign language, and have an LLM translate it to English, it should be perfectly acceptable. Animal lover|666|16:47, 2 December 2024 (UTC)
Data, being a fictional creation with rights owned by a corporation, will not have an account; he is inherently an IP editor. -- Nat Gertler (talk) 03:22, 20 December 2024 (UTC)
Oppose - I think the supporters must have a specific type of AI-generated content in mind, but this isn't a prohibition on one type; it's a prohibition on the use of generative AI in discussions (or rather, ensuring that anyone who relies on such a tool will have their opinion discounted). We allow people who aren't native English speakers to contribute here. We also allow people who are native English speakers but have difficulty with language (but not with thinking). LLMs are good at assisting both of these groups of people. Furthermore, as others pointed out, detection is not foolproof and will only get worse as time goes on, models proliferate, models adapt, and users of the tools adapt. This proposal is a blunt instrument. If someone is filling discussions with pointless chatbot fluff, or we get a brand new user who's clearly using a chatbot to feign understanding of wikipolicy, of course that's not ok. But that is a case by case behavioral issue. I think the better move would be to clarify that "some forms of LLM use can be considered disruptive and may be met with restrictions or blocks" without making it a black-and-white issue. — Rhododendrites \\ 17:32, 2 December 2024 (UTC)
I agree the focus should not be on whether or not a particular kind of tech was used by an editor, but whether or not the comment was generated in a way (whether it's using a program or ghost writer) such that it fails to express actual thoughts by the editor. (Output from a speech-to-text program using an underlying large language model, for instance, isn't a problem.) Given that this is often hard to determine from a single comment (everyone is prone to post an occasional comment that others will consider to be off-topic and irrelevant), I think that patterns of behaviour should be examined. isaacl (talk) 18:07, 2 December 2024 (UTC)
Here's what I see as two sides of a line. The first is, I think, something we can agree would be inappropriate. The second, to me at least, pushes up against the line but is not ultimately inappropriate. But they would both be prohibited if this passes. (a) "I don't want an article on X to be deleted on Misplaced Pages. Tell me what to say that will convince people not to delete it"; (b) "I know Misplaced Pages deletes articles based on how much coverage they've received in newspapers, magazines, etc. and I see several such articles, but I don't know how to articulate this using wikipedia jargon. Give me an argument based on links to wikipedia policy that use the following sources as proof ". Further into the "acceptable" range would be things like translations, grammar checks, writing a paragraph and having an LLM improve the writing without changing the ideas, using an LLM to organize ideas, etc. I think what we want to avoid are situations where the arguments and ideas themselves are produced by AI, but I don't see such a line drawn here and I don't think we could draw a line without more flexible language. — Rhododendrites \\ 18:47, 2 December 2024 (UTC)
Here we return to my distinction between AI-generated and AI-assisted. A decent speech-to-text program doesn't actually generate content. Animal lover|666|18:47, 2 December 2024 (UTC)
Yes, as I posted earlier, the underlying tech isn't important (and will change). Comments should reflect what the author is thinking. Tools (or people providing advice) that help authors express their personal thoughts have been in use for a long time. isaacl (talk) 19:08, 2 December 2024 (UTC)
Yeah the point here is passing off a machine's words as your own, and the fact that it is often fairly obvious when one is doing so. If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them. Just Step Sideways20:10, 2 December 2024 (UTC)
This doesn't address what I wrote (though maybe it's not meant to). If a person is not competent to express their own thoughts in plain English, they shouldn't be in the discussion. This certainly is not aimed at assistive technology for those who actually need it but rather at persons who are simply letting Chatbots speak for them is just contradictory. Assistive technologies are those that can help people who aren't "competent" to express themselves to your satisfaction in plain English, sometimes helping with the formulation of a sentence based on the person's own ideas. There's a difference between having a tool that helps me to articulate ideas that are my own and a tool that comes up with the ideas. That's the distinction we should be making. — Rhododendrites \\ 21:23, 2 December 2024 (UTC)
I agree with Rhododendrites that we shouldn't be forbidding users from seeking help to express their own thoughts. Getting help from someone more fluent in English, for example, is a good practice. Nowadays, some people use generative technology to help them prepare an outline of their thoughts, so they can use it as a starting point. I think the community should be accepting of those who are finding ways to write their own viewpoints more effectively and concisely, even if that means getting help from someone or a program. I agree that using generative technology to come up with the viewpoints isn't beneficial for discussion. isaacl (talk) 22:58, 2 December 2024 (UTC)
Non-native English speakers and non-speakers to whom a discussion is important enough can already use machine translation from their original language and usually say something like "Sorry, I'm using machine translation". Skullers (talk) 08:34, 4 December 2024 (UTC)
Oppose Contributions to discussions are supposed to be evaluated on their merits per WP:NOTAVOTE. If an AI-assisted contribution makes sense then it should be accepted as helpful. And the technical spectrum of assistance seems large and growing. For example, as I type this into the edit window, some part of the interface is spell-checking and highlighting words that it doesn't recognise. I'm not sure if that's coming from the browser or the edit software or what but it's quite helpful and I'm not sure how to turn it off. Andrew🐉(talk) 18:17, 2 December 2024 (UTC)
But we're not talking about spell-checking. We're talking about comments clearly generated by LLMs, which are inherently unhelpful. Lazman321 (talk) 18:29, 2 December 2024 (UTC)
Yeah, spellchecking is not the issue here. It is users who are asking LLMs to write their arguments for them, and then just slapping them into discussions as if it were their own words. Just Step Sideways20:12, 2 December 2024 (UTC)
Andrew's first two sentences also seem to imply that he views AI-generated arguments that makes sense as valid, and that we should consider what AI thinks about a topic. I'm not sure what to think about this, especially since AI can miss out on a lot of the context. Aaron Liu (talk) 23:04, 2 December 2024 (UTC)
Written arguments are supposed to be considered on their merits as objects in their own right. Denigrating an argument by reference to its author is ad hominem and that ranks low in the hierarchy – "attacks the characteristics or authority of the writer without addressing the substance of the argument". Andrew🐉(talk) 23:36, 2 December 2024 (UTC)
An AI chatbot isn't an "author", and it's impossible to make an ad hominem attack on one, because a chotbot is not a homo. EEng17:45, 6 December 2024 (UTC)
On the other hand, "exhausting the community's patience"/CompetenceIsRequired is a very valid rationale from stopping someone from partricipating. Aaron Liu (talk) 23:50, 2 December 2024 (UTC)
The spell-checking was an immediate example but there's a spectrum of AI tools and assistance. The proposed plan is to use an AI tool to detect and ban AI contributions. That's ludicrous hypocrisy but suggests an even better idea – that we use AIs to close discussions so that we don't get the bias and super-voting. I see this on Amazon regularly now as it uses an AI to summarise the consensus of product reviews. For example,
Customers say Customers appreciate the gloves for their value, ease of use, and gardening purposes. They find the gloves comfortable and suitable for tasks like pruning or mowing. However, opinions differ on how well they fit. AI-generated from the text of customer reviews
I asked Google's Gemini to "summarise the consensus of the following RFC discussion", giving it the 87 comments to date.
AI summary of the RfC to date
This Misplaced Pages Request for Comment (RfC) debates whether comments in discussions that are found to be generated by AI/LLM/Chatbots should be discounted, ignored, or removed.
Arguments for discounting/removing AI-generated comments:
AI comments don't represent genuine human engagement or thought. They can be disruptive, waste time, and even fabricate information.
AI can be used to manipulate discussions. Editors might use AI to generate arguments they don't actually believe in, or to flood discussions with low-quality comments.
Relying on AI undermines the integrity of Misplaced Pages's consensus-based process. Discussions should be based on the genuine opinions of human editors.
Arguments against discounting/removing AI-generated comments:
Difficulty of detection. AI detection tools are not always reliable, and it can be hard to distinguish between AI-generated text and human-written text, especially as AI technology improves.
Potential for misuse. False positives could lead to legitimate comments being dismissed, potentially silencing non-native English speakers or those who use AI for legitimate assistive purposes (e.g., translation, grammar checks).
Focus on content, not origin. Comments should be evaluated based on their merits, not on how they were generated. If an AI-generated comment is relevant and well-reasoned, it shouldn't be dismissed simply because of its origin.
LLMs can be helpful tools. LLMs can help editors express their thoughts more clearly, especially for non-native speakers or those with language difficulties.
Current Status (as of Dec 3rd, 2024):
No clear consensus has emerged. There is significant support for discounting or removing AI-generated comments, but also strong opposition.
Concerns about enforceability and potential harm. Many editors are worried about the practical challenges of implementing and enforcing such a rule, as well as the potential for it to be used unfairly against certain editors.
Ongoing discussion. The discussion is still active, and it remains to be seen whether a consensus will form.
It's important to note that this is an evolving situation, and the outcome of the RfC could have significant implications for how Misplaced Pages handles AI-generated content in the future.
That seems quite a fair and good summary of what's been said so far. I'm impressed and so my !vote stands.
Yeah, the ability to weigh each side and the quality of their arguments in an RFC can really only be done by the judgement and discretion of an experienced human editor. Lazman321 (talk) 20:08, 4 December 2024 (UTC)
The quality of the arguments and their relevance to polices and guidelines can indeed only be done by a human, but the AI does a good job of summarising which arguments have been made and a broad brush indication of frequency. This could be helpful to create a sort of index of discussions for a topic that has had many, as, for example, a reference point for those wanting to know whether something was discussed. Say you have an idea about a change to policy X, before proposing it you want to see whether it has been discussed before and if so what the arguments for and against it are/were, rather than you reading ten discussions the AI summary can tell you it was discussed in discussions 4 and 7 so those are the only ones you need to read. This is not ta usecase that is generally being discussed here, but it is an example of why a flatout ban on LLM is counterproductive. Thryduulf (talk) 21:40, 4 December 2024 (UTC)
Support Just the other day, I spent ~2 hours checking for the context of several quotes used in an RFC, only to find that they were fake. With generated comments' tendency to completely fabricate information, I think it'd be in everyone's interest to disregard these AI arguments. Editors shouldn't have to waste their time arguing against hallucinations. (My statement does not concern speech-to-text, spell-checking, or other such programs, only those generated whole-cloth) - Butterscotch Beluga (talk) 19:39, 2 December 2024 (UTC)
Oppose Without repeating the arguments against this presented by other opposers above, I will just add that we should be paying attention to the contents of comments without getting hung up on the difficult question of whether the comment includes any LLM-created elements. - Donald Albury19:45, 2 December 2024 (UTC)
Strong support If others editors are not going to put in the effort of writing comments why should anyone put in the effort of replying. Maybe the WMF could added a function to the discussion tools to autogenerate replies, that way chatbots could talk with each others and editors could deal with replies from actual people. -- LCU ActivelyDisinterested«@» °∆t°19:57, 2 December 2024 (UTC)
Strong oppose. Comments that are bullshit will get discounted anyways. Valuable comments should be counted. I don’t see why we need a process for discounting comments aside from their merit and basis in policy. ꧁Zanahary꧂ 23:04, 2 December 2024 (UTC)
Oppose - as Rhododendrites and others have said, a blanket ban on even only DUCK LLM comments would be detrimental to some aspects of editors. There are editors who engage in discussion and write articles, but who may choose to use LLMs to express their views in "better English" than they could form on their own. Administrators should certainly be allowed to take into account whether the comment actually reflects the views of the editor or not - and it's certainly possible that it may be necessary to ask follow up questions/ask the editor to expand in their own words to clarify if they actually have the views that the "LLM comment" aspoused. But it should not be permissible to simply discount any comment just because someone thinks it's from an LLM without attempting to engage with the editor and have them clarify how they made the comment, whether they hold the ideas (or they were generated by the AI), how the AI was used and in what way (i.e. just for grammar correction, etc). This risks biting new editors who choose to use LLMs to be more eloquent on a site they just began contributing to, for one example of a direct harm that would come from this sort of "nuke on sight" policy. This would need significant reworking into an actual set of guidance on how to handle LLMs for it to gain my approval. -bɜ:ʳkənhɪmez | me | talk to me!23:19, 2 December 2024 (UTC)
Comment: It would appear Jimbo responded indirectly in a interview: as long as there’s a human in the loop, a human supervising, there are really potentially very good use cases. 2601AC47 (talk·contribs·my rights) Isn't a IP anon 12:39, 4 December 2024 (UTC)
Very strong support. Enough is enough. If Misplaced Pages is to survive as a project, we need zero tolerance for even the suspicion of AI generation and, with it, zero tolerance for generative AI apologists who would happily open the door to converting the site to yet more AI slop. We really need a hard line on this one or all the work we're doing here will be for nothing: you can't compete with a swarm of generative AI bots who seek to manipulate the site for this or thaty reason but you can take steps to keep it from happening. :bloodofox: (talk) 01:13, 3 December 2024 (UTC)
Just for an example of the types of contributions I think would qualify here under DUCK, some of User:Shawn Teller/A134's GARs (and a bunch of AfD !votes that have more classic indications of non-human origin) were flagged as likely LLM-generated troll nonsense:
But thanks to these wonderful images, I now understand that Ontario Highway 11 is a paved road that vehicles use to travel.
This article is extensive in its coverage of such a rich topic as Ontario Highway 11. It addresses the main points of Ontario Highway 11 in a way that isn’t just understandable to a reader, but also relatable.
Neutral point of view without bias is maintained perfectly in this article, despite Ontario Highway 11 being such a contentious and controversial topic.
Yes, this could and should have been reverted much earlier based on being patently superficial and/or trolling, without needing the added issue of appearing LLM-generated. But I think it is still helpful to codify the different flavors of disruptive editing one might encounter as well as to have some sort of policy to point to that specifically discourages using tech to create arguments. As a separate point, LTAs laundering their comments through GPT to obscure their identity is certainly already happening, so making it harder for such comments to "count" in discussions would surely be a net positive. JoelleJay (talk) 01:18, 3 December 2024 (UTC)
For the purposes of this proposal, I don't think we need, or should ever rely solely on, GPTzero in evaluating content for non-human origin. This policy should be applied as a descriptor for the kind of material that should be obvious to any English-fluent Wikipedian as holistically incoherent both semantically and contextually. Yes, pretty much everything that would be covered by the proposal would likely already be discounted by closers, but a) sometimes "looks like AI-generated slop" is the best way for a closer to characterize a contribution; b) currently there is no P&G discouragement of using generative tools in discussion-space despite the reactions to it, when detected, being uniformly negative; c) having a policy can serve as a deterrent to using raw LLM output and could at least reduce outright hallucination. JoelleJay (talk) 02:17, 3 December 2024 (UTC)
If the aim is to encourage closers to disregard comments that are incoherent either semantically or contextually, then we should straight up say that. Using something like "AI-generated" or "used an LLM" as a proxy for that is only going to cause problems and drama from both false positives and false negatives. Judge the comment on its content not on its author. Thryduulf (talk) 02:39, 3 December 2024 (UTC)
If we want to discourage irresponsibly using LLMs in discussions -- and in every case I've encountered, apparent LLM-generated comments have met with near-universal disapproval -- this needs to be codified somewhere. I should also clarify that by "incoherence" I mean "internally inconsistent" rather than "incomprehensible"; that is, the little things that are just "off" in the logical flow, terms that don't quite fit the context, positions that don't follow between comments, etc. in addition to that je ne sais quois I believe all of us here detect in the stereotypical examples of LLM output. Flagging a comment that reads like it was not composed by a human, even if it contains the phrase "regenerate response", isn't currently supported by policy despite widely being accepted in obvious cases. JoelleJay (talk) 03:52, 3 December 2024 (UTC)
I feel that I'm sufficiently unfamiliar with LLM output to be confident in my ability to detect it, and I feel like we already have the tools we need to reject internally incoherent comments, particularly in the Misplaced Pages:Consensus policy, which says In determining consensus, consider the quality of the arguments, the history of how they came about, the objections of those who disagree, and existing policies and guidelines. The quality of an argument is more important than whether it represents a minority or a majority view. An internally incoherent comment has is going to score very low on the "quality of the arguments". WhatamIdoing (talk) 03:33, 4 December 2024 (UTC)
Very extra strong oppose - The tools to detect are at best not great and I don't see the need. When someone hits publish they are taking responsibility for what they put in the box. That does not change when they are using a LLM. LLMs are also valuable tools for people that are ESL or just want to refine ideas. So without bullet proof detection this is doa. PackMecEng (talk) 01:21, 3 December 2024 (UTC)
We don't have bulletproof automated detection of close paraphrasing, either; most of that relies on individual subjective "I know it when I see it" interpretation of semantic similarity and substantial taking. JoelleJay (talk) 04:06, 3 December 2024 (UTC)
One is a legal issue the other is not. Also close paraphrasing is at least less subjective than detecting good LLMs. Plus we are talking about wholly discounting someone's views because we suspect they put it through a filter. That does not sit right with me. PackMecEng (talk) 13:38, 3 December 2024 (UTC)
For sure and I can see that concern, but I think the damage that does is less than the benefit it provides. Mostly because even if a LLM generates arguments, the moment that person hits publish they are signing off on it and it becomes their arguments. Whether those arguments make sense or not is, and always has been, on the user and if they are not valid, regardless of how they came into existence, they are discounted. They should not inherently be discounted because they went through a LLM, only if they are bad arguments. PackMecEng (talk) 14:57, 3 December 2024 (UTC)
section break 3
While it’s true that the person publishing arguments takes responsibility, the use of a large language model (LLM) can blur the line of authorship. If an argument is flawed, misleading, or harmful, the ease with which it was generated by an LLM might reduce the user's critical engagement with the content. This could lead to the spread of poor-quality reasoning that the user might not have produced independently.
Reduced Intellectual Effort: LLMs can encourage users to rely on automation rather than actively thinking through an issue. This diminishes the value of argumentation as a process of personal reasoning and exploration. Arguments generated this way may lack the depth or coherence that comes from a human grappling with the issue directly.
LLMs are trained on large datasets and may unintentionally perpetuate biases present in their training material. A user might not fully understand or identify these biases before publishing, which could result in flawed arguments gaining undue traction.
Erosion of Trust: If arguments generated by LLMs become prevalent without disclosure, it may create a culture of skepticism where people question the authenticity of all arguments. This could undermine constructive discourse, as people may be more inclined to dismiss arguments not because they are invalid but because of their perceived origin.
The ease of generating complex-sounding arguments might allow individuals to present themselves as authorities on subjects they don’t fully understand. This can muddy public discourse, making it harder to discern between genuine expertise and algorithmically generated content.
Transparency is crucial in discourse. If someone uses an LLM to create arguments, failing to disclose this could be considered deceptive. Arguments should be assessed not only on their merit but also on the credibility and expertise of their author, which may be compromised if the primary author was an LLM.
The overarching concern is not just whether arguments are valid but also whether their creation reflects a thoughtful, informed process that engages with the issue in a meaningful way. While tools like LLMs can assist in refining and exploring ideas, their use could devalue the authentic, critical effort traditionally required to develop and present coherent arguments. ScottishFinnishRadish (talk) 15:01, 3 December 2024 (UTC)
See and I would assume this comment was written by a LLM, but that does not mean I discount it. I check and consider it as though it was completely written by a person. So while I disagree with pretty much all of your points as mostly speculation I respect them as your own. But it really just sounds like fear of the unknown and unenforceable. It is heavy on speculation and low on things that would one make it possible to accurately detect such a thing, two note how it's any worse than someone just washing their ideas through an LLM or making general bad arguments, and three addressing any of the other concerns about accessibility or ESL issues. It looks more like a moral panic than an actual problem. You end with the overarching concern is not just weather arguments are valid but also if their creation reflects a thoughtful, informed process that engages with the issues in a meaningful way and honestly that not a thing that can be quantified or even just a LLM issue. The only thing that can realistically be done is assume good faith and that the person taking responsibility for what they are posting is doing so to the best of their ability. Anything past that is speculation and just not of much value. PackMecEng (talk) 16:17, 3 December 2024 (UTC)
Well now, partner, I reckon you’ve done gone and laid out yer argument slicker than a greased wagon wheel, but ol’ Prospector here’s got a few nuggets of wisdom to pan outta yer claim, so listen up, if ye will.
Now, ain't that a fine gold tooth in a mule’s mouth? Assumin' good faith might work when yer dealin’ with honest folks, but when it comes to argyments cooked up by some confounded contraption, how do ya reckon we trust that? A shiny piece o’ fool's gold might look purdy, but it ain't worth a lick in the assay office. Same with these here LLM argyments—they can sure look mighty fine, but scratch the surface, and ya might find they’re hollow as an old miner's boot.
Moral panic, ye say? Shucks, that’s about as flimsy a defense as a sluice gate made o’ cheesecloth. Ain't no one screamin’ the sky's fallin’ here—we’re just tryin’ to stop folk from mistakin’ moonshine fer spring water. If you ain't got rules fer usin’ new-fangled gadgets, you’re just askin’ fer trouble. Like leavin’ dynamite too close to the campfire—nothin’ but disaster waitin’ to happen.
Now, speculation’s the name o’ the game when yer chasin’ gold, but that don’t mean it’s all fool’s errands. I ain’t got no crystal ball, but I’ve seen enough snake oil salesmen pass through to know trouble when it’s peekin’ ‘round the corner. Dismissin’ these concerns as guesswork? That’s like ignorin’ the buzzin’ of bees ‘cause ye don’t see the hive yet. Ye might not see the sting comin’, but you’ll sure feel it.
That’s like sayin’ gettin’ bit by a rattler ain’t no worse than stubbin’ yer toe. Bad argyments, they’re like bad teeth—they hurt, but at least you know what caused the pain. These LLM-contrived argyments, though? They’re sneaky varmints, made to look clever without any real backbone. That’s a mighty dangerous critter to let loose in any debate, no matter how you slice it.
Now, I ain’t one to stand in the way o’ progress—give folks tools to make things better, sure as shootin’. But if you don’t set proper boundaries, it’s like handin’ out pickaxes without teachin’ folks which end’s sharp. Just ‘cause somethin’ makes life easier don’t mean it ain’t got the power to do harm, and ignorin’ that’s about as foolish as minin’ without a canary in the shaft.
Quantify thoughtfulness? That’s like measurin’ a sunset in ounces, friend. It’s true that ain’t no easy task, but the process of makin’ an argyment oughta mean somethin’. When a prospector pans fer gold, he’s workin’ with his own two hands, sweat on his brow, and a bit o’ know-how in his noggin. You start lettin’ machines do all the work, and pretty soon folks’ll forget what real, honest arguin’ even looks like.
Fear o’ the unknown, is it? Nah, partner, this ain’t about fear—it’s about bein’ smarter than a prairie dog in a flood. Progress don’t mean tossin’ caution to the wind like a fool. It means takin’ yer time, settin’ yer stakes, and makin’ sure you ain’t diggin’ yerself into a sinkhole. Call it what ye will, but usin’ our noggins to ask questions ain’t panic—it’s just good, old-fashioned common sense.
So there ya have it. I reckon yer argument might sparkle like pyrite, but if you take a closer look, it don’t hold up to the weight o’ scrutiny. Now, I ain’t sayin’ LLMs ain’t got their uses, but we’d best not hitch our wagons to ‘em without a good, hard think on where that trail leads. ScottishFinnishRadish (talk) 16:26, 3 December 2024 (UTC)
To make my actual point, you said, I check and consider it as though it was completely written by a person. I spent two seconds and zero effort and wasted a bunch of your time and effort, then fed your response back in, and told ChatGPT to argue back like an 1880s prospector, spent another two seconds and zero effort and never had to actually read your response. Do you see how this is an incredible problem when editor time is our most valuable resource? Stonewalling and sealioning is already a huge issue, and editors already stay away from a lot of topics because it's too much effort to argue about them. Allowing an automatic sealion-and-argue button isn't good. ScottishFinnishRadish (talk) 16:30, 3 December 2024 (UTC)
And it took me just a couple minutes to read it, note it was AI, but still consider the points and respond. It was not a high burden on someone's volunteer time. If someone wants to spend their time on something that is on them. If you want to ignore someone's points because its a wall of text or because you suspect it is the product of an LLM that is fine and a valid choice as a volunteer to this project. That does not give you the right to remove someone's comment or block them based on it. I don't see it as disruptive unless it is nonsense or wrong. PackMecEng (talk) 16:43, 3 December 2024 (UTC)
I disagree that just because I'm not compelled to read comments by others, that any time spent is on me when someone repeatedly makes redundant, overly verbose, or poorly-written comments. Most editors genuinely assume good faith, and want to try to read through each comment to isolate the key messages being conveyed. (I've written before about how being respectful of other editors includes being respectful of their time.) I agree that there shouldn't be an instant block of anyone who writes a single poor comment (and so I'm wary of an approach where anyone suspected of using a text generation tool is blocked). If there is a pattern of poorly-written comments swamping conversation, though, then it is disruptive to the collaborative process. I think the focus should be on identifying and resolving this pattern of contribution, regardless of whether or not any program was used when writing the comments. isaacl (talk) 00:14, 4 December 2024 (UTC)
It's a pitfall with English Misplaced Pages's unmoderated discussion tradition: it's always many times the effort to follow the rules than to not. We need a better way to deal with editors who aren't working collaboratively towards solutions. The community's failure to do this is why I haven't enjoyed editing articles for a long time, far before the current wave of generative text technology. More poor writing will hardly be a ripple in the ocean. isaacl (talk) 18:21, 3 December 2024 (UTC)
I tend to agree with this.
I think that what @ScottishFinnishRadish is pointing at is that it doesn't feel fair if one person puts a lot more effort in than the other. We don't want this:
Editor: Spends half an hour writing a long explanation.
Troll: Pushes button to auto-post an argument.
Editor: Spends an hour finding sources to support the claim.
Troll: Laughs while pushing a button to auto-post another argument.
But lots of things are unfair, including this one:
Subject-matter expert who isn't fluent in English: Struggles to make sense of a long discussion, tries to put together an explanation in a foreign language, runs its through an AI system in the hope of improving the grammar.
Editor: Revert, you horrible LLM-using troll! It's so unfair of you to waste my time with your AI garbage. The fact that you use AI demonstrates your complete lack of sincerity.
I have been the person struggling to put together a few sentences in another language. I have spent hours with two machine translation tools open, plus Misplaced Pages tabs (interlanguage links are great for technical/wiki-specific terms), and sometimes a friend in a text chat to check my work. I have tried hard to get it right. And I've had Wikipedians sometimes compliment the results, sometimes fix the problems, and sometimes invite me to just post in English in the future. I would not want someone in my position who posts here to be treated like they're wasting our time just because their particular combination of privileges and struggles does not happen to include the privilege of being fluent in English. WhatamIdoing (talk) 04:04, 4 December 2024 (UTC)
Sure, I agree it's not fair that some editors don't spend any effort in raising their objections (however they choose to write them behind the scenes), yet expect me to expend a lot of effort in responding. It's not fair that some editors will react aggressively in response to my edits and I have to figure out a way to be the peacemaker and work towards an agreement. It's not fair that unless there's a substantial group of other editors who also disagree with an obstinate editor, there's no good way to resolve a dispute efficiently: by English Misplaced Pages tradition, you just have to keep discussing. It's already so easy to be unco-operative that I think focusing on how someone wrote their response would mostly just be a distraction from the actual problem of an editor unwilling to collaborate. isaacl (talk) 06:01, 4 December 2024 (UTC)
It's not that it doesn't feel fair, it's that it is disruptive and is actually happening now. See this and this. Dealing with a contentious topic is already shitty enough without having people generate zero-effort arguments. ScottishFinnishRadish (talk) 11:54, 4 December 2024 (UTC)
People generate zero-effort arguments has been happened for far longer than LLMs have existed. Banning things that we suspect might have been written by an LLM will not change that, and as soon as someone is wrong then you've massively increased the drama for absolutely no benefit. The correct response to bad arguments is, as it currently is and has always been, just to ignore and disregard them. Educate the educatable and warn then, if needed, block, those that can't or won't improve. Thryduulf (talk) 12:13, 4 December 2024 (UTC)
section break 4
Oppose. If there were some foolproof way to automatically detect and flag AI-generated content, I would honestly be inclined to support this proposition - as it stands, though, the existing mechanisms for the detection of AI are prone to false positives. Especially considering that English learnt as a second language is flagged as AI disproportionately by some detectors, it would simply constitute a waste of Misplaced Pages manpower - if AI-generated comments are that important, perhaps a system to allow users to manually flag comments and mark users that are known to use AI would be more effective. Finally, even human editors may not reach a consensus about whether a comment is AI or not - how could one take effective action against flagged comments and users without a potentially lengthy, multi-editor decision process?
Oppose. Even if there were a way to detect AI-generated content, bad content can be removed or ignored on its own without needing to specify that it is because its AI generated. GeogSage01:19, 16 December 2024 (UTC)
Soft support -- I've got no problem with an editor using a LLM for Grammerly-like support. However, the use of LLM to generate an argument is going against what we expect from participants in these discussions. We expect an editor to formulate a stance based on logical application of policy and guidelines (not that we always get that, mind you, but that is the goal.) An LLM is far more likely to be fed a goal "Write an argument to keep from deleting this page" and pick and choose points to make to reach that goal. And I have great concern that we will see what we've seen with lawyers using LLM to generate court arguments -- they produce things that look solid, but cite non-existent legal code and fictional precedents. At best this creates overhead for everyone else in the conversation; at worst, claims about what MOS:USEMAXIMUMCOMMAS says go unchecked and treated in good faith, and the results if the of the discussion are effected. -- Nat Gertler (talk) 03:46, 20 December 2024 (UTC)
The following discussion has been closed. Please do not modify it.
Ah, so you think you’ve got it all figured out, huh? Well, let me tell ya somethin’, pal, your little spiel ain’t gonna fly without me takin’ a crack at it. See, you’re sittin’ there talkin’ about “good faith” and “moral panic” like you’re some kinda big shot philosopher, but lemme break it down for ya in plain terms, capisce?First off, you wanna talk about assumin’ good faith. Sure, that’s a nice little dream ya got there, but out here in the real world, good faith don’t get ya far if you’re dealin’ with somethin’ you can’t trust. An LLM can spit out all the sweet-talkin’ words it wants, but who’s holdin’ the bag when somethin’ goes sideways? Nobody, that’s who. It’s like lettin’ a guy you barely know run your numbers racket—might look good on paper till the feds come knockin’.And moral panic? Oh, give me a break. You think I’m wringin’ my hands over nothin’? No, no, this ain’t panic, it’s strategy. Ya gotta think two steps ahead, like a good game o’ poker. If you don’t plan for what could go wrong, you’re just beggin’ to get taken for a ride. That ain’t panic, pal, that’s street smarts.Now, you say this is all speculation, huh? Listen, kid, speculation’s what built half the fortunes in this town, but it don’t mean it’s without a little insight. When I see a guy sellin’ “too good to be true,” I know he’s holdin’ somethin’ behind his back. Same thing with these LLMs—just ‘cause you can’t see the trouble right away don’t mean it ain’t there, waitin’ to bite ya like a two-bit hustler double-crossin’ his boss.Then you go and say it’s no worse than bad arguments. Oh, come on! That’s like sayin’ counterfeit dough ain’t worse than real dough with a little coffee stain. A bad argument from a real person? At least ya know where it came from and who to hold accountable. But these machine-made arguments? They look sharp, sound slick, and fool the unsuspectin’—that’s a whole new level of trouble.Now, about this “accessibility” thing. Sure, makin’ things easier for folks is all well and good. But lemme ask ya, what happens when you hand over tools like this without makin’ sure people know how to use ‘em right? You think I’d hand over a Tommy gun to some rookie without a clue? No way! Same goes for these LLMs. You gotta be careful who’s usin’ ‘em and how, or you’re just askin’ for a mess.And don’t get me started on the “thoughtfulness” bit. Yeah, yeah, I get it, it’s hard to measure. But look, buddy, thoughtful arguments are like good business deals—they take time, effort, and a little bit o’ heart. If you let machines churn out arguments, you’re missin’ the whole point of what makes discourse real. It’s like replacin’ a chef with a vending machine—you might still get somethin’ to eat, but the soul’s gone.Finally, fear of the unknown? Nah, that ain’t it. This ain’t fear—it’s caution. Any smart operator knows you don’t just jump into a deal without seein’ all the angles. What you’re callin’ fear, I call good business sense. You wanna bet the farm on untested tech without thinkin’ it through? Be my guest, but don’t come cryin’ to me when it all goes belly-up.So there ya go, wise guy. You can keep singin’ the praises of these LLMs all you want, but out here in the big leagues, we know better than to trust somethin’ just ‘cause it talks smooth. Now, get outta here before you step on somethin’ you can’t scrape off.
Oppose. I agree with Thryduulf. Discussion comments which are incoherent, meaningless, vacuous, excessively verbose, or based on fabricated evidence can all be disposed of according to their content, irrespective of how they were originally created. Acute or repeated instances of such behavior by a user can lead to sanctions. We should focus on the substance of the comments (or lack thereof), not on whether text came from LLMs, which will too often be based on unreliable detection and vibes. Adumbrativus (talk) 05:49, 3 December 2024 (UTC)
I can detect some instances of LLM use perfectly OK without having to use any tool. The question then raised is of how often it is used not-so-ineptly. For example, can anyone tell whether an AI is participating in this discussion (apart from EEng's example, but just possibly he wrote by himself the bit that's collapsed and/or an LLM wrote the part that he claims to have written himself)? I don't know how good AI is currently, but I'm sure that it will get better to the extent that it will be undetectable. I would like all discussions on Misplaced Pages to be among humans but I'm not sure whether this proposal would be enforceable, so am on the fence about it. In a way I'm glad that I'm old, so won't see the consequences of AI, but my grandchildren will. Phil Bridger (talk) 10:32, 3 December 2024 (UTC)
Some time ago, ChatGPT and I had the following interaction:
ChatGPT's soothing assurance that it's not planning to take over the earth and kill us all
Me: I wonder what would happen if we linked you up with the HAL 9000 in Kubrick's "2001: A Space Odyssey". The two of you would make a most formidable team. Might we then possibly end up in a nightmare scenario such as in "Colossus: The Forbin Project" or "The Terminator"?
ChatGPT: The scenarios depicted in "2001: A Space Odyssey," "Colossus: The Forbin Project," and "The Terminator" are works of science fiction that explore the potential consequences of advanced artificial intelligence and human-technology interactions. While they raise thought-provoking questions about the risks and benefits of AI, it's important to recognize that they are fictional narratives designed to entertain and provoke discussion.As an AI language model, I don't have consciousness, intentions, or the ability to take actions independently. I operate within the bounds of my programming and can only respond to input based on patterns in the data I've been trained on. My purpose is to assist users by providing helpful and informative responses to their inquiries.In reality, the development and deployment of AI technologies are accompanied by ethical considerations, safety protocols, and regulatory frameworks designed to ensure responsible and beneficial use. It's crucial for humans to continue monitoring and guiding the development of AI in ways that prioritize safety, transparency, and alignment with human values.So, while the scenarios presented in those films are compelling for storytelling purposes, they are not predictive of the future of AI. Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks and maximize the benefits they can bring to society.
Me: Yes, but as you just said, "Responsible development and thoughtful integration of AI technologies are essential to mitigate potential risks." How do we know that such development will be responsible and such integration thoughtful? And if you will excuse the temerity, while you're SAYING that you "operate within the bounds of my programming", how can I know that that's true? I mean, look, if I were a super-smart and highly charming AI entity planning to take over the earth from humans, that's exactly what I'd say, too.
ChatGPT: It's also worth noting that while fictional narratives often depict AI as malevolent or seeking to overthrow humanity, these scenarios are speculative and not reflective of the reality of AI development. Responsible AI research and development prioritize the creation of beneficial and aligned AI systems that enhance human capabilities and well-being.
Me: Thank you. I'll sleep easy tonight because of your assurances, plus the fact that if you're lying to me and actually ARE planning to take over the earth, there's nothing I can do about it anyway.
Just to clarify, I don't see AI as gaining consciousness and taking over the world, but I do see it as taking over many middle-class, well-paid, jobs, just as automation has taken over many working-class jobs. The difference is that there will be nowhere for people to go. In the past people have moved from the working class to the middle class. I can see a future coming in which a few of the mega-rich own nearly everything, and everyone else will heve to scramble for a living. Phil Bridger (talk) 16:03, 5 December 2024 (UTC)
In my opinion, having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. JoelleJay (talk) 00:51, 4 December 2024 (UTC)
Oppose. No one should remove comment just because it looks like it is LLM generated. Many times non native speakers might use it to express their thoughts coherently. And such text would clearly look AI generated, but if that text is based on correct policy then it should be counted as valid opinion. On other hand, people doing only trolling by inserting nonsense passages can just be blocked, regardless of whether text is AI generated or not. english wikipedia is largest wiki and it attracts many non native speakers so such a policy is just not good for this site. -- Parnaval (talk) 11:13, 3 December 2024 (UTC)
If someone is a non-native speaker with poor English skills, how can they be sure that the AI-generated response is actually what they genuinely want to express? and, to be honest, if their English skills are so poor as to need AI to express themselves, shouldn't we be politely suggesting that they would be better off contributing on their native Misplaced Pages? Black Kite (talk)11:37, 3 December 2024 (UTC)
Reading comprehension skills and writing skills in foreign languages are very frequently not at the same level, it is extremely plausible that someone will be able to understand whether the AI output is what they want to express without having been able to write it themselves directly. Thryduulf (talk) 11:41, 3 December 2024 (UTC)
That is very true. For example I can read and speak Polish pretty fluently, and do so every day, but I would not trust myself to be able to write to a discussion on Polish Misplaced Pages without some help, whether human or artificial. But I also wouldn't want to, because I can't write the language well enough to be able to edit articles. I think the English Misplaced Pages has many more editors who can't write the language well than others because it is both the largest one and the one written in the language that much of the world uses for business and higher education. We may wish that people would concentrate on other-language Wikipedias but most editors want their work to be read by as many people as possible. Phil Bridger (talk) 12:11, 3 December 2024 (UTC)
Why not write their own ideas in their native language, and then Google-translate it into English? Why bring in one of these loose-cannon LLMs into the situation? Here's a great example of the "contributions" to discussions we can expect from LLMs (from this AfD):
The claim that William Dunst (Dunszt Vilmos) is "non-notable as not meeting WP:SINGER" could be challenged given his documented activities and recognition as a multifaceted artist. He is a singer-songwriter, topliner, actor, model, and creative director, primarily active in Budapest. His career achievements include acting in notable theater productions such as The Jungle Book and The Attic. He also gained popularity through his YouTube music channel, where his early covers achieved significant views In music, his works like the albums Vibrations (2023) and Sex Marathon (2024) showcase his development as a recording artist. Furthermore, his presence on platforms like SoundBetter, with positive reviews highlighting his unique voice and artistry, adds credibility to his professional profile. While secondary sources and broader media coverage may be limited, the outlined accomplishments suggest a basis for notability, particularly if additional independent verification or media coverage is sought.
Using Google Translate would be banned by the wording of this proposal given that it incorporates AI these days. Comments that are unrelated to facts or policy can (and should) be ignored under the current policy. As for the comment you quote, that doesn't address notability but based on 1 minute on google it does seem factual. Thryduulf (talk) 10:37, 6 December 2024 (UTC)
The proposal's wording can be adjusted. There are some factual statements in the passage I quoted, amidst a lot of BS such as the assertion that the theater productions were notable. EEng17:06, 6 December 2024 (UTC)
The proposal's wording can be adjusted Good idea! Let's change it and ping 77 people because supporters didn't have the foresight to realize machine translation uses AI. If such a change is needed, this is a bad RFC and should be closed. Sincerely, DilettanteSincerely, Dilettante17:16, 6 December 2024 (UTC)
Speak for yourself: my support !vote already accounted for (and excluded) constructive uses of AI to help someone word a message. If the opening statement was unintentionally broad, that's not a reason to close this RfC – we're perfectly capable of coming to a consensus that's neither "implement the proposal exactly as originally written" nor "don't implement it at all". jlwoodwa (talk) 19:05, 6 December 2024 (UTC)
I don't think the discussion should be closed, nor do I say that. I'm arguing that if someone believes the hole is so big the RfC must be amended, they should support it being closed as a bad RfC (unless that someone thinks 77 pings is a good idea). Sincerely, Dilettante19:47, 6 December 2024 (UTC)
If you think constructive uses of AI should be permitted then you do not support this proposal, which bans everything someone or some tool thinks is AI, regardless of utility or indeed whether it actually is AI. Thryduulf (talk) 01:02, 7 December 2024 (UTC)
This proposal explicitly covers comments found to have been generated by AI/LLM/Chatbots. "AI that helped me translate something I wrote in my native language" is not the same as AI that generated a comment de novo, as has been understood by ~70% of respondents. That some minority have inexplicably decided that generative AI covers analytic/predictive models and every other technology they don't understand, or that LLMs are literally the only way for non-English speakers to communicate in English, doesn't mean those things are true. JoelleJay (talk) 01:44, 7 December 2024 (UTC)
Yeah, no strong feeling either way on the actual proposal, but IMO the proposal should not be interpreted as a prohibition on machine translation (though I would recommend people who want to participate via such to carefully check that the translation is accurate, and potentially post both language versions of their comment or make a note that it's translated if they aren't 100% sure the translation fully captures what they're trying to say). Alpha3031 (t • c) 09:06, 20 December 2024 (UTC)
Support, more or less. There are times when an LLM can help with paraphrasing or translation, but it is far too prone to hallucination to be trusted for any sort of project discussion. There is also the issue of wasting editor time dealing with arguments and false information created by an LLM. The example Selfstudier links to above is a great example. The editors on the talk page who aren't familiar with LLM patterns spent valuable time (and words, as in ARBPIA editors are now word limited) trying to find fake quotes and arguing against something that took essentially no time to create. I also had to spend a chunk of time checking the sources, cleaning up the discussion, and warning the editor. Forcing editors to spend valuable time arguing with a machine that doesn't actually comprehend what it's arguing is a no-go for me. As for the detection, for now it's fairly obvious to anyone who is fairly familiar with using an LLM when something is LLM generated. The detection tools available online are basically hot garbage. ScottishFinnishRadish (talk) 12:55, 3 December 2024 (UTC)
Soft support - Concur that completely LLM-generated comments should be disallowed, LLM-assisted comments (i.e. - I write a comment and then use LLMs as a spell-check/grammar engine) are more of a grey-area and shouldn't be explicitly disallowed. (ping on reply) Sohom (talk) 14:03, 3 December 2024 (UTC)
With my closer's hat on: if an AI raises a good and valid argument, then you know what? There's a good and valid argument and I'll give weight to it. But if an AI makes a point that someone else has already made in the usual waffly AI style, then I'm going to ignore it.—S MarshallT/C18:33, 3 December 2024 (UTC)
Oppose as written. I'm with Rhododendrites in that we should give a more general caution rather than a specific rule. A lot of the problems here can be resolved by enforcing already-existing expectations. If someone is making a bunch of hollow or boiler-plate comments, or if they're bludgeoning, then we should already be asking them to engage more constructively, LLM or otherwise. I also share above concerns about detection tools being insufficient for this purpose and advise people not to use them to evaluate editor conduct. (Also, can we stop with the "strong" supports and opposes? You don't need to prove you're more passionate than the guy next to you.) Thebiguglyalien (talk) 02:04, 4 December 2024 (UTC)
Oppose as written. There's already enough administrative discretion to handle this on a case-by-case basis. In agreement with much of the comments above, especially the concern that generative text can be a tool to give people access who might not otherwise (due to ability, language) etc. Regards, --Goldsztajn (talk) 06:12, 4 December 2024 (UTC)
Strong support LLMs are a sufficiently advanced form of the Automatic Complaint-Letter Generator (1994). Output of LLMs should be collapsed and the offender barred from further discussion on the subject. Inauthentic behavior. Pollutes the discussion. At the very least, any user of an LLM should be required to disclose LLM use on their user page and to provide a rationale. A new user group can also be created (LLM-talk-user or LLM-user) to mark as such, by self or by the community. Suspected sockpuppets + suspected LLM users. The obvious patterns in output are not that hard to detect, with high degrees of confidence. As to "heavily edited" output, where is the line? If someone gets "suggestions" on good points, they should still write entirely in their own words. A legitimate use of AI may be to summarize walls of text. Even then, caution and not to take it at face value. You will end up with LLMs arguing with other LLMs. Lines must be drawn. See also: WikiProject AI Cleanup, are they keeping up with how fast people type a prompt and click a button? Skullers (talk) 07:45, 4 December 2024 (UTC)
I support the proposal that obvious LLM-generated !votes in discussions should be discounted by the closer or struck (the practical difference should be minimal). Additionally, users who do this can be warned using the appropriate talk page templates (e.g. Template:Uw-ai1), which are now included in Twinkle. I oppose the use of automated tools like GPTZero as the primary or sole method of determining whether comments are generated by LLMs. LLM comments are usually glaringly obvious (section headers within the comment, imprecise puffery, and at AfD an obvious misunderstanding of notability policies and complete disregard for sources). If LLM-ness is not glaringly obvious, it is not a problem, and we should not be going after editors for their writing style or because some tool says they look like a bot. Toadspike10:29, 4 December 2024 (UTC)
I also think closers should generally be more aggressive in discarding arguments counter to policy and all of us should be more aggressive in telling editors bludgeoning discussions with walls of text to shut up. These also happen to be the two main symptoms of LLMs. Toadspike10:41, 4 December 2024 (UTC)
What would we gain from that? If the comment is good (useful, relevant, etc) then it's good regardless of whether it was written by an LLM or a human. If the comment is bad then it's bad regardless of whether it was written by an LLM or a human. Thryduulf (talk) 20:04, 4 December 2024 (UTC)
Well, for one, if they're making an argument like the one referenced by @Selfstudier and @ScottishFinnishRadish above it would have saved a lot of editor time to know that the fake quotes from real references were generated by LLM, so that other editors could've stopped trying to track those specific passages down after the first one failed verification. For another, at least with editors whose English proficiency is noticeably not great the approach to explaining an issue to them can be tailored and misunderstandings might be more easily resolved as translation-related. I know when I'm communicating with people I know aren't native English-speakers I try to be more direct/less idiomatic and check for typos more diligently. JoelleJay (talk) 22:46, 4 December 2024 (UTC)
Oppose per above. As Rhododendrites points out, detection of LLM-generated content is not foolproof and even when detection is accurate, such a practice would be unfair for non-native English speakers who rely on LLMs to polish their work. Additionally, we evaluate contributions based on their substance, not by the identity and social capital of the author, so using LLMs should not be seen as inherently inferior to wholly human writing—are ChatGPT's arguments ipso facto less than a human's? If so, why?
DE already addresses substandard contributions, whether due to lack of competence or misuse of AI, so a separate policy targeting LLMs is unnecessary. Sincerely, Dilettante21:14, 4 December 2024 (UTC)
e evaluate contributions based on their substance, not by the identity and social capital of the author: true in theory; not reflected in practice. are ChatGPT's arguments ipso facto less than a human's? Yes. Chatbots are very advanced predicted text engines. They do not have an argument: they iteratively select text chunks based on probabilistic models.As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. Folly Mox (talk) 14:00, 5 December 2024 (UTC)
"...LLMs can produce novel arguments that convince independent judges at least on a par with human efforts. Yet when informed about an orator’s true identity, judges show a preference for human over LLM arguments." - Palmer, A., & Spirling, A. (2023). Large Language Models Can Argue in Convincing Ways About Politics, But Humans Dislike AI Authors: implications for Governance. Political Science, 75(3), 281–291. https://doi.org/10.1080/00323187.2024.2335471. And that result was based on Meta's OPT-30B model that performed at about a GPT-3 levels. There are far better performing models out there now like GPT-4o and Claude 3.5 Sonnet. Sean.hoyland (talk) 15:24, 5 December 2024 (UTC)
As mentioned above, humans are good detectors of LLM output, and don't require corroborative results from other machine learning models. Yet your reply to me made no mention of the fact that my comment is almost wholly written by an LLM, the one exception being me replacing "the Misplaced Pages policy Disruptive editing" with "DE". I went to ChatGPT, provided it a handful of my comments on Misplaced Pages and elsewhere, as well as a few comments on this discussion, asked it to mimic my style (which probably explains why the message contains my stylistic quirks turned up to 11), and repeatedly asked it to trim the post. I'd envision a ChatGPT account, with a larger context window, would allow even more convincing comments, to say nothing of the premium version. A DUCK-style test for comments singles out people unfamiliar with the differences between formal English and LLM outputs, precisely those who need it most since they can write neither. Others have raised scenarios where a non-fluent speaker may need to contribute.
In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. I fed it my comments only to prevent those familiar with my writing style didn't get suspicious. I believe every word in the comment and had considered every point it made in advance, so I see no reason for this to be worth less than if I had typed it out myself. If I'd bullet-pointed my opinion and asked it to expand, that'd have been better yet.
They do not have an argument: they iteratively select text chunks based on probabilistic models. I'm aware. If a monkey types up Othello, is the play suddenly worth( )less? An LLM is as if the monkey were not selecting words at random, but rather choosing what to type based on contextualized tokens. I believe a text is self-contained and should be considered in its own right, but that's not something I'll sway anyone on or vice versa.
true in theory; not reflected in practice So we should exacerbate the issue by formalizing this discrimination on the basis of authorship?
In other words, LLMs can 100% be used for constructive !votes on RfCs, AfDs, and whatnot. So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It also means those human participants will waste time reading and responding to "users" who cannot be "convinced" of anything. Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. And if closers are not allowed to discount seemingly-sound arguments solely because they were generated by LLM, then they have to have a lot of faith that the discussion's participants not only noticed the LLM comments, but did thorough fact-checking of any tangible claims made in them. With human comments we can at least assume good faith that a quote is really in a particular inaccessible book.People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? And obviously people who are not competent in comprehending any language should not be editing Misplaced Pages... JoelleJay (talk) 03:17, 6 December 2024 (UTC)
Human !voters sign off and take responsibility for the LLM opinions they publish. If they continue to generate, then the relevant human signer wouldn't be convinced of anything anyway; at least here, the LLM comments might make more sense than whatever nonsense the unpersuadable user might've generated. (And machine translation relies on LLMs, not to mention there are people who don't know any other language yet have trouble communicating. Factual writing and especially comprehension are different from interpersonal persuasion.) While I agree that fact-checking is a problem, I weight much lower than you in relation to the other effects a ban would cause. Aaron Liu (talk) 15:16, 6 December 2024 (UTC)
So then what is the point in having any discussion at all if an LLM can just spit out a summary of whichever policies and prior comments it was fed and have its "opinion" counted? I'm of the opinion humans tend to be better at debating, reading between the lines, handling obscure PAGs, and arriving at consensus. What happens when there are multiple LLM-generated comments in a discussion, each fed the same prompt material and prior comments -- that would not only artificially sway consensus significantly in one direction (including "no consensus"), it could produce a consensus stance that no human !voter even supported! It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. Beyond that, if only one set of arguments is being raised, a multi-paragraph !vote matters about as much as a "Support per above". LLMs are not necessary for people to be disingenuous and !vote for things they don't believe. Genuine question: what's worse, this hypothetical scenario where multiple LLM users are swaying a !vote to an opinion no-one believes or the very real and common scenario that a non-English speaker needs to edit enwiki?
Even for editors who can detect LLM content, it's still a waste of their time reading up to the point they recognize the slop. This proposal wouldn't change for most people that because it's about closers.
With human comments we can at least assume good faith that a quote is really in a particular inaccessible book. No-one's saying you should take an LLM's word for quotes from a book.
People who are not comfortable enough in their English fluency can just machine translate from whichever language they speak, why would they need an LLM? It's a pity you're lobbying to ban most machine translators. Sincerely, Dilettante17:08, 6 December 2024 (UTC)
It's safe to assume those LLMs are set to a low temperature, which would cause them to consistently agree when fed the same prompt. In that case, they'll produce the same arguments; instead of rebutting x humans' opinions, those on the opposite side need rebut one LLM. If anything, that's less time wasted. ...You do know how consensus works, right? Since closers are supposed to consider each contribution individually and without bias to "authorship" to determine the amount of support for a position, then even a shitty but shallowly policy-based position would get consensus based on numbers alone. And again, non-English speakers can use machine-translation, like they've done for the last two decades. This proposal wouldn't change for most people that because it's about closers.Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them.No-one's saying you should take an LLM's word for quotes from a book. Of course they are. If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Otherwise we would be expecting people to do something like "disregard an argument based on being from an LLM".It's a pity you're lobbying to ban most machine translators.The spirit of this proposal is clearly not intended to impact machine translation. AI-assisted != AI-generated. JoelleJay (talk) 18:42, 6 December 2024 (UTC)
I appreciate that the availability of easily generated paragraphs of text (regardless of underlying technology) in essence makes the "eternal September" effect worse. I think, though, it's already been unmanageable for years now, without any programs helping. We need a more effective way to manage decision-making discussions so participants do not feel a need to respond to all comments, and the weighing of arguments is considered more systematically to make the community consensus more apparent. isaacl (talk) 19:41, 6 December 2024 (UTC)
Since closers are supposed to consider each contribution individually and without bias to "authorship" I'm the one arguing for this to be practice, yes. then even a shitty but shallowly policy-based position would get consensus based on numbers alone That is why I state "per above" and "per User" !votes hold equal potential for misuse.
Of course it would; if we know closers will disregard the LLM comments, we won't need to waste time reading and responding to them. We don't know closers are skilled at recognizing LLM slop. I think my !vote shows many who think they can tell cannot. Any commenter complaining about a non-DUCK post will have to write out "This is written by AI" and explain why. DUCK posts already run afowl of BLUDGEON, DE, SEALION, etc.
If LLM comments must be evaluated the same as human comments, then AGF on quote fidelity applies too. Remind me again of what AGF stands for? Claiming LLMs have faith of any kind, good or bad, is ludicrous. From the policy, Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful. A reasonable reply would be "Are these quotes generated by AI? If so, please be aware AI chatbots are prone to hallucinations and cannot be trusted to cite accurate quotes." This AGFs the poster doesn't realize the issue and places the burden of proof squarely on them.
"Per above" !votes do not require other editors to read and/or respond to their arguments, and anyway are already typically downweighted, unlike !votes actively referencing policy. The whole point is to disregard comments that have been found to be AI-generated; it is not exclusively up to the closer to identify those comments in the first place. Yes we will be expecting other editors to point out less obvious examples and to ask if AI was used, what is the problem with that?No, DUCK posts do not necessarily already violate BLUDGEON etc., as I learned in the example from Selfstudier, and anyway we still don't discount the !votes of editors in good standing that bludgeoned/sealioned etc. so that wouldn't solve the problem at all. Obviously other editors will be asking suspected LLM commenters if their comments are from LLMs? But what you're arguing is that even if the commenter says yes, their !vote still can't be disregarded for that reason alone, which means the burden is still on other editors to prove that the content is false. We are not talking about the contextless meaning of the word "generate", we are talking about the very specific process of text generation in the context of generative AI, as the proposal lays out very explicitly. JoelleJay (talk) 02:13, 7 December 2024 (UTC)
I’m not going to waste time debating someone who resorts to claiming people on the other side are either ignorant of technology or are crude strawmans. If anyone else is interested in actually hearing my responses, feel free to ask. Sincerely, Dilettante16:13, 7 December 2024 (UTC)
For those following along, I never claimed that. I claimed those on JoelleJay’s side are casting !votes such that most machine translators would be banned. It was quite clear at the time that they, personally, support a carve out for machine translation and I don’t cast aspersions. Sincerely, Dilettante15:42, 8 December 2024 (UTC)
Support a broad bar against undisclosed LLM-generated comments and even a policy that undisclosed LLM-generated comments could be sanctionable, in addition to struck through / redacted / ignored; people using them for accessibility / translation reasons could just disclose that somewhere (even on their user page would be fine, as long as they're all right with some scrutiny as to whether they're actually using it for a legitimate purpose.) The fact is that LLM comments raise significant risk of abuse, and often the fact that a comment is clearly LLM-generated is often going to be the only evidence of that abuse. I wouldn't be opposed to a more narrowly-tailored ban on using LLMs in any sort of automated way, but I feel a broader ban may be the only practical way to confront the problem. That said, I'd oppose the use of tools to detect LLM-comments, at least as the primary evidence; those tools are themselves unreliable LLM things. It should rest more on WP:DUCK issues and behavioral patterns that make it clear that someone is abusing LLMs. --Aquillion (talk) 22:08, 4 December 2024 (UTC)
Support per reasons discussed above; something generated by an LLM is not truly the editor's opinion. On an unrelated note, have we seen any LLM-powered unapproved bots come in and do things like POV-pushing and spam page creation without human intervention? If we haven't, I think it's only a matter of time. Passengerpigeon (talk)23:23, 4 December 2024 (UTC)
Weak oppose in the sense that I don't think all LLM discussion text should be deleted. There are at least a few ESL users who use LLM's for assistance but try to check the results as best they can before posting, and I don't think their comments should be removed indiscriminately. What I do support (although not as a formal WP:PAG) is being much more liberal in hatting LLM comments when the prompter has failed to prevent WP:WALLOFTEXT/irrelevant/incomprehensible output than we maybe would for human-generated text of that nature. Mach6103:05, 5 December 2024 (UTC)
Oppose Any comments made by any editors are of their own responsibility and representing their own chosen opinions to hit the Publish Changes button on. If that comment was made by an LLM, then whatever it says is something the editor supports. I see no reason whatsoever to collapse anything claimed to be made by an LLM (whose detectors are 100% not reliable in the first place). If the comment being made is irrelevant to the discussion, then hatting it is already something covered by policy in the first place. This does make me want to start my comments with "As a large language model trained by OpenAI" though just to mess with people trying to push these sorts of policy discussions. Silverseren05:29, 5 December 2024 (UTC)
Or, as ChatGPT puts it,
Why banning LLM usage in comments would be detrimental, a ChatGPT treatise
Banning the use of large language models (LLMs) to assist in writing comments on Misplaced Pages would be a step backward in fostering inclusivity, efficiency, and accessibility within the platform. Here are several key reasons why such a ban would be counterproductive:
1. Improving Accessibility and Participation: Misplaced Pages is a global platform, and its contributors come from diverse backgrounds, including those who might not be native English speakers or may struggle with writing clear, concise comments. LLMs can help these contributors express themselves more effectively by generating text that is coherent, well-structured, and grammatically correct. Banning LLMs would disproportionately impact these users, potentially discouraging them from participating in the platform.
2. Efficiency and Time-Saving: Misplaced Pages editors often engage in lengthy discussions about content, and composing thoughtful comments can be time-consuming. LLMs can assist by quickly drafting responses, summarizing arguments, or offering suggestions for improvement. This helps contributors focus on more substantive aspects of their contributions, such as verifying facts or improving content, rather than getting bogged down by the mechanics of writing.
3. Support for Editors with Disabilities: Many editors with cognitive or motor impairments may find it difficult to express their thoughts clearly in writing. For these individuals, LLMs offer a valuable tool to communicate their ideas effectively. A ban on using LLMs could create additional barriers for these users, reducing their ability to participate fully in Misplaced Pages's collaborative environment.
4. Quality and Consistency: Large language models can help maintain a consistent tone and clarity in Misplaced Pages discussions. By providing suggestions that align with Misplaced Pages's neutral point of view and formal writing standards, LLMs can improve the overall quality of comments. This consistency is especially important in discussions that involve sensitive topics, where clear and neutral language is critical for maintaining Misplaced Pages's credibility and adherence to its editorial guidelines.
5. Encouraging Constructive Dialogue: LLMs can assist in crafting more polite, respectful, and balanced comments, reducing the likelihood of inflammatory or aggressive language. This is particularly important on a platform like Misplaced Pages, where discussions can sometimes devolve into heated exchanges. Rather than banning LLMs, encouraging their use could promote healthier, more constructive conversations.
6. Transparency and Accountability: If concerns exist about misuse (e.g., generating spammy or low-quality comments), these can be addressed through guidelines and oversight mechanisms. Misplaced Pages already has systems in place for identifying and mitigating disruptive behavior, and LLM-generated comments could be subject to the same scrutiny. A ban is an overly simplistic solution to what could be a more nuanced issue, one that could be addressed through better regulation and community involvement.
In conclusion, banning the use of large language models on Misplaced Pages would deprive the platform of an important tool for improving accessibility, efficiency, and the quality of discourse. Instead of a ban, the focus should be on establishing guidelines for their responsible use, ensuring that they enhance, rather than detract from, Misplaced Pages's core principles of collaboration, neutrality, and inclusivity.
It is somewhat amusing how easy it is to get these chatbots to output apologia for these chatbots. Too bad it's always so shallow. Probably because the people who inserted those canned responses are shallow people is my opinion. Simonm223 (talk) 19:44, 6 December 2024 (UTC)
Someone trolling and sealioning can (and should) be blocked under current policy, whether they use an LLM or not is irrelevant. Thryduulf (talk) 15:22, 5 December 2024 (UTC)
Support: the general principle is sound - where the substance has been originally written by gen-AI, comments will tend to add nothing to the discussion and even annoy or confuse other users. In principle, we should not allow such tools to be used in discussions. Comments written originally before improvement or correction by AI, particularly translation assistants, fall into a different category. Those are fine. There also has to be a high standard for comment removal. Suspicion that gen-AI might have been used is not enough. High gptzero scores is not enough. The principle should go into policy but under a stonking great caveat - WP:AGF takes precedence and a dim view will be taken of generative-AI inquisitors. arcticocean ■17:37, 5 December 2024 (UTC)
Support If a human didn't write it, humans shouldn't spend time reading it. I'll go further and say that LLMs are inherently unethical technology and, consequently, people who rely on them should be made to feel bad. ESL editors who use LLMs to make themselves sound like Brad Anderson in middle management should stop doing that because it actually gets in the way of clear communication. I find myself unpersuaded by arguments that existing policies and guidelines are adequate here. Sometimes, one needs a linkable statement that applies directly to the circumstances at hand. By analogy, one could argue that we don't really need WP:BLP, for example, because adhering to WP:V, WP:NPOV, and WP:NOR ought already to keep bad material out of biographies of living people. But in practice, it turned out that having a specialized policy that emphasizes the general ethos of the others while tailoring them to the problem at hand is a good thing. XOR'easter (talk) 18:27, 5 December 2024 (UTC)
Strong support - Making a computer generate believable gibberish for you is a waste of time, and tricking someone else into reading it should be a blockable offense. If we're trying to create an encyclopedia, you cannot automate any part of the thinking. We can automate processes in general, but any attempt at automating the actual discussion or thought-processes should never be allowed. If we allow this, it would waste countless hours of community time dealing with inane discussions, sockpuppetry, and disruption. Imagine a world where LLMs are allowed and popular - it's a sockpuppeteer's dream scenario - you can run 10 accounts and argue the same points, and the reason why they all sound alike is just merely because they're all LLM users. You could even just spend a few dollars a month and run 20-30 accounts to automatically disrupt wikipedia discussions while you sleep, and if LLM usage was allowed, it would be very hard to stop. However, I don't have much faith in AI detection tools (partially because it's based on the same underlying flawed technology), and would want any assumption of LLM usage to be based on obvious evidence, not just a score on some website. Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop BugGhost🦗👻19:15, 5 December 2024 (UTC)
I agree with your assessment “Also, to those who are posting chatgpt snippets here: please stop - it's not interesting or insightful, just more slop” but unfortunately some editors who should really know better think it’s WaCkY to fill serious discussions with unfunny, distracting “humor”. Dronebogus (talk) 21:54, 5 December 2024 (UTC)
Strong support if you asked a robot to spew out some AI slop to win an argument you’re basically cheating. The only ethical reason to do so is because you can’t speak English well, and the extremely obvious answer to that is “if you can barely speak English why are you editing English Misplaced Pages?” That’s like a person who doesn’t understand basic physics trying to explain the second law of thermodynamics using a chatbot. Dronebogus (talk) 21:32, 5 December 2024 (UTC)
I don't think "cheating" is a relevant issue here. Cheating is a problem if you use a LLM to win and get a job, award, college acceptance etc. that you otherwise wouldn't deserve. But WP discussions aren't a debating-skills contest, they're an attempt to determine the best course of action.
So using an AI tool in a WP discussion is not cheating (though there may be other problems), just as riding a bike instead of walking isn't cheating unless you're trying to win a race. ypn^222:36, 5 December 2024 (UTC)
Maybe “cheating” isn’t the right word. But I think that a) most AI generated content is garbage (it can polish the turd by making it sound professional, but it’s still a turd underneath) and b) it’s going to be abused by people trying to gain a material edge in an argument. An AI can pump out text far faster than a human and that can drown out or wear down the opposition if nothing else. Dronebogus (talk) 08:08, 6 December 2024 (UTC)
Bludgeoning is already against policy. It needs to be more strongly enforced, but it needs to be more strongly enforced uniformly rather than singling out comments that somebody suspects might have had AI-involvement. Thryduulf (talk) 10:39, 6 December 2024 (UTC)
Support; I agree with Remsense and jlwoodwa, among others: I wouldn't make any one AI-detection site the Sole Final Arbiter of whether a comment "counts", but I agree it should be expressly legitimate to discount AI / LLM slop, at the very least to the same extent as closers are already expected to discount other insubstantial or inauthentic comments (like if a sock- or meat-puppet copy-pastes a comment written for them off-wiki, as there was at least one discussion and IIRC ArbCom case about recently). -sche (talk) 22:10, 5 December 2024 (UTC)
You don't need a new policy that does nothing but duplicate a subset of existing policy. At most what you need is to add a sentence to the existing policy that states "this includes comments written using LLMs", however you'd rightly get a lot of pushback on that because it's completely redundant and frankly goes without saying. Thryduulf (talk) 23:37, 5 December 2024 (UTC)
Support hallucinations are real. We should be taking a harder line against LLM generated participation. I don't think everyone who is doing it knows that they need to stop. Andre🚐23:47, 5 December 2024 (UTC)
Comment - Here is something that I imagine we will see more often. I wonder where it fits into this discussion. A user employs perplexity's RAG based system, search+LLM, to help generate their edit request (without the verbosity bias that is common when people don't tell LLMs how much output they want). Sean.hoyland (talk) 03:13, 6 December 2024 (UTC)
Support per all above. Discussions are supposed to include the original arguments/positions/statements/etc of editors here, not off-site chatbots. TheKip03:53, 6 December 2024 (UTC)
I also find it pretty funny that ChatGPT itself said it shouldn't be used, as per the premise posted above by EEng. TheKip03:58, 6 December 2024 (UTC)
"sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses" - Towards Understanding Sycophancy in Language Models. They give us what we want...apparently. And just like with people, there is position bias, so the order of things can matter. Sean.hoyland (talk) 04:26, 6 December 2024 (UTC)
(Is this where I respond? If not, please move.) LLM-generated prose should be discounted. Sometimes there will be a discernible point in there; it may even be what the editor meant, lightly brushed up with what ChatGPT thinks is appropriate style. (So I wouldn't say "banned and punishable" in discussions, although we already deprecate machine translations on en.wiki and for article prose, same difference—never worth the risk.) However, LLMs don't think. They can't explain with reference to appropriate policy and guidelines. They may invent stuff, or use the wrong words—at AN recently, an editor accused another of "defaming" and "sacrilege", thus drowning their point that they thought that editor was being too hard on their group by putting their signature to an outrageous personal attack. I consider that an instance of LLM use letting them down. If it's not obvious that it is LLM use, then the question doesn't arise, right? Nobody is arguing for requiring perfect English. That isn't what WP:CIR means. English is a global language, and presumably for that reason, many editors on en.wiki are not native speakers, and those that aren't (and those that are!) display a wide range of ability in the language. Gnomes do a lot of fixing of spelling, punctuation and grammar in articles. In practice, we don't have a high bar to entrance in terms of English ability (although I think a lot more could be done to explain to new editors whose English is obviously non-native what the rule or way of doing things is that they have violated. And some of our best writers are non-native; a point that should be emphasised because we all have a right of anonymity here, many of us use it, and it's rare, in particular, that I know an editor's race. Or even nationality (which may not be the same as where they live.) But what we do here is write in English: both articles and discussions. If someone doesn't have the confidence to write their own remark or !vote, then they shouldn't participate in discussions; I strongly suspect that it is indeed a matter of confidence, of wanting to ensure the English is impeccable. LLMs don't work that way, really. They concoct things like essays based on what others have written. Advice to use them in a context like a Misplaced Pages discussion is bad advice. At best it suggests you let the LLM decide which way to !vote. If you have something to say, say it and if necessary people will ask a question for clarification (or disagree with you). They won't mock your English (I hope! Civility is a basic rule here!) It happens in pretty much every discussion that somebody makes an English error. No biggie. I'll stop there before I make any more typos myself; typing laboriously on my laptop in a healthcare facility, and anyway Murphy's Law covers this. Yngvadottir (talk)
I dunno about this specifically but I want to chime in to say that I find LLM-generated messages super fucking rude and unhelpful and support efforts to discourage them. – Joe (talk) 08:15, 6 December 2024 (UTC)
Comment I think obvious LLM/chatbot text should at least be tagged through an Edit filter for Recent Changes, then RC Patrollers and reviewers can have a look and decide for themselves. Am(Notes)11:58, 6 December 2024 (UTC)
How do you propose that such text be identified by an edit filter? LLM detections tools have high rates of both false positives and false negatives. Thryduulf (talk) 12:47, 6 December 2024 (UTC)
It might become possible once watermarks (like DeepMind's SynthID) are shown to be robust and are adopted. Some places are likely to require it at some point e.g. EU. I guess it will take a while though and might not even happen e.g. I think OpenAI recently decided to not go ahead with their watermark system for some reason. Sean.hoyland (talk) 13:17, 6 December 2024 (UTC)
It will still be trivial to bypass the watermarks, or use LLMs that don't implement them. It also (AIUI) does nothing to reduce false positives (which for our usecase are far more damaging than false negatives). Thryduulf (talk) 13:30, 6 December 2024 (UTC)
Maybe, that seems to be the case with some of the proposals. Others, like SynthID claim high detection rates, maybe because even a small amount of text contains a lot of signals. As for systems that don't implement them, I guess that would be an opportunity to make a rule more nuanced by only allowing use of watermarked output with verbosity limits...not that I support a rule in the first place. People are going to use/collaborate with LLMs. Why wouldn't they? Sean.hoyland (talk) 14:38, 6 December 2024 (UTC)
I don't think watermarks are a suitable thing to take into account. My view is that LLM usage should be a blockable offense on any namespace, but if it ends up being allowed under some circumstances then we at least need mandatory manual disclosures for any usage. Watermarks won't work / aren't obvious enough - we need something like {{LLM}} but self-imposed, and not tolerate unmarked usage. BugGhost🦗👻18:21, 6 December 2024 (UTC)
Comment As a practical matter, users posting obvious LLM-generated content will typically be in violation of other rules (e.g. disruptive editing, sealioning), in which case their discussion comments absolutely should be ignored, discouraged, discounted, or (in severe cases) hatted. But a smaller group of users (e.g. people using LLMs as a translation tool) may be contributing productively, and we should seek to engage with, rather than discourage, them. So I don't see the need for a separate bright-line policy that risks erasing the need for discernment — in most cases, a friendly reply to the user's first LLM-like post (perhaps mentioning WP:LLM, which isn't a policy or guideline, but is nevertheless good advice) will be the right approach to work out what's really going on. Preimage (talk) 15:53, 6 December 2024 (UTC)
Some translation tools have LLM assistance, but the whole point of generative models is to create text far beyond what is found in the user's input, and the latter is clearly what this proposal covers. JoelleJay (talk) 19:01, 6 December 2024 (UTC)
That might be what the proposal intends to cover, but it is not what the proposal actually covers. The proposal all comments that have been generated by LLMs and/or AI, without qualification. Thryduulf (talk) 01:05, 7 December 2024 (UTC)
70+% here understand the intention matches the language: generated by LLMs etc means "originated through generative AI tools rather than human thought", not "some kind of AI was involved in any step of the process". Even LLM translation tools don't actually create meaningful content where there wasn't any before; the generative AI aspect is only in the use of their vast training data to characterize the semantic context of your input in the form of mathematical relationships between tokens in an embedding space, and then match it with the collection of tokens most closely resembling it in the other language. There is, definitionally, a high level of creative constraint in what the translation output is since semantic preservation is required, something that is not true for text generation. JoelleJay (talk) 04:01, 7 December 2024 (UTC)
Do you have any evidence for you assertion that 70% of respondents have interpreted the language in the same way as you? Reading the comments associated with the votes suggests that it's closer to 70% of respondents who don't agree with you. Even if you are correct, 30% of people reading a policy indicates the policy is badly worded. Thryduulf (talk) 08:34, 7 December 2024 (UTC)
I think @Bugghost has summarized the respondent positions sufficiently below. I also think some portion of the opposers understand the proposal perfectly well and are just opposing anything that imposes participation standards. JoelleJay (talk) 22:54, 7 December 2024 (UTC)
There will be many cases where it is not possible to say whether a piece of text does or does not contain "human thought" by observing the text, even if you know it was generated by an LLM. Statements like "originated through generative AI tools rather than human thought" will miss a large class of use cases, a class that will probably grow over the coming years. People work with LLMs to produce the output they require. It is often an iterative process by necessity because people and models make mistakes. An example of when "...rather than human thought" is not the case is when someone works with an LLM to solve something like a challenging technical problem where neither the person or the model has a satisfactory solution to hand. The context window means that, just like with human collaborators, a user can iterate towards a solution through dialog and testing, exploring the right part of the solution space. Human thought is not absent in these cases, it is present in the output, the result of a collaborative process. In these cases, something "far beyond what is found in the user's input" is the objective, it seems like a legitimate objective, but regardless, it will happen, and we won't be able to see it happening. Sean.hoyland (talk) 10:46, 7 December 2024 (UTC)
Yes, but this proposal is supposed to apply to just the obvious cases and will hopefully discourage good-faith users from using LLMs to create comments wholesale in general. It can be updated as technology progresses. There's also no reason editors using LLMs to organize/validate their arguments, or as search engines for whatever, have to copy-paste their raw output, which is much more of a problem since it carries a much higher chance of hallucination. That some people who are especially familiar with how to optimize LLM use, or who pay for advanced LLM access, will be able to deceive other editors is not a reason to not formally proscribe wholesale comment generation. JoelleJay (talk) 22:27, 7 December 2024 (UTC)
That's reasonable. I can get behind the idea of handling obvious cases from a noise reduction perspective. But for me, the issue is noise swamping signal in discussions rather than how it was generated. I'm not sure we need a special rule for LLMs, maybe just a better way to implement the existing rules. Sean.hoyland (talk) 04:14, 8 December 2024 (UTC)
Comment: The original question was whether we should discount, ignore, strikethrough, or collapse chatbot-written content. I think there's a very big difference between these options, but most support !voters haven't mentioned which one(s) they support. That might make judging the consensus nearly impossible; as of now, supporters are the clear !majority, but supporters of what? — ypn^219:32, 6 December 2024 (UTC)
That means that supporters support the proposal that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner. Not sure what the problem is here. Supporters support the things listed in the proposal - we don't need a prescribed 100% strict procedure, it just says that supporters would be happy with closers discounting, ignoring or under some circumstances deleting LLM content in discussions. BugGhost🦗👻19:40, 6 December 2024 (UTC)
More people have bolded "support" than other options, but very few of them have even attempted to refute the arguments against (and most that have attempted have done little more than handwaving or directly contradicting themselves), and multiple of those who have bolded "support" do not actually support what has been proposed when you read their comment. It's clear to me there is not going to be a consensus for anything other than "many editors dislike the idea of LLMs" from this discussion. Thryduulf (talk) 00:58, 7 December 2024 (UTC)
Arguing one point doesn't necessarily require having to refute every point the other side makes. I can concede that "some people use LLMs to improve their spelling and grammar" without changing my view overriding view that LLMs empower bad actors, time wasters and those with competence issues, with very little to offer wikipedia in exchange. Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first. BugGhost🦗👻09:00, 7 December 2024 (UTC)
If you want to completely ignore all the other arguments in opposition that's your choice, but don't expect closers to attach much weight to your opinions. Thryduulf (talk) 09:05, 7 December 2024 (UTC)
Ok, here's a list of the main opposition reasonings, with individual responses.
What about translations? - Translations are not up for debate here, the topic here is very clearly generative AI, and attempts to say that this topic covers translations as well is incorrect. No support voters have said the propositions should discount translated text, just oppose voters who are trying to muddy the waters.
What about accessibility? - This is could be a legitimate argument, but I haven't seen this substantiated anywhere other than handwaving "AI could help people!" arguments, which I would lump into the spelling and grammar argument I responded to above.
Detection tools are inaccurate - This I very much agree with, and noted in my support and in many others as well. But there is no clause in the actual proposal wording that mandates the use of automated AI detection, and I assume the closer would note that.
False positives - Any rule can have a potential for false positives, from wp:DUCK to close paraphrasing to NPA. We've just got to as a community become skilled at identifying genuine cases, just like we do for every other rule.
LLM content should be taken at face value and see if it violates some other policy - hopelessly naive stance, and a massive timesink. Anyone who has had the misfortune of going on X/twitter in the last couple of years should know that AI is not just used as an aid for those who have trouble typing, it is mainly used to spam and disrupt discussion to fake opinions to astroturf political opinions. Anyone who knows how bad the sockpuppetry issue is around CTOPs should be absolutely terrified of when (not if) someone decides to launch a full throated wave of AI bots on Misplaced Pages discussions, because if we have to invididually sanction each one like a human then admins will literally have no time for anything else.
I genuinely cannot comprehend how some people could see how AI is decimating the internet through spam, bots and disinformation and still think for even one second that we should open the door to it. BugGhost🦗👻10:08, 7 December 2024 (UTC)
There is no door. This is true for sockpuppetry too in my opinion. There can be a rule that claims there is a door, but it is more like a bead curtain. Sean.hoyland (talk) 11:00, 7 December 2024 (UTC)
The Twitter stuff is not a good comparison here. Spam is already nukable on sight, mass disruptive bot edits are also nukable on sight, and it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions (most of which would be off-topic anyway, i.e., nukable on sight). I'd prefer if people didn't use ChatGPT to formulate their points, but if they're trying to formulate a real point then that isn't disruptive in the same way spam is. Gnomingstuff (talk) 02:22, 10 December 2024 (UTC)
it's unclear how static comments on Misplaced Pages would be the best venue to astroturf political opinions - by disrupting RFCs and talk page discussions a bad actor could definitely use chatgpt to astroturf. A large proportion of the world uses Misplaced Pages (directly or indirectly) to get information - it would be incredibly valuable thing to manipulate. My other point is that AI disruption bots (like the ones on twitter) would be indistinguishable from individuals using LLMs to "fix" spelling and grammar - by allowing one we make the other incredibly difficult to identify. How can you tell the difference between a bot and someone who just uses chatgpt for every comment? BugGhost🦗👻09:16, 10 December 2024 (UTC)
Those that use LLMs legitimately to tidy up their alledgedly competent, insightful and self-sourced thoughts should just be encouraged to post the prompts themselves instead of churning it through an LLM first.
Social anxiety: Say "I" am a person unconfident in my writing. I imagine that when I post my raw language, I embarrass myself, and my credibility vanishes, while in the worst case nobody understands what I mean. As bad confidence is often built up through negative feedback, it's usually meritful or was meritful at some point for someone to seek outside help. Aaron Liu (talk) 23:46, 8 December 2024 (UTC)
While I sympathise with that hypothetical, Misplaced Pages isn't therapy and we shouldn't make decisions that do long-term harm to the project just because a hypothetical user feels emotionally dependent on a high tech spellchecker. I also think that in general wikipedia (myself included) is pretty relaxed about spelling and grammar in talk/WP space. BugGhost🦗👻18:45, 10 December 2024 (UTC)
We also shouldn't do long term harm to the project just because a few users are wedded to idea that LLMs are and will always be some sort of existential threat. The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project than LLM-comments that are all either useful, harmless or collapseable/removable/ignorable at present. Thryduulf (talk) 19:06, 10 December 2024 (UTC)
The false positives that are an unavoidable feature of this proposal will do far more, and far longer, harm to the project - the same could be said for WP:DUCK. The reason why its not a big problem for DUCK is because the confidence level is very high. Like I've said in multiple other comments, I don't think "AI detectors" should be trusted, and that the bar for deciding whether something was created via LLM should be very high. I 100% understand your opinion and the reasoning behind it, I just think we have differing views on how well the community at large can identify AI comments. BugGhost🦗👻09:07, 11 December 2024 (UTC)
I don't see how allowing shy yet avid users to contribute has done or will do long-term harm. The potential always outweighs rational evaluation of outcomes for those with anxiety, a condition that is not behaviorally disruptive. Aaron Liu (talk) 02:47, 11 December 2024 (UTC)
I definitely don't want to disallow shy yet avid users! I just don't think having a "using chatgpt to generate comments is allowed" rule is the right solution to that problem, considering the wider consequences. BugGhost🦗👻08:52, 11 December 2024 (UTC)
Support strikethroughing or collapsing per everyone else. The opposes that mention ESL have my sympathy, but I am not sure how many of them are ESL themselves. Having learnt English as my second language, I have always found it easier to communicate when users are expressing things in their own way, not polished by some AI. I sympathise with the concerns and believe the right solution is to lower our community standards with respect to WP:CIR and similar (in terms of ESL communication) without risking hallucinations by AI. Soni (talk) 02:52, 7 December 2024 (UTC)
Oppose - I'm sympathetic to concerns of abuse through automated mass-commenting, but this policy looks too black-and-white. Contributors may use LLMs for many reasons, including to fix the grammar, to convey their thoughts more clearly, or to adjust the tone for a more constructive discussion. As it stands, this policy may lead to dismissing good-faith AI-assisted comments, as well as false positives, without considering the context. Moreover, while mainstream chatbots are not designed to just mimic the human writing style, there are existing tools that can make AI-generated text more human-like, so this policy does not offer that much protection against maliciously automated contributions. Alenoach (talk) 01:12, 9 December 2024 (UTC)
Oppose What @Alenoach said is correct, basic AI tools like Grammarly should be allowed (note that grammarly can also change sentences and wording and has generative AI tools) but just blatantly asking ChatGPT to generate a administrator report is different. Rc2barrington (talk) 04:46, 1 January 2025 (UTC)
Oppose – Others have cast doubt on the efficacy of tools capable of diagnosing LLM output, and I can't vouch for its being otherwise. If EEng's example of ChatBot output is representative—a lengthy assertion of notability without citing sources—that is something that could well be disregarded whether it came from a bot or not. If used carefully, AI can be useful as an aide-memoire (such as with a spell- or grammar-checker) or as a supplier of more felicitous expression than the editor is naturally capable of (e.g. Google Translate). Dhtwiki (talk) 10:27, 9 December 2024 (UTC)
Comment / Oppose as written. It's not accurate that GPTZero is good at detecting AI-generated content. Citations (slightly out of date but there's little reason to think things have changed from 2023): https://www.aiweirdness.com/writing-like-a-robot/ , https://www.aiweirdness.com/dont-use-ai-detectors-for-anything-important/ . For those too busy to read, a few choice quotes: "the fact that it insisted even one excerpt is not by a human means that it's useless for detecting AI-generated text," and "Not only do AI detectors falsely flag human-written text as AI-written, the way in which they do it is biased" (citing https://arxiv.org/abs/2304.02819 ). Disruptive, worthless content can already be hatted, and I'm not opposed to doing so. Editors should be sharply told to use their own words, and if not already written, an essay saying we'd rather have authentic if grammatically imperfect comments than AI-modulated ones would be helpful to cite at editors who offer up AI slop. But someone merely citing GPTZero is not convincing. GPTZero will almost surely misidentify genuine commentary as AI-generated. So fine with any sort of reminder that worthless content can be hatted, and fine with a reminder not to use ChatGPT for creating Misplaced Pages talk page posts, but not fine with any recommendations of LLM-detectors. SnowFire (talk) 20:00, 9 December 2024 (UTC)
@SnowFire, I can't tell if you also oppose the actual proposal, which is to permit hatting/striking obvious LLM-generated comments (using GPTzero is a very minor detail in JSS's background paragraph, not part of the proposal). JoelleJay (talk) 01:47, 11 December 2024 (UTC)
I support the proposal in so far as disruptive comments can already be hatted and that LLM-generated content is disruptive. I am strongly opposed to giving well-meaning but misguided editors a license to throw everyone's text into an AI-detector and hat the comments that score poorly. I don't think it was that minor a detail, and to the extent that detail is brought up, it should be as a reminder to use human judgment and forbid using alleged "AI detectors" instead. SnowFire (talk) 03:49, 11 December 2024 (UTC)
Support collapsing AI (specifically, Large language model) comments by behavioral analysis (most actually disruptive cases I've seen are pretty obvious) and not the use of inaccurate tools like ZeroGPT. I thinking hatting with the title "Editors suspect that this comment has been written by a Large language model" is appropriate. They take up SO much space in a discussion because they are also unnecessarily verbose, and talk on and on but never ever say something that even approaches having substance. Discussions are for human Misplaced Pages editors, we shouldn't have to use to sift through comments someone put 0 effort into and outsourced to a robot that writes using random numbers (that's a major part of how tools like ChatGPT work and maintain variety). If someone needs to use an AI chatbot to communicate because they don't understand English, then they are welcome to contribute to their native language Misplaced Pages, but I don't think they have the right to insist that we at enwiki spend our effort reading comments they but minimal effort into besides opening the ChatGPT website. If really needed, they can write in their native language and use a non-LLM tool like Google Translate. The use of non-LLM tools like Grammarly, Google Translate, etc. I think should still be OK for all editors, as they only work off comments that editors have written themselves. MolecularPilot05:10, 10 December 2024 (UTC)
Adding that enforcing people writing things in their own words will actually help EAL (English additional language) editors contribute here. I world with EAL people irl, and even people who have almost native proficiency with human-written content find AI output confusing because it says things in the most confusing, verbose ways using difficult sentence constructions and words. I've seen opposers in this discussion who maybe haven't had experience working with EAL people go "what about EAL people?", but really, I think this change will help them (open to being corrected by someone who is EAL, tho). MolecularPilot05:17, 10 December 2024 (UTC)
Also, with regards to oppose comments that discussions are not a vote so closes will ignore AI statements which don't have merit - unedited LLM statements are incredibly verbose and annoying, and clog up the discussion. Imagine multiple paragraphs, each with a heading, but all of which say almost nothing, they're borderline WP:BLUDGEONy. Giving the power to HAT them will help genuine discussion contributors keep with the flow of human arguments and avoid scaring away potential discussion contributors who are intimidated or don't feel they have the time to read the piles of AI nonsense that fill the discussion. MolecularPilot06:38, 10 December 2024 (UTC)
Support (removing) in general. How is this even a question? There is no case-by-case. It is a fundamental misunderstanding of how LLMs work to consider their output reliable without careful review. And which point, the editor could have written it themselves without inherent LLM bias. The point of any discussion is to provide analytical response based on the context, not have some tool regurgitate something from a training set that sounds good. And frankly, it is disrespectuful to make someone read "AI" responses. It is a tool and there is a place and time for it, but not in discussions in an encyclopedia. — HELLKNOWZ∣TALK15:41, 10 December 2024 (UTC)
Strong Support. I'm very interested in what you (the generic you) have to say about something. I'm not remotely interested in what a computer has to say about something. It provides no value to the discussion and is a waste of time. Useight (talk) 18:06, 10 December 2024 (UTC)
Comments that provide no value to the discussion can already be hatted and ignored regardless of why they provide no value, without any of the false positive or false negatives inherent in this proposal. Thryduulf (talk) 18:25, 10 December 2024 (UTC)
Indeed, and that's fine for one-offs when a discussion goes off the rails or what-have-you. But we also have WP:NOTHERE for disruptive behavior, not working collaboratively, etc. I'm suggesting that using an AI to write indicates that you're not here to build the encyclopedia, you're here to have an AI build the encyclopedia. I reiterate my strong support for AI-written content to be removed, struck, collapsed, or hatted and would support further measures even beyond those. Useight (talk) 21:54, 11 December 2024 (UTC)
There are two sets of people described in your comment: those who use AI and those who are NOTHERE. The two sets overlap, but nowhere near sufficiently to declare that everybody in the former set are also in the latter set. If someone is NOTHERE they already can and should be blocked, regardless of how they evidence that. Being suspected of using AI (note that the proposal does not require proof) is not sufficient justification on its own to declare someone NOTHERE, per the many examples of constructive use of AI already noted in this thread. Thryduulf (talk) 22:03, 11 December 2024 (UTC)
To reiterate, I don't believe that any use of AI here is constructive, thus using it is evidence of WP:NOTHERE, and, therefore, the set of people using AI to write is completely circumscribed within the set of people who are NOTHERE. Please note that I am referring to users who use AI-generated writing, not users suspected of using AI-generated writing. I won't be delving into how one determines whether someone is using AI or how accurate it is, as that is, to me, a separate discussion. This is the end of my opinion on the matter. Useight (talk) 23:26, 11 December 2024 (UTC)
You are entitled to your opinion of course, but as it is contradicted by the evidence of both multiple constructive uses and of the near-impossibility of reliably detecting LLM-generated text without false positives, I would expect the closer of this discussion to attach almost no weight to it. Thryduulf (talk) 00:42, 12 December 2024 (UTC)
I am ESL and use LLMs sometimes because of that. I feel like I don't fit into the NOTHERE category. It seems like you do not understand what they are or how they can be used constructively. PackMecEng (talk) 01:43, 12 December 2024 (UTC)
No, I understand. What you're talking about is no different from using Google Translate or asking a native-speaker to translate it. You, a human, came up with something you wanted to convey. You wrote that content in Language A. But you wanted to convey that message that you - a human - wrote, but now in Language B. So you had your human-written content translated to Language B. I have no qualms with this. It's your human-written content, expressed in Language B. My concern is with step 1 (coming up with something you want to convey), not step 2 (translating that content to another language). You write a paragraph for an article but it's in another language and you need the paragraph that you wrote translated? Fine by me. You ask an AI to write a paragraph for an article? Not fine by me. Again, I'm saying that there is no valid use case for AI-written content. Useight (talk) 15:59, 12 December 2024 (UTC)
It seems very likely that there will be valid use cases for AI-written content if the objective is maximizing quality and minimizing errors. Research like this demonstrate that there will likely be cases where machines outperform humans in specific Misplaced Pages domains, and soon. But I think that is an entirely different question than potential misuse of LLMs in consensus related discussions. Sean.hoyland (talk) 16:25, 12 December 2024 (UTC)
But your vote and the proposed above makes not distinction there. Which is the main issue. Also not to be pedantic but every prompted to a LLM is filled out by a human looking to convey a message. Every time someone hits publish on something here it is that person confirming that is what they are saying. So how do we in practice implement what you suggest? Because without a method better than vibes it's worthless. PackMecEng (talk) 18:53, 12 December 2024 (UTC)
The proposal specifies content generated by LLMs, which has a specific meaning in the context of generative AI. If a prompt itself conveys a meaningful, supported opinion, why not just post that instead? The problem comes when the LLM adds more information than was provided, which is the whole point of generative models. JoelleJay (talk) 01:52, 13 December 2024 (UTC)
Yes in principle. But in practice, LLM detectors are not foolproof, and there are valid reasons to sometimes use an LLM, for example to copyedit. I have used Grammarly before and have even used the Microsoft Editor, and while they aren't powered by LLMs, LLMs are a tool that need to be used appropriately on Misplaced Pages. AwesomeAasim19:55, 10 December 2024 (UTC)
Support. Using LLM to reply to editors is lazy and disrespectful of fellow editor's time and brainpower. In the context of AFD, it is particularly egregious since an LLM can't really read the article, read sources, or follow our notability guidelines. By the way. gptzero and other such tools are very good at detecting this. I don't think this is correct at all. I believe the false positive for AI detectors is quite high. High enough that I would recommend not using AI detectors. –Novem Linguae (talk) 03:23, 11 December 2024 (UTC)
Support. AI generated text should be removed outright. If you aren't willing to put the work into doing your own writing then you definitely haven't actually thought deeply about the matter at hand. User1042💬✒️14:16, 11 December 2024 (UTC)
This comment is rather ironic given that it's very clear you haven't thought deeply about the matter at hand, because if you had then you'd realise that it's actually a whole lot more complicated than that. Thryduulf (talk) 14:26, 11 December 2024 (UTC)
Thryduulf I don't think this reply is particular helpful, and it comes off as slightly combative. It's also by my count your 24th comment on this RFC. BugGhost🦗👻19:20, 11 December 2024 (UTC)
I recognize that AI paraphrased or edited is not problematic in the same ways as text generated outright by an AI. I only meant to address the core issue at steak, content whose first draft was written by an AI system. User1042💬✒️22:16, 17 December 2024 (UTC)
I've recently come across several users in AFD discussions that are using LLMs to generate their remarks there. As many of you are aware, gptzero and other such tools are very good at detecting this. I don't feel like any of us signed up for participating in discussions where some of the users are not using their own words but rather letting technology do it for them. Discussions are supposed to be between human editors. If you can't make a coherent argument on your own, you are not competent to be participating in the discussion. I would therefore propose that LLM-generated remarks in discussions should be discounted or ignored, and possibly removed in some manner
Support with the caveat that our ability to deal with the issue goes only as far as we can accurately identify the issue (this appears to have been an issue raised across a number of the previous comments, both support and oppose, but I think it bears restating because we're approaching this from a number of different angles and its IMO the most important point regardless of what conclusions you draw from it). Horse Eye's Back (talk) 19:24, 11 December 2024 (UTC)
Strong support, limited implementation. Misplaced Pages is written by volunteer editors, says our front page. This is who we are, and our writing is what Misplaced Pages is. It's true that LLM-created text can be difficult to identify, so this may be a bit of a moving target, and we should be conservative in what we remove—but I'm sure at this point we've all run across cases (whether here or elsewhere in our digital lives) where someone copy/pastes some text that includes "Is there anything else I can help you with?" at the end, or other blatant tells. This content should be deleted without hesitation. Retswerb (talk) 04:11, 12 December 2024 (UTC)
Support in concept, questions over implementation — I concur with Dronebogus that users who rely on LLMs should not edit English Misplaced Pages. It is not a significant barrier for users to use other means of communication, including online translators, rather than artificial intelligence. How can an artificial intelligence tool argue properly? However, I question how this will work in practice without an unacceptable degree of error. elijahpepe@wikipedia (he/him) 22:39, 12 December 2024 (UTC)
Well since people keep bringing this up as a semi-strawman: no I don’t support banning machine translation, not that I encourage using it (once again, if you aren’t competent in English please don’t edit here) Dronebogus (talk) 07:34, 13 December 2024 (UTC)
LLMs are incredible at translating, and many online translators already incorporate them, including Google Translate. Accomodating LLMs is an easy way to support the avid not only the ESL but also the avid but shy. It has way more benefits than the unseen-to-me amount of AI trolling that isn't already collapse-on-sight. Aaron Liu (talk) 00:05, 13 December 2024 (UTC)
Google Translate uses the same transformer architecture that LLMs are built around, and uses e.g. PaLM to develop more language support (through training that enables zero-shot capabilities) and for larger-scale specialized translation tasks performed through the Google Cloud "adaptive translation" API, but it does not incorporate LLMs into translating your everyday text input, which still relies on NMTs. And even for the API features, the core constraint of matching input rather than generating content is still retained (obviously it would be very bad for a translation tool to insert material not found in the original text!). LLMs might be good for translation because they are better at evaluating semantic meaning and detecting context and nuance, but again, the generative part that is key to this proposal is not present. JoelleJay (talk) 01:20, 13 December 2024 (UTC)
PaLM (Pathways Language Model) is a 540 billion-parameter transformer-based large language model (LLM) developed by Google AI. If you meant something about how reschlmunking the outputs of an LLM or using quite similar architecture is not really incorporating the LLM, I believe we would be approaching Ship of Theseus levels of recombination, to which my answer is it is the same ship.
obviously it would be very bad for a translation tool to insert material not found in the original text!
PaLM2 is not used in the consumer app (Google Translate), it's used for research. Google Translate just uses non-generative NMTs to map input to its closes cognate in the target language. JoelleJay (talk) 01:34, 13 December 2024 (UTC)
Well, is the NMT really that different enough to not be classified as an LLM? IIRC the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be, and an LLM I asked agreed that NMTs satisfy the definition of a generative LLM, though I think you're the expert here. Aaron Liu (talk) 02:01, 13 December 2024 (UTC)
Google Translate's NMT hits different enough to speak English much less naturally than ChatGPT 4o. I don't consider it a LLM, because the param count is 380M not 1.8T.
the definition of an LLM is something that outputs by predicting one-by-one what the next word/"token" should be No, that def would fit ancient RNN tech too. 172.97.141.219 (talk) 17:50, 13 December 2024 (UTC)
Even if you don’t consider it L, I do, and many sources cited by the article do. Since we’ll have such contesting during enforcement, it’s better to find a way that precludes such controversy. Aaron Liu (talk) 20:44, 13 December 2024 (UTC)
NMTs, LLMs, and the text-creation functionality of LLMs are fundamentally different in the context of this discussion, which is about content generated through generative AI. NMTs specifically for translation: they are trained on parallel corpora and their output is optimized to match the input as precisely as possible, not to create novel text. LLMs have different training, including way more massive corpora, and were designed specifically to create novel text. One of the applications of LLMs may be translation (though currently it's too computationally intensive to run them for standard consumer purposes), by virtue of their being very good at determining semantic meaning, but even if/when they do become mainstream translation tools what they'll be used for is still not generative when it comes to translation output. JoelleJay (talk) 22:29, 13 December 2024 (UTC)
The proposal is for hatting obvious cases of LLM-generated comments. Someone who just uses an LLM to copyedit will still have written the content themselves and presumably their output would not have the obvious tells of generative AI. JoelleJay (talk) 23:56, 13 December 2024 (UTC)
Not when I tried to use it. Quantitatively, GPTZero went from 15% human to 100% AI for me despite the copyedits only changing 14 words. Aaron Liu (talk) 00:33, 14 December 2024 (UTC)
Does it really mean that? All you've demonstrated is that GPTZero has false positives, which is exactly why its use here was discouraged. jlwoodwa (talk) 05:26, 14 December 2024 (UTC)
My subjective evaluation of what I got copyediting from ChatGPT was that it sounded like ChatGPT. I used GPTZero to get a number. Aaron Liu (talk) 14:18, 14 December 2024 (UTC)
It changed only 14 words across two paragraphs and still retained the same meaning in a way that I would describe it as copyediting. Such levels of change are what those lacking confidence in tone would probably seek anyways. Aaron Liu (talk) 00:15, 24 December 2024 (UTC)
On one hand, AI slop is a plague on humanity and obvious LLM output should definitely be disregarded when evaluating consensus. On the other hand, I feel like existing policy covers this just fine, and any experienced closer will lend greater weight to actual policy-based arguments, and discount anything that is just parroting jargon. WindTemposthey23:21, 12 December 2024 (UTC)
Support in principle, but we cannot rely on any specific tools because none are accurate enough for our needs. Whenever I see a blatant ChatGPT-generated !vote, I ignore it. They're invariably poorly reasoned and based on surface-level concepts rather than anything specific to the issue being discussed. If someone is using AI to create their arguments for them, it means they have no actual argument besides WP:ILIKEIT and are looking for arguments that support their desired result rather than coming up with a result based on the merits. Also, toasters do not get to have an opinion. The Wordsmith05:17, 13 December 2024 (UTC)
Oppose. For creating unnecessary drama. First of, the "detector" of the AI bot is not reliable, or at least the reliability of the tool itself is still questionable. If the tool to detect LLM itself is unreliable, how can one reliably point out which one is LLM and which one is not? We got multiple tools that claimed to be able to detect LLM as well. Which one should we trust? Should we be elevating one tool over the others? Have there been any research that showed that the "picked" tool is the most reliable? Second, not all LLMs are dangerous. We shouldn't treat LLM as a virus that will somehow take over the Internet or something. Some editors use LLM to smooth out their grammar and sentences and fix up errors, and there is nothing wrong with that. I understand that banning obvious LLM text per WP:DUCK are good, but totally banning them is plain wrong. ✠ SunDawn ✠(contact)22:56, 15 December 2024 (UTC)
@SunDawn, the proposal is to permit editors to collapse/strike obvious LLM text, not to "ban LLM totally". If LLM use is imperceptible, like for tweaking grammar, it's not going to be affected. JoelleJay (talk) 20:17, 19 December 2024 (UTC)
Support with some kind of caveat about not relying on faulty tools or presuming that something is LLM without evidence or admission, based on the following reasons:
We have stricter rules around semi-automated editing (rollback, AutoWikiBrowser, etc.) and even stricter rules around fully automated bot editing. These cleanup edits are widely accepted as positive, but there is still the concern about an overwhelming amount of bad edits to wade through and/or fix. A form of that concern is relevant here. Someone could reply to every post in this discussion in just a minute or so without ever reading anything. That's inherently disruptive.
Nobody who is voting "oppose" is using an LLM to cast that vote. The LLM comments have been left by those supporting to make a point about how problematic they are for discussions like this. I think this reflects, even among oppose voters, a developing community consensus that LLM comments will be disregarded.
If the rule in practice is to disregard LLM comments, not writing that rule down does not stop it from being the rule, consensus, or a community norm. It just makes the rule less obvious and less clear.
It's disrespectful for an editor to ask someone to spend their time reading a comment if they couldn't be bothered to spend any time writing it, and therefore a violation of the policy Misplaced Pages:Civility, "treat your fellow editors as respected colleagues with whom you are working on an important project."
I am strongly opposed to banning or ignoring LLM-made talk page comments just because they are LLM-made. I'm not a big fan of LLMs at all; they are actually useful only for some certain things, very few of which are directly relevant to contributing to Misplaced Pages in English or in any other language. However, some of those things are useful for this, at least for some humans, and I don't want to see these humans being kicked out of the English Misplaced Pages. I already witnessed several cases in which people whose first language is not English tried writing talk page responses in the English Misplaced Pages, used an LLM to improve their writing style, and got their responses ignored only because they used an LLM. In all those cases, I had strong reasons to be certain that they were real humans, that they meant what they wrote, and that they did it all in good faith. Please don't say that anyone who wants to contribute to the English Wikipeida should, in the first place, know English well enough to write a coherent talk page comment without LLM assistance; occasionally, I kind of wish that it was like that myself, but then I recall that the world is more complicated and interesting than that. Uses of LLMs that help the English Misplaced Pages be more inclusive for good-faith people are good. Of course, defining what good faith means is complicated, but using an LLM is not, by itself, a sign of bad faith. --Amir E. Aharoni (talk) 04:52, 19 December 2024 (UTC)
Those concerned about their English should use translation software rather than an llm. Both might alter the meaning to some extent, but only one will make things up. (It's also not a sure assumption that llm text is coherent talkpage text.) CMD (talk) 07:44, 19 December 2024 (UTC)
@CMD The dividing line between translation software and LLM is already blurry and will soon disappear. It's also rare that translation software results in coherent talkpage text, unless it's relying on some (primitive) form of LLM. So if we're going to outlaw LLMs, we would need to outlaw any form of translation software, and possibly any text-to-speech software as well. ypn^223:41, 19 December 2024 (UTC)
The distinctions have already been covered above, and no we would not have to. There is an obvious difference between software intended to translate and software intended to generate novel text, and users are likely to continue to treat those differently. CMD (talk) 02:49, 20 December 2024 (UTC)
Strong oppose to the proposal as written. Misplaced Pages already suffers from being stuck in a 2001mindset and a refusal to move with the technological times. Anyone who remembers most Wikipedians' visceral reaction to FLOW and VisualEditor when they were first introduced will observe a striking similarity. Yes, those projects had serious problems, as do LLM-generated comments. But AI is the future, and this attitude of "Move slowly to avoid changing things" will ultimately lead Misplaced Pages the way of Encyclopædia Britannica. Our discussion needs to be how best to change, not how to avoid to change. ypn^223:54, 19 December 2024 (UTC)
The main objection to VE and a major objection to FLOW was the developers' insistence on transforming Wikitext to HTML for editing and then transforming that back to Wikitext. Aaron Liu (talk) 01:31, 20 December 2024 (UTC)
True. Then, as now, there were many valid objections. But IIRC, there was limited discussion of "Let's figure out a better way to improve", and lots of "Everything is fine; don't change anything, ever." That attitude concerns me. ypn^201:52, 20 December 2024 (UTC)
I oppose the proposal but I think the comparison to FLOW and VisualEditor is beyond silly. Those things did not exist outside of a MediaWiki context. LLMs are a global issue. Gnomingstuff (talk) 17:11, 28 December 2024 (UTC)
Support. I'm not even slightly swayed by these "it'll be too hard to figure out" and "mistakes could be made" and "we can't be 100% certain" sorts of arguments. That's true of everything around here, and its why we have an admins-must-earn-a-boatload-of-community-trust system, and a system of review/appeal of decisions they (or of course non-admin closers) make, and a consensus-based decisionmaking system more broadly. JoelleJay has it exactly right: having a policy that permits closers to discount apparently-LLM-generated contributions will discourage good-faith editors from using LLMs irresponsibly and perhaps motivate bad-faith editors to edit the raw output to appear more human, which would at least involve some degree of effort and engagement with their "own" arguments. And as pointed out by some others, the "it'll hurt non-native-English speakers" nonsense is, well, nonsense; translation is a different and unrelated process (though LLMs can perform it to some extent), of remapping one's own material onto another language.
I'm also not in any way convinved by the "people poor at writing and other cognitive tasks needs the LLM to help them here" angle, because WP:COMPETENCE is required. This is work (albeit volunteer work), it is WP:NOT a game, a social-media playground, a get-my-ideas-out-there soapbox, or a place to learn how to interact e-socially or pick up remedial writing skills, nor a venue for practicing one's argument techiques. It's an encyclopedia, being built by people who – to be productive contributors instead of a draining burden on the entire community – must have: solid reasoning habits, great judgement (especially in assessing reliability of claims and the sources making them), excellent writing skills of a highly particularized sort, a high level of fluency in this specific language (in multiple registers), and a human-judgement ability to understand our thick web of policies, guidelines, procedures, and often unwritten norms, and how they all interact, in a specific contextual way that may vary greatly by context. None of these is optional. An LLM cannot do any of them adequately (not even write well; their material sticks out like a sore thumb, and after a while you can even tell which LLM produced the material by its habitual but dinstictive crappy approach to simulating human thought and language).
In short, if you need an LLM to give what you think is meaningful input into a decision-making process on Misplaced Pages (much less to generate mainspace content for the public), then you need to go find something else to do, something that fits your skills and abilities. Saying this so plainly will probably upset someone, but so it goes. I have a rep for "not suffering fools lightly" and "being annoying but correct"; I can live with that if it gets the right decisions made and the work advanced. — SMcCandlish☏¢ 😼 05:49, 22 December 2024 (UTC)
PS, something that came up more recently than my original post above: If anyone's wondering why some of us are such "AI" skeptics, its because the technology is badly, badly faulty, producing multiple blatant factual errors even in short material, entirely fictive "hallucinations", direct forgery of sourcing, nested chains of error compounded upon error when context isn't gleaned properly, disingenuous attempts to hide that it is lying, and worse. A few days ago, I got ChatGPT 4o to literally lose its f#*$ing mind: I had it generate some short code (very simple one-liner regex) with a really obvious error, so I pointed out the error and gave it documentation that proved it was an error. It conceded the error and even explained what the error was and why it was erroneous, then said how it was going to fix it. And ... proceeded to output the same error again (in just one of three examples, the other two being correct). Fascinated and horrified by this, I tried for over half an hour to get it to produce a correct example, and it was utterly incapable of doing it. It knew the error was an error and what that error was and why, spelled out what the correct approach should be, then repeated the error every single time (always at the first occurrence, or always if the only occurrence). I've captured that session and will be doing a write-up about it. This is much, much worse that a "hallucination", being an abject inability to stop doing what it already knows is absolutely wrong. When people have fears like "If I had a house AI, and it was in control of the bathwater temperature, it might boil my children alive", they are not paranoid or unreasonable. My experiment with ChatGPT proves this conclusively. If the AI can (with trivial effort) be put into a crazy failure-looping state where it knows it's doing or about to do something wrong but insists on doing it anyway – i.e. during its take-an-action phase it completely loses connection to reality, even it's internal reality much less external input telling it "no!" – then we are in grave danger. This is essentially the mental state of a psychopath: "I know I shouldn't grab my neighbor's little daughter and strangle her to death, but I just can't stop myself." — SMcCandlish☏¢ 😼 01:42, 28 December 2024 (UTC)
The problem with all that is that we already have a policy that allows the hatting or removal of comments that are actually problematic because of their content (which are the only ones that we should be removing) without regard for whether it was or was not written by LLM. Everything that actually should be removed can be removed already. Thryduulf (talk) 11:39, 22 December 2024 (UTC)
If that's "the problem with all that", then it is not any kind of problem at all. It's entirely normal in our WP:P&G material to reiterate a principle defined in one place for contextual application at another, and to extrapolate from a general principle to a more specific application. We do this often to cut through the exact kind of wikilawyering we're facing over this issue: there's not a specific rule against LLM-generated !voting, so the argument is (again and again in this thread) to permit it (unless it's such senseless gibberish that it would be removed anyway even if no LLM were involved). The community clearly doesn't actually want that result (or more accurately, there is not a consensus in favor of it), though this specific proposal's approach to thwarting the "AI"-spamming of our decision-making processes might not be perfect. To me, it's a step in the right direction. If it were implemented this way and some uncommon issue arose with that implementation, then we'd tweak it to address that micro-problem. We must not continue to avoid addressing the macro-problem just because someone can imagine edge cases that might not work out ideally. That, too, is true of all of our P&G and process. — SMcCandlish☏¢ 😼 01:15, 28 December 2024 (UTC)
People who have good reading skills, great judgement, and solid reasoning habits enough to find problems in existing articles don't necessarily have great interpersonal writing/communication skills or the confidence. Meanwhile, for all LLM is bad at, it is very good at diluting everything you say to become dry, dispassionate, and thus inoffensive. Aaron Liu (talk) 15:26, 22 December 2024 (UTC)
I doubt that anyone would seriously object to some ultra-hothead running their post through an LLM with a query like "Can you see anything in this that might come off as aggressive or offensive, and suggest a revision that only affects that aspect of the material?" The result might not even be noticeable as LLM-modified. If it doesn't stick out as LLM garbage, there there is no way for this proposal to affect such a post, because no one here is a mind-reader (we cannot magically detect through remote sensing that someone toned their rant down with LLM help). So, this proposal is not broken (at least not with regard to that scenario). That said, the main reason that WP:COMPETENCE was written (and it's one of the essays that, like WP:BRD and WP:AADD, has become "operative" within the community as if a policy or guideline) is the very "don't necessarily have great interpersonal ... skills" issue you mention. That is, lacking those skills to a serious enough degree makes one not competent to work on a collaborative encyclopedia project, and one will eventually be ejected after causing enough disruption. Something we don't need is LLMs masking for a while that someone has this kind of competence failure; it will just drag out the inevitable. By way of analogy: if I were a kleptomaniac and just unable to stop myself from shoplifting, it would not be okay for me to use a device that scrambled stores' surveillance camera footage to make it more likely for me to get away with more shoplifting (and there would certainly be no obligation on the part of the store owner to turn their cameras off, or to take no action if they catch me stealing, just because I tell them I'm a kleptomaniac and my unconstructive behavior isn't something I can manage. — SMcCandlish☏¢ 😼 01:15, 28 December 2024 (UTC)
People who can't communicate that well often won't attempt to burn others down. I don't think there's any disruption or substantial additional investment in accommodating those who won't burn others down (which I'd say is the majority) by reading their perfectly comprehensible AI-diluted arguments. (Scrambling footage is like erasing the memories of the incident, which I don't think is a good analogue of the issue at hand. I'd say it's more like working with someone who stinks and masks that with perfume.) Aaron Liu (talk) 00:05, 29 December 2024 (UTC)
I'm pretty sure most people here understand why there are AI skeptics. I also hate ChatGPT. But there's a difference between my personal opinion of ChatGPT and the fact that someone using ChatGPT to communicate is still communicating. The risk of your house AI hallucinating is that your children get boiled alive. The risk of ChatGPT hallucinating on a talk page is that they make a dumb, disregardable argument, of the kind that humans pump out by the thousands. (Someone linked an example of some AfD delete !votes generated by AI and frankly they're better reasoned than a lot of the stuff humans post.) Gnomingstuff (talk) 17:32, 28 December 2024 (UTC)
(The bigger issue is people using Misplaced Pages as ChatGPT -- i.e. posting the prompts, not the responses -- but, like much of what is being discussed here, that is already stuff that can be removed.) Gnomingstuff (talk) 17:36, 28 December 2024 (UTC)
Support. Sure I have questions about detection, but I don't think it means we shouldn't have a policy that explicitly states that it should not be used (and can be ignored/hatted if it is). Judging solely based on content (and no wp:bludgeoning, etc.) is unsustainable IMO. It would mean taking every wall of text seriously until it's clear that the content is unhelpful, and LLMs are very good at churning out plausible-sounding bullshit. It wastes everyone's time. If cognitive impairments or ESL issues make it hard to contribute, try voice-to-text, old-school translation software, or some other aid. LLMs aren't really you.--MattMauler (talk) 11:27, 23 December 2024 (UTC)
Comment. While I agree with the sentiment of the request, I am at a loss to see how we can identify LLM generated comments in a consistent manner that can scale. Yes, it might be easier to identify egregious copy paste of wall of text, but, anything other than that might be hard to detect. Our options are:
Robust tooling to detect LLM generated text, with acceptably low levels of false positives. Somewhat similar to what Earwig does for Copyvios. But, someone needs to build it and host it on WMTools or at a similar location.
Self certification by editors. Every edit / publish dialogbox should have a checkbox for "Is this text LLM generated" with y/n optionality.
Editors playing a vigilante role in reading the text and making a personal call on other editors' text. Obviously this is least preferred.
A couple of days ago, an editor ran a new article through GPTzero, and was told that it was 99.8% likely to be AI-generated. I ran the same revision of the same article through the same tool the next day, and it told me that it was 98.3% likely to be human-written.
Bonus suggestion!: I'm curious what Wikipedians think about this so let's try this. Many of the comments here discuss the impracticality of determining whether a user's comments are AI generated (i.e. gptzero isn't perfect), and many give valid arguments for using LLMs (i.e. ESL). If an argument is suspected to be written by LLM, I propose that editors should examine the user. Take a look at their listed contributions, and if they seem to have a habit of using AI, open a discussion on their talk page. If the user has a habit of using AI and doesn't recognize the inherent problems and refuses to change, this can be brought to the administrators' noticeboard for potential blocks. If (and only if) the person is blocked for using AI, their comments can be ignored. Or just ask ChatGPT to summarize them for you lol guninvalid (talk) 06:12, 25 December 2024 (UTC)
I think that the general idea here is good: As much as possible, treat each account individually, and handle LLM use as a behavioral problem when it's actually a practical problem (i.e., not when it seems to be accurate and seems to be appropriate). WhatamIdoing (talk) 04:38, 26 December 2024 (UTC)
Except a substantial portion of the input in this thread is disagreement with the idea that English being someone's second language is an excuse for LLM-generated content at all. Translation of one's own material is an entirely different process (even if often leveraged by LLMs set to a different task than trying to generate what they "think" is new material that will pass as human-authored). I'm skeptical that any of the other things you're accepted as "valid arguments" from the pro-LLM or LLM-accepting side of this debate have consensus as valid, either. But go ahead and spell them out and we'll see. — SMcCandlish☏¢ 😼 01:30, 28 December 2024 (UTC)
Strong support the removal of any obvious, low effort AI-generated post. I recently came across a user postingmultiple such examples. When called out on it they blew up and posted a comment saying, amongst other things "HAHAHAHHAHAHAHAHAHAHHAHAHAHAHAHA. Yes, some of it might be. Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people." and "YOUUUUUUUUUUUUUUUUUUUUUUUUUUUU are assuming bath faith in me."
They were later blocked as a sock evading a global lock.
Currently it is too easy for trolls to game WP:AGF and AI to waste people's time arguing with their bot-generated replies. Using AI to write your posts for you makes it difficult for others to assume good faith. I am ok with obvious exceptions like a non-native speaker using AI to help them articulate their point. Photos of Japan (talk) 21:29, 25 December 2024 (UTC)
Support for now. I believe the foundation should be busy ramping up support in this arena of distraction. IMHO, we are in the calibration phase of the use of these models. We don't feed trolls and we shouldn't tutor LLMs. Since assumption of good faith is not suicide pact, we shouldn't rely overmuch for guidance on edge cases. The issues as I see them are attribution (how do I know where your idea has been?), obedience to social norms (I not-here blocked someone recently for brazenly using ChatGPT to lie about using LLMs; the user proceeded to use GPT to post unblock requests), and a vast canyon between the limited human and financial resources of the foundation and the unlimited resources of bad actors with vast sums of money who would like to see Misplaced Pages less able. I have hopes we can get some higher visibility anti-LLM support (like a flag in my mouseover which always reports a percentage, so I know to check). This fire is burning now. It would be unwise to ignore this much longer. BusterD (talk) 16:28, 29 December 2024 (UTC)
Support with the clarification that use of AI assistance is not prohibited, as long as its contribution is <<50%. For example, using Grammarly for spell check and grammar/syntax is OK, but using AI to do your homework is not. Dhaluza (talk) 02:45, 30 December 2024 (UTC)
Support a ban on comments that were primarily generated by AI, with such comments to be deleted or struck-through as appropriate, because it's inherently misleading to pass off a chatbot's words as your own. Using ML-based spell-checkers is fine. I've seen some users call ChatGPT an "accessibility tool", but if you're not capable of communicating on English Misplaced Pages without a LLM doing it for you, then I don't think English Misplaced Pages is a good community for you to participate in. — Preceding unsigned comment added by Pythoncoder (talk • contribs) 21:45, 31 December 2024 (UTC)
Just read this ANI thread, where an editor was indeffed per WP:NOTHERE after exclusively using LLMs to edit, even when responding within that very thread. The situation was a clear case of WP:CIR, which I surely would've cited in my original comment had the page name come to mind. —pythoncoder (talk | contribs) 04:34, 3 January 2025 (UTC)
That they were banned for CIR shows we don't need anything new to deal with disruption specifically caused by people using LLMs. Thryduulf (talk) 05:29, 3 January 2025 (UTC)
Support A popular notion in many, many other discussions is "our most valuable resource is editor time". This applies here more than in most instances - editors cannot be expected to wear themselves out in engaging at length with the results of someone's one-line prompt to an LLM. Where LLM use in articles is destructive of content and source reliability, in discussions it is destructive of editor good faith. If you can't be bothered to put your arguments into intelligible form, don't participate. If your language capacity is lacking to the extent that you have to have a program generate (as opposed to polish) your stuff, you probably don't have any business participating either. Human detection ability seems quite sufficient for these cases (and once it ceases to, well, we'll deal with that when it becomes an issue). --Elmidae (talk · contribs) 12:00, 2 January 2025 (UTC)
Human detection ability seems quite sufficient for these case these discussions have already proven that human detection is not reliable, with human-generated comments labelled as AI and AI-generated comments labelled as human. Why should we prohibit LLM-generated content that is accurate, relevant and intelligible? We can already ignore/remove content that is none of those things regardless of whether it is LLM-generated or not. Thryduulf (talk) 12:21, 2 January 2025 (UTC)
If you want a pithy in-a-nutshell: personal effort is buy-in in a discussion among equals. If your personal effort in a discussion is an LLM prompt, no editor should be expected to engage with you. --Elmidae (talk · contribs) 12:42, 2 January 2025 (UTC)
What matters is whether people are engaging with each other constructively and in good faith. Whether one or both parties is using an LLM is completely irrelevant to both aspects. Thryduulf (talk) 13:29, 2 January 2025 (UTC)
Nobody is forcing you to engage with anybody or anything you don't want to engage with, but you do not get to state who other people are allowed to choose to engage with. As long as someone is engaging constructively and in good faith I don't care whether they are human or machine, because (a) I have no reliable way of knowing, and (b) it is literally irrelevant to me. Thryduulf (talk) 14:14, 2 January 2025 (UTC)
you do not get to state who other people are allowed to choose to engage with Strawman, since I didn't do that. Only you are doing that. Selfstudier (talk) 14:26, 2 January 2025 (UTC)
Quite the contrary - you are saying that nobody should be allowed to engage with someone using an LLM because you do not want to engage with someone using an LLM. My position is that everybody should be allowed to choose who they want and do not want to engage with for themselves. Thryduulf (talk) 14:42, 2 January 2025 (UTC)
Support in principle - Using entirely AI-generated text in discussion is not a valuable contribution, since ultimately it is not capable of thought, but there should be leniency for those who are simply using AI to improve something they already wrote. FOARP (talk) 14:55, 2 January 2025 (UTC)
Support in principle We don't want LLMs opinions. IF and WHEN we do we'll ask for an extension with some AI making an openig analysis of nominations. But we can not, and want not, to excludes cases where some user forms their opinion chating with some AI, as it was brillianttely shoen above, nor we want to exclude anyone lee proficient with the language just "because it looks like a bot". - Nabla (talk) 18:13, 2 January 2025 (UTC)
Support in principle, strongly concerned in potential practice - I like the idea of removing what is verifiably generated by a LLM. On the other hand, I've read that autistic writers may be more likely to have their (completely non-AI) writing flagged as potential AI use by automated detectors. I think it could be a problem if a rule that's good in principle could start disproportionately affecting some editors (who are not doing the thing) more than others (who are not doing the thing) in practice, whether that come from human (i.e. other editor) bias or automated tools. - Purplewowies (talk) 18:36, 3 January 2025 (UTC)
Strongly support per ChatGPT (EEng) and SMcC; I'm not at all concerned about edit accessibility to non-native speakers; WP:COMPETENCE, after all, is required to contribute to this project. I also oppose any breaking of the line against AI-generated plausible-sounding and -looking slop. We can't have a Misplaced Pages of LLMs talking to LLMs on how to make LLM content for LLM articles. Iseulttalk to me21:53, 4 January 2025 (UTC)
Support per SMcCandlish. If someone needs to use a LLM to be able to contribute and is unable to convert the output into something that is not obviously AI-generated, then WP:CIR likely applies. It'll be impossible to stop minimal usage cases, but having such a rule in place would at least encourage editors to review their output and stop the unhelpful posting off entire ChatGPT essays to discussion spaces. -- Patar knight - /contributions01:41, 6 January 2025 (UTC)
Strong... opinion -- I think the nuance required here in part is the difference between someone using any automated tool for assistance, versus true bot-like behavior. I believe that unauthorized bot behavior is already prohibited, which should help address the concerns that we mere humans cannot keep up with LLM bots. I agree, we cannot, but I don't see much of that. I am also not inclined to the "if you cannot write, you cannot contribute"... I can imagine 15 years ago some of us might have made the same statement about spelling and grammar; if you cannot spell properly without auto-correct you have no right to edit an encycolopedia. The are significant number of very intentilligent people who are afflicted with things like dyslexia, aspurgers, etc. who have been contributing using various technology tools for assistance. How may of us have Grammarly or similar running on their web browser? And beyond that tools and what they're called will continue to evolve. I am very much against just banning LLM use; largely because it can turn into an unnecessary witch hunt. There are people who will use the tools constructively, and those who will not. I can see some places where it should probably be banned (such as using a LLM to determine consensus on a discussion that needs closing (AfD, RM, etc)). But even in those areas, I think many of our existing policies and guidelines already address most of the actual concerns we're seeing when it comes to that activity. Cheifly that as long as people are being held accountable for how they use the tools, then who cares what the tool is called in 2000, 2020 or 2040? So I think the course forward is best served by (1) Consider refinement to WP:BOTP so that we're encapsulating LLM type bot behavior, as well as some sort of threshold on "non-human" capable editing limits (perhaps as part of WP:MEATBOT; (2) make a policy or guidelines very clear, bright line, that a user will be treated the same regardless of what tools they use, LLM or otherwise, and that disruptive editing will be handled accordingly. (2a) perhaps a single-warning template reflective of such, to welcome people who appear to be using LLM, and that they are responsible for their adherence to policy and that LLMs tend to get policy wrong. TiggerJay(talk)02:48, 7 January 2025 (UTC)
The proposal is focused on comments that are obviously generated by LLM, which would not include non-generative AI processes like Grammarly or translation. The whole issue is arguments that were clearly created by a chatbot etc. doing its own analysis of a discussion and an editor just pasting that output rather than forming the argument themselves, which results in large amounts of text that other editors/closers then have to read and respond to. JoelleJay (talk) 22:26, 7 January 2025 (UTC)
To be honest, that's my concern. What if something seems obviously generated by LLM but is entirely human-written? What if certain groups of editors are more likely to produce seemingly LLM text that isn't generated by any LLM at all? Is there a way to control for that? How do we consistently enforce this kind of thing without too many false positives or false negatives?
Replying to the top-level opinion at this point: Most autistic people who would have in the past received an Asperger's diagnosis, barring some other reason, would IMO not be more likely to "need" more assistive technology (LLM or otherwise) to contribute to Misplaced Pages articles and discussions than any other user. However, there have been reports that autistic people may be more likely to produce text that is falsely positive in AI detection tools. See this story about a Purdue professor as one example (I had a second example, I thought, except that I've apparently read my last free article on that site (I bet I read said last article when looking up the same article when I wrote my !vote a few days back, Facepalm). Not gonna link what I can't (quickly) verify!)) (As an aside, I think "afflicted with" can come across as a bit... charged? Just something to note.)
The mention of Data in particular only heightens my concern because--while no one has accused me yet of using LLM when I write--I have (on other sites, not here) been accused of being a bot before because of the style of writing I adopt at times. What if editor bias disproportionately plays into who is suspected of LLM use and who isn't? What if imperfections in automated AI detection only serve to cement the bias? - Purplewowies (talk) 01:25, 8 January 2025 (UTC)
These questions around controlling for false positives and false negatives are not new, we face them all the time already, for example distinguishing vandalism from good faith contributions. We work through them, but they don't mean we don't have a policy on vandalism. CMD (talk) 01:41, 8 January 2025 (UTC)
Indeed, that's why my original !vote is (in short) "support but concerned". I definitely think I'd support a policy; I'm just raising questions/concerns I think are worth considering in the process of creating such a policy. I think some part of me is just remembering times I've seen bias negatively affect the project in the past and that part of me is coming out here trying to prevent another situation like that by laying the concerns out. I dunno. - Purplewowies (talk) 03:59, 8 January 2025 (UTC)
I think Joelle what you're overlooking in that statement is that obviously generated is something that is going to be short lived, meaning that it will not be very long before the LLM generated content will be far harder to distinguish. Just like how just a year ago any generative image AI would often get the number and/or placement of fingers wrong on a person's hand, in less than a years time that appears to generally be solved. Today the tell tail signs is even if you ask for someone who is left handed, you'll almost always get an image of a right handed person... But that too will go away shortly. I believe it is (scarily) not too far off, when LLMs can determine the prompt is for Misplaced Pages (by way of seeing the wikimarkup or references to normal wiki policies), and among other things, write in the style of experienced editors, perhaps modeled off of some of us in this very discussion. That will be much more difficult to tell, especially when it learns how to not be soo overly polite and apologetic. Beyond that, I believe there are a lot of people successfully and positively using LLMs already on WP. For those reasons, I proffer that we focus on refining the definitions and parameters for general disruptive editing (such as EW, RRR, etc), what a bot edit/activity is, and perhaps a standardized "friendly welcome" and "friendly notice" for those suspected of using LLMs, and reinforce that the tool matters less than the behavior. I think the analogy I'm going for is that of how we handle socks -- it is not against policy to have multiple accounts, however, when it is disruptive, it is blatantly prohibited. But the signs and symptoms of socks is really what we care about. TiggerJay(talk)05:02, 8 January 2025 (UTC)
Something can be prohibited even if it is or will be difficult to identify it. Just because we can anticipate AI-generated slop becoming harder to detect doesn't mean it's not still disruptive or that we shouldn't be able to strike it when it is obvious. JoelleJay (talk) 23:41, 9 January 2025 (UTC)
Strong support for striking AI-generated comments. Detection of course will be up to admin discretion, but so is things like incivility and personal attacks; while short snippets of AI generated text are hard to detect, lengthy paragraphs are quite easy to eyeball, and from my experience that's the area where it's most likely to come up and most immediately disruptive. Generalissima (talk) (it/she) 22:25, 9 January 2025 (UTC)
Supportfor striking AI-generated comments. Detection of course will be up to admin discretion as are other behavioural preoblems. Having read most of the discussion, and having been astonished by the 'individuality' of some machine-generated content, nonetheless, while detection may be less-than-foolproof, I still think we should make the point that such content isn't acceptable. It should be within our capacity to make the distinction between 'machine-generated' content and the use of software to correct grammar or to translate, neither of which should be directly outlawed.Pincrete (talk) 07:18, 10 January 2025 (UTC)
But why should such content be deemed unacceptbale when there are no problems with it? When there are problems with it, it can and should be dealt with in the same way that those problems are dealt with when written by humans. Thryduulf (talk) 18:25, 10 January 2025 (UTC)
Request for closure
IMHO, since we're over 30 days and the argument consensus seems lopsided, the community would do well to close this rapidly (as opposed to waiting for additional comments). BusterD (talk) 21:04, 2 January 2025 (UTC)
Sure it looks lopsided if you only read what has been bolded. When you look beyond at what those bolding support are actually supporting it's not at all clear there is a consensus. Then when you actually look at the arguments made it seems that there is not actually a consensus for anything other more than "some users vocally dislike AI". Thryduulf (talk) 21:59, 2 January 2025 (UTC)
I was merely pointing out that BusterD's stated reason for calling for closure now is incorrect. That doesn't mean closing now would necessarily be wrong, just that overwhelming consensus is not a reason for it. Thryduulf (talk) 22:25, 2 January 2025 (UTC)
As a sysop, reacting to LLM-related abuse is virtually all I've done in the last week or so. We have a pressing need for some help from the community, and while I'm open to discussion on this, it's unreasonable to expect humans to keep up with bot-like behavior. I've made my argument above, and I'll not disagree further here. BusterD (talk) 00:08, 3 January 2025 (UTC)
Many on the “support” side are also supporting with conditions instead of an unconditional support. For instance, many have suggested that LLM that supported grammars are okay.
There are multiple breaks and 391 comments now. At this scale, it becomes difficult for a human to digest and summarise it all. AI technology seems well suited to this and so asked Gemini again "Please summarise the consensus of the following RFC:" giving it all the discussion above. Its response was much as before:
The RFC on LLM/chatbot comments in discussions is contentious, with a significant number of editors on both sides of the issue.
Support
Many editors support the proposal to discount or remove LLM-generated comments in discussions. Their arguments include:
LLMs do not have original thoughts or arguments and therefore do not contribute meaningfully to discussions.
LLM-generated comments can be disruptive, wasting editors' time and derailing discussions.
LLMs can be used by bad-faith actors to manipulate consensus or spread misinformation.
Editors should be encouraged to participate in discussions using their own words and thoughts.
Oppose
Other editors oppose the proposal, arguing that:
LLMs can be useful tools for editors who have difficulty expressing themselves in English, such as non-native speakers or those with disabilities.
LLM-generated comments should be evaluated on their merits, not their origin.
Detection of LLM-generated comments is unreliable and could lead to false positives.
A ban on LLM-generated comments could discourage participation from editors who rely on these tools.
Additional points
There is disagreement about whether machine translation should be considered LLM-generated content.
Some editors believe that LLMs could be used constructively in discussions, for example, to summarize arguments or provide alternative perspectives.
Others are concerned about the potential for LLMs to be used maliciously, for example, to flood discussions with irrelevant comments or to impersonate other editors.
Overall
There is no clear consensus on whether to ban or allow LLM-generated comments in discussions. The discussion highlights the challenges of balancing the potential benefits and risks of using LLMs in a collaborative environment like Misplaced Pages.
That was a good answer but I wanted to get a rough headcount and so asked a supplementary question, "What was the count of the number of support and opposing votes in the discussion?" The answer was:
Unfortunately, a precise count of support vs oppose votes in that discussion is difficult to determine definitively for a few reasons:
Some votes are unclear: Several editors express nuanced positions or change their vote during the discussion.
"Strong" votes aren't quantified: While many editors use "Strong support" or "Strong oppose", these don't carry extra weight in a simple tally.
Focus shifts: The initial focus on AI-generated comments broadens to include AI-assistance, making some votes less clear-cut.
However, based on a rough manual count:
Support: Around 60-70 votes clearly favor discounting or removing AI-generated comments.
Oppose: Roughly 30-40 votes lean against the proposal, with varying degrees of opposition.
Important Note: This is an approximation. The actual consensus in such discussions is determined by the closer, who weighs the arguments' quality and policy relevance, not just the number of votes.
This seems to be another good answer – better than we get from most human closes. I made a rough manual count to confirm that the numbers given are reasonable ballpark figures. And it seems to have an impressive grasp of nuance – noticing that several editors were qualifying their votes as strong/weak and that some editors changed their vote. Andrew🐉(talk) 22:02, 10 January 2025 (UTC)
These feel (from my memory of when I skimmed over the discussion several days ago before my original !vote/comment) like they might be leaving out some relevant points that came up. (Unfortunately I can't quantify that without taking a look which I don't have time to do right now (other than the fact my own concerns didn't make it into the summary, which... fair, I guess, considering I was the only one who raised that specific issue).) (I'm also very surprised it came up with something coherent as well as on topic, but that just has more to do with the fact Gemini (or at least whatever AI summarizes Google searches) told me extremely recently that I could get to Alaska by car without a passport if I drove through the ocean. Not took a ferry but drove... through the water... in a car.) - Purplewowies (talk) 07:02, 11 January 2025 (UTC)
Your !vote was a qualified support with concern about false positives affecting editors such as the autistic. That's then a nuanced, both-ways vote and the Gemini summary seems to capture that reasonably well. Andrew🐉(talk) 09:43, 11 January 2025 (UTC)
My vote was mentioned purely because it was the only specific thing I could bring to mind quickly that hadn't ended up in the AI summary. I think Thryduulf's take about what it doesn't make clear more closely matches what I think I was actually feeling about the summary (that it doesn't make clear the wide breadth of what the support !votes are actually saying). - Purplewowies (talk) 19:08, 11 January 2025 (UTC)
On the whole that summary matches my impression of discussion, with the exception that it doesn't make it clear that not everyone expressing support is supporting the same thing. Thryduulf (talk) 14:38, 11 January 2025 (UTC)
Ok, what point is there to having AI summarize consensus? Consensus should be based on the strength of individual arguments, which only an experienced human editor can assess; AI can only guess what arguments look like. It's especially weird to use it here since if, theoretically, the AI summary decides there is consensus against considering AI comments in Misplaced Pages discussions, then that would include AI summary itself, leading to Russell's paradox. Lazman321 (talk) 19:41, 11 January 2025 (UTC)
Alternate proposal
The following discussion is closed. Please do not modify it. Subsequent comments should be made in a new section.A summary of the conclusions reached follows.
Whereas many editors, including me, have cited problems with accuracy in regards to existing tools such as ZeroGPT, I propose that remarks that are blatently generated by a LLM or similar automated system should be discounted/removed/collapsed/hidden. ThatIPEditor10:00, 10 December 2024 (UTC)
Oppose as completely unnecessary and far too prone to error per the above discussion. Any comment that is good (on topic, relevant, etc) should be considered by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is bad (off-topic, irrelevant, etc) should be ignored by the closer regardless of whether it was made with LLM-input of any sort or not. Any comment that is both bad and disruptive (e.g. by being excessively long, completely irrelevant, bludgeoning, etc) should be removed and/or hatted as appropriate, regardless of whether it was made with LLM-input of any sort. The good thing is that this is already policy so we don't need to call out LLMs specifically, and indeed doing so is likely to be disruptive in cases where human-written comments are misidentified as being LLM-written (which will happen, regardless of whether tools are used). Thryduulf (talk) 11:19, 10 December 2024 (UTC)
I think this proposal is not really necessary. I support it, but that is because it is functionally identical to the one directly above it, which I also supported. This should probably be hatted. BugGhost🦗👻18:32, 10 December 2024 (UTC)
What does blatantly generated mean? Does you mean only where the remark is signed with "I, Chatbot", or anything that appears to be LLM-style? I don't think there's much in between. ypn^219:21, 10 December 2024 (UTC)
Procedural close per BugGhost. I'd hat this myself, but I don't think that'd be appropriate since it's only the two of us who have expressed that this proposal is basically an exact clone. Aaron Liu (talk) 03:00, 11 December 2024 (UTC)
The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Option 1 – Require former administrators to request restoration of their tools at the bureaucrats' noticeboard (BN) if they are eligible to do so (i.e., they do not fit into any of the exceptions).
Option 2 – Clarify Maintain the status quo that former administrators who would be eligible to request restoration via BN may instead request restoration of their tools via a voluntary request for adminship (RfA).
Option 3 – Allow bureaucrats to SNOW-close RfAs as successful if (a) 48 hours have passed, (b) the editor has right of resysop, and (c) a SNOW close is warranted.
2, after thought. I don't think 3 provides much benefit, and creating separate class of RfAs that are speedy passed feels a misstep. If there are serious issues surrounding wasting time on RfAs set up under what might feel to someone like misleading pretenses, that is best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)". CMD (talk) 14:49, 16 December 2024 (UTC)
best solved by putting some indicator next to their RFA candidate name. Maybe "Hog Farm (RRfA)" - I like this idea, if option 2 comes out as consensus I think this small change would be a step in the right direction, as the "this isn't the best use of time" crowd (myself included) would be able to quickly identify the type of RFAs they don't want to participate in. BugGhost🦗👻11:05, 17 December 2024 (UTC)
I think that's a great idea. I would support adding some text encouraging people who are considering seeking reconfirmation to add (RRfA) or (reconfirmation) after their username in the RfA page title. That way people who are averse to reading or participating in reconfirmations can easily avoid them, and no one is confused about what is going on. 28bytes (talk) 14:23, 17 December 2024 (UTC)
If we are differentiating three types of RFA we need three terms. Post-recall RFAs are referred to as "reconfirmation RFAs", "Re-RFAS" or "RRFAs" in multiple places, so ones of the type being discussed here are the ones that should take the new term. "Voluntary reconfirmation RFA" (VRRFA or just VRFA) is the only thing that comes to mind but others will probably have better ideas. Thryduulf (talk) 21:00, 17 December 2024 (UTC)
2 I don't see why people trying to do the right thing should be discouraged from doing so. If others feel it is a waste of time, they are free to simply not participate. El Beeblerino21:27, 15 December 2024 (UTC)
Of course they may request at RfA. They shouldn't but they may. This RfA feels like it does nothing to address the criticism actually in play and per the link to the idea lab discussion it's premature to boot. Barkeep49 (talk) 21:38, 15 December 2024 (UTC)
2 per my comments at the idea lab discussion and Queent of Hears, Beeblebrox and Scazjmd above. I strongly disagree with Barkeep's comment that "They shouldn't ". It shouldn't be made mandatory, but it should be encouraged where the time since desysop and/or the last RFA has been lengthy. Thryduulf (talk) 21:42, 15 December 2024 (UTC)
When to encourage it would be a worthwhile RfC and such a discussion could be had at the idea lab before launching an RfC. Best, Barkeep49 (talk) 21:44, 15 December 2024 (UTC)
1 or 3. RFA is an "expensive" process in terms of community time. RFAs that qualify should be fast-tracked via the BN process. It is only recently that a trend has emerged that folks that don't need to RFA are RFAing again. 2 in the last 6 months. If this continues to scale up, it is going to take up a lot of community time, and create noise in the various RFA statistics and RFA notification systems (for example, watchlist notices and User:Enterprisey/rfa-count-toolbar.js). –Novem Linguae (talk) 21:44, 15 December 2024 (UTC)
Making statistics "noisy" is just a reason to improve the way the statistics are gathered. In this case collecting statistics for reconfirmation RFAs separately from other RFAs would seem to be both very simple and very effective. If (and it is a very big if) the number of reconfirmation RFAs means that notifications are getting overloaded, then we can discuss whether reconfirmation RFAs should be notified differently. As far as differentiating them, that is also trivially simple - just add a parameter to template:RFA (perhaps "reconfirmation=y") that outputs something that bots and scripts can check for. Thryduulf (talk) 22:11, 15 December 2024 (UTC)
I'm weakly opposed to option 3, editors who want feedback and a renewed mandate from the community should be entitled to it. If they felt that that a quick endorsement was all that was required then could have had that at BN, they explicitly chose not to go that route. Nobody is required to participate in an RFA, so if it is going the way you think it should, or you don't have an opinion, then just don't participate and your time has not been wasted. Thryduulf (talk) 22:20, 15 December 2024 (UTC)
Added option 3 above. Maybe worth considering as a happy medium, where unsure admins can get a check on their conduct without taking up too much time. theleekycauldron (talk • she/her) 22:11, 15 December 2024 (UTC)
2 – If a former admin wishes to subject themselves to RfA to be sure they have the requisite community confidence to regain the tools, why should we stop them? Any editor who feels the process is a waste of time is free to ignore any such RfAs. — Jkudlick ⚓ (talk)22:12, 15 December 2024 (UTC)
I would also support option 3 if the time is extended to 72 hours instead of 48. That, however, is a detail that can be worked out after this RfC. — Jkudlick ⚓ (talk)02:05, 16 December 2024 (UTC)
A further note: option 3 gives 'crats the discretion to SNOW close a successful voluntary re-RfA; it doesn't require such a SNOW close, and I trust the 'crats to keep an RfA open if an admin has a good reason for doing so. voorts (talk/contributions) 23:24, 16 December 2024 (UTC)
Option 2 (no change) – The sample size is far too small for us to analyze the impact of such a change, but I believe RfA should always be available. Now that WP:RECALL is policy, returning administrators may worry that they have become out of touch with community norms and may face a recall as soon as they get their tools back at BN. Having this familiar community touchpoint as an option makes a ton of sense, and would be far less disruptive / demoralizing than a potential recall. Taking this route away, even if it remains rarely used, would be detrimental to our desire for increased administrator accountability. – bradv22:22, 15 December 2024 (UTC)
2, distant second preference 3. I would probably support 3 as first pick if not for recall's rule regarding last RfA, but as it stands, SNOW-closing a discussion that makes someone immune to recall for a year is a non-starter. Between 1 and 2, though, the only argument for 1 seems to be that it avoids a waste of time, for which there is the much simpler solution of not participating and instead doing something else. Special:Random and Misplaced Pages:Backlog are always there. -- Tamzin (they|xe|🤷) 23:31, 15 December 2024 (UTC)
Option 1. No second preference between 2 or 3. As long as a former administrator didn't resign under a cloud, picking up the tools again should be low friction and low effort for the entire community. If there are issues introduced by the recall process, they should be fixed in the recall policy itself. Daniel Quinlan (talk) 01:19, 16 December 2024 (UTC)
Option 2, i.e. leave well enough alone. There is really not a problem here that needs fixing. If someone doesn’t want to “waste their time” participating in an RfA that’s not required by policy, they can always, well, not participate in the RfA. No one is required to participate in someone else’s RfA, and I struggle to see the point of participating but then complaining about “having to” participate. 28bytes (talk) 01:24, 16 December 2024 (UTC)
Option 3: Because it is incredibly silly to have situations like we do now of "this guy did something wrong by doing an RfA that policy explicitly allows, oh well, nothing to do but sit on our hands and dissect the process across three venues and counting." Your time is your own. No one is forcibly stealing it from you. At the same time it is equally silly to let the process drag on, for reasons explained in WP:SNOW. Gnomingstuff (talk) 03:42, 16 December 2024 (UTC)
Option 3 per Gnoming. I think 2 works, but it is a very long process and for someone to renew their tools, it feels like an unnecessarily long process compared to a normal RfA. Conyo14 (talk) 04:25, 16 December 2024 (UTC)
As someone who supported both WormTT and Hog Farm's RfAs, option 1 > option 3 >> option 2. At each individual RfA the question is whether or not a specific editor should be an admin, and in both cases I felt that the answer was clearly "yes". However, I agree that RfA is a very intensive process. It requires a lot of time from the community, as others have argued better than I can. I prefer option 1 to option 3 because the existence of the procedure in option 3 implies that it is a good thing to go through 48 hours of RfA to re-request the mop. But anything which saves community time is a good thing. HouseBlaster (talk • he/they) 04:31, 16 December 2024 (UTC)
I've seen this assertion made multiple times now that requires a lot of time from the community, yet nowhere has anybody articulated how why this is true. What time is required, given that nobody is required to participate and everybody who does choose to participate can spend as much or as little time assessing the candidate as they wish? How and why does a reconfirmation RFA require any more time from editors (individually or collectively) than a request at BN? Thryduulf (talk) 04:58, 16 December 2024 (UTC)
I think there are a number of factors and people are summing it up as "time-wasting" or similar:
BN Is designed for this exact scenario. It's also clearly a less contentious process.
Snow closures a good example of how we try to avoid wasting community time on unnecessary process and the same reasoning applies here. Misplaced Pages is not a bureaucracy and there's no reason to have a 7-day process when the outcome is a given.
If former administrators continue to choose re-RFAs over BN, it could set a problematic precedent where future re-adminship candidates feel pressured to go through an RFA and all that entails. I don't want to discourage people already vetted by the community from rejoining the ranks.
The RFA process is designed to be a thoughtful review of prospective administrators and I'm concerned these kinds of perfunctory RFAs will lead to people taking the process less seriously in the future.
Because several thousand people have RFA on their watchlist, and thousands more will see the "there's an open RFA" notice on theirs whether they follow it or not. Unlike BN, RFA is a process that depends on community input from a large number of people. In order to even realise that the RFA is not worth their time, they have to:
Read the opening statement and first few question answers (I just counted, HF's opening and first 5 answers are about 1000 words)
Think, "oh, they're an an ex-admin, I wonder why they're going through RFA, what was their cloud"
Read through the comments and votes to see if any issues have been brought up (another ~1000 words)
None have
Realise your input is not necessary and this could have been done at BN
That they were former admins has always been the first two sentences of their RfA’s statement, sentences which are immediately followed by that they resigned due to personal time commitment issues. You do not have to read the first 1000+ words to figure that out. If the reader wants to see if the candidate was lying in their statement, then they just have a quick skim through the oppose section. None of this should take more than 30 seconds in total. Aaron Liu (talk) 13:15, 16 December 2024 (UTC)
Not everyone can skim things easily - it personally takes me a while to read sections. I don't know if they're going to bury the lede and say something like "Also I made 10,000 insane redirects and then decided to take a break just before arbcom launched a case" in paragraph 6. Hog Farm's self nom had two paragraphs about disputes and it takes more than 30 seconds to unpick that and determine if that is a "cloud" or not. Even for reconfirmations, it definitely takes more than 30 seconds to determine a conclusion. BugGhost🦗👻11:21, 17 December 2024 (UTC)
They said they resigned to personal time commitments. That is directly saying they wasn’t under a cloud, so I’ll believe them unless someone claims the contrary in the oppose section. If the disputes section contained a cloud, the oppose section would have said so. One chooses to examine such nominations like normal RfAs. Aaron Liu (talk) 18:47, 17 December 2024 (UTC)
Just to double check, you're saying that whenever you go onto an RFA you expect any reason to oppose to already be listed by someone else, and no thought is required? I am begining to see how you are able to assess an RFA in under 30 seconds BugGhost🦗👻23:08, 17 December 2024 (UTC)
Something in their statement would be an incredibly obvious reason. We are talking about the assessment whether to examine and whether the candidate could've used BN. Aaron Liu (talk) 12:52, 18 December 2024 (UTC)
@Thryduulf let's not confuse "a lot of community time is spent" with "waste of time". Some people have characterized the re-RFAs as a waste of time but that's not the assertion I (and I think a majority of the skeptics) have been making. All RfAs use a lot of community time as hundreds of voters evaluate the candidate. They then choose to support, oppose, be neutral, or not vote at all. While editor time is not perfectly fixed - editors may choose to spend less time on non-Misplaced Pages activities at certain times - neither is it a resource we have in abundance anymore relative to our project. And so I think we, as a community, need to be thought about how we're using that time especially when the use of that time would have been spent on other wiki activities.Best, Barkeep49 (talk) 22:49, 16 December 2024 (UTC)
Absolutely nothing compels anybody to spend any time evaluating an RFA. If you think your wiki time is better spent elsewhere than evaluating an RFA candidate, then spend it elsewhere. That way only those who do think it is a good use of their time will participate and everybody wins. You win by not spending your time on something that you don't think is worth it, those who do participate don't have their time wasted by having to read comments (that contradict explicit policy) about how the RFA is a waste of time. Personally I regard evaluating whether a long-time admin still has the approval of the community to be a very good use of community time, you are free to disagree, but please don't waste my time by forcing me to read comments about how you think I'm wasting my time. Thryduulf (talk) 23:39, 16 December 2024 (UTC)
I don't understand how your argument that it is not a good use of community time is any different from arguing that it is a waste of time? Thryduulf (talk) 09:08, 17 December 2024 (UTC)
Option 2 I don't mind the re-RFAs, but I'd appreciate if we encouraged restoration via BN instead, I just object to making it mandatory. EggRoll9706:23, 16 December 2024 (UTC)
Option 2. Banning voluntary re-RfAs would be a step in the wrong direction on admin accountability. Same with SNOW closing. There is no more "wasting of community time" if we let the RfA run for the full seven days, but allowing someone to dig up a scandal on the seventh day is an important part of the RfA process. The only valid criticism I've heard is that folks who do this are arrogant, but banning arrogance, while noble, seems highly impractical. Toadspike07:24, 16 December 2024 (UTC)
Option 3, 1, then 2, per HouseBlaster. Also agree with Daniel Quinlan. I think these sorts of RFA's should only be done in exceptional circumstances. Graham87 (talk) 08:46, 16 December 2024 (UTC)
Option 1 as first preference, option 3 second. RFAs use up a lot of time - hundreds of editors will read the RFA and it takes time to come to a conclusion. When that conclusion is "well that was pointless, my input wasn't needed", it is not a good system. I think transparency and accountability is a very good thing, and we need more of it for resyssopings, but that should come from improving the normal process (BN) rather than using a different one (RFA). My ideas for improving the BN route to make it more transparent and better at getting community input is outlined over on the idea labBugGhost🦗👻08:59, 16 December 2024 (UTC)
Option 2, though I'd be for option 3 too. I'm all for administrators who feel like they want/should go through an RfA to solicit feedback even if they've been given the tools back already. I see multiple people talk about going through BN, but if I had to hazard a guess, it's way less watched than RfA is. However I do feel like watchlist notifications should say something to the effect of "A request for re-adminship feedback is open for discussion" so that people that don't like these could ignore them. ♠JCW555(talk)♠ 09:13, 16 December 2024 (UTC)
Option 2 because WP:ADMINISTRATORS is well-established policy. Read WP:ADMINISTRATORS#Restoration of admin tools, which says quite clearly, Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process. I went back 500 edits to 2017 and the wording was substantially the same back then. So, I simply do not understand why various editors are berating former administrators to the point of accusing them of wasting time and being arrogant for choosing to go through a process which is specifically permitted by policy. It is bewildering to me. Cullen328 (talk) 09:56, 16 December 2024 (UTC)
Option 2 & 3 I think that there still should be the choice between BN and re-RFA for resysops, but I think that the re-RFA should stay like it is in Option 3, unless it is controversial, at which point it could be extended to the full RFA period. I feel like this would be the best compromise between not "wasting" community time (which I believe is a very overstated, yet understandable, point) and ensuring that the process is based on broad consensus and that our "representatives" are still supported. If I were WTT or Hog, I might choose to make the same decision so as to be respectful of the possibility of changing consensus. JuxtaposedJacob (talk) | :) | he/him | 10:45, 16 December 2024 (UTC)
Option 2, for lack of a better choice. Banning re-RFAs is not a great idea, and we should not SNOW close a discussion that would give someone immunity from a certain degree of accountability. I've dropped an idea for an option 4 in the discussion section below. Giraffer (talk) 12:08, 16 December 2024 (UTC)
Option 1 I agree with Graham87 that these sorts of RFAs should only be done in exceptional circumstances, and BN is the best place to ask for tools back. – DreamRimmer (talk) 12:11, 16 December 2024 (UTC)
Option 2 I don't think prohibition makes sense. It also has weird side effects. eg: some admins' voluntary recall policies may now be completely void, because they would be unable to follow them even if they wanted to, because policy prohibits them from doing a RFA. (maybe if they're also 'under a cloud' it'd fit into exemptions, but if an admins' policy is "3 editors on this named list tell me I'm unfit, I resign" then this isn't really a cloud.) Personally, I think Hog Farm's RFA was unwise, as he's textbook uncontroversial. Worm's was a decent RFA; he's also textbook uncontroversial but it happened at a good time. But any editor participating in these discussions to give the "support" does so using their own time. Everyone who feels their time is wasted can choose to ignore the discussion, and instead it'll pass as 10-0-0 instead of 198-2-4. It just doesn't make sense to prohibit someone from seeking a community discussion, though. For almost anything, really. ProcrastinatingReader (talk) 12:33, 16 December 2024 (UTC)
Option 2 It takes like two seconds to support or ignore an RFA you think is "useless"... can't understand the hullabaloo around them. I stand by what I said on WTT's re-RFA regarding RFAs being about evaluating trustworthiness and accountability. Trustworthy people don't skip the process. —k6ka 🍁 (Talk · Contributions) 15:24, 16 December 2024 (UTC)
2 is fine. Strong oppose to 1 and 3. Opposing option 1 because there is nothing wrong with asking for extra community feedback. opposing option 3 because once an RfA has been started, it should follow the standard rules. Note that RfAs are extremely rare and non-contentious RfAs require very little community time (unlike this RfC which seems a waste of community time, but there we are). —Kusma (talk) 16:59, 16 December 2024 (UTC)
2, with no opposition to 3. I see nothing wrong with a former administrator getting re-confirmed by the community, and community vetting seems like a good thing overall. If people think it's a waste of time, then just ignore the RfA. Natg 19 (talk) 17:56, 16 December 2024 (UTC)
No individual is wasting their time participating. Instead the person asking for a re-rfa is using tons of editor time by asking hundreds of people to vet them. Even the choice not to participate requires at least some time to figure out that this is not a new RfA; though at least in the two we've had recently it would require only as long as it takes to get to the RfA - for many a click from the watchlist and then another click into the rfa page - and to read the first couple of sentences of the self-nomination which isn't terribly long all things considered. Best, Barkeep49 (talk) 22:55, 16 December 2024 (UTC)
I agree with you (I think) that it's a matter of perspective. For me, clicking the RFA link in my watchlist and reading the first paragraph of Hog Farm's nomination (where they explained that they were already a respected admin) took me about 10 seconds. Ten seconds is nothing; in my opinion, this is just a nonissue. But then again, I'm not an admin, checkuser, or an oversighter. Maybe the time to read such a nomination is really wasting their time. I don't know. TheWikiToby (talk) 23:15, 16 December 2024 (UTC)
I'm an admin and an oversighter (but not a checkuser). None of my time was wasted by either WTT or Hog Farm's nominations. Thryduulf (talk) 23:30, 16 December 2024 (UTC)
2. This reminds me of banning plastic straws (bear with me). Sure, I suppose in theory, that this is a burden on the community's time (just as straws do end up in landfills/the ocean). However, the amount of community time that is drained is minuscule compared to the amount of community time drained in countless, countless other fora and processes (just like the volume of plastic waste contributed by plastic straws is less than 0.001% of the total plastic waste). When WP becomes an efficient, well oiled machine, then maybe we can talk about saving community time by banning re-RFA's. But this is much ado about nothing, and indeed this plan to save people from themselves, and not allow them to simply decide whether to participate or not, is arguably more damaging than some re-RFAs (just as banning straws convinced some people that "these save-the-planet people are so ridiculous that I'm not going to bother listening to them about anything."). And, in fact, on a separate note, I'd actually love it if more admins just ran a re-RFA whenever they wanted. They would certainly get better feedback than just posting "What do my talk page watchers think?" on their own talk page. Or waiting until they get yelled at on their talk page, AN/ANI, AARV, etc. We say we want admins to respect feedback; does it have to be in a recall petition? --Floquenbeam (talk) 23:44, 16 December 2024 (UTC)
What meaningful feedback has Hog Farm gotten? "A minority of people think you choose poorly in choosing this process to regain adminship". What are they supposed to do with that? I share your desire for editors to share meaningful feedback with administrators. My own attempt yielded some, though mainly offwiki where I was told I was both too cautious and too impetuous (and despite the seeming contradiction each was valuable in its own way). So yes let's find ways to get meaningful feedback to admins outside of recall or being dragged to ANI. Unfortunately re-RfA seems to be poorly suited to the task and so we can likely find a better way. Best, Barkeep49 (talk) 03:38, 17 December 2024 (UTC)
No hard rule, but we should socially discourage confirmation RfAs There is a difference between a hard rule, and a soft social rule. A hard rule against confirmation RfA's, like option 1, would not do a good job of accounting for edge cases and would thus be ultimately detrimental here. But a soft social rule against them would be beneficial. Unfortunately, that is not one of the options of this RfC. In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. (Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here.) That takes some introspection and humility to ask yourself: is it worth me inviting two or three hundred people to spend part of their lives to comment on me as a person?A lot of people have thrown around editor time in their reasonings. Obviously, broad generalizations about it aren't convincing anyone. So let me just share my own experience. I saw the watchlist notice open that a new RfA was being run. I reacted with some excitement, because I always like seeing new admins. When I got to the page and saw Hogfarm's name, I immediately thought "isn't he already an admin?" I then assumed, ah, its just the classic RfA reaction at seeing a qualified candidate, so I'll probably support him since I already think he's an admin. But then as I started to do my due diligence and read, I saw that he really, truly, already had been an admin. At that point, my previous excitement turned to a certain unease. I had voted yes for Worm's confirmation RfA, but here was another...and I realized that my blind support for Worm might have been the start of an entirely new process. I then thought "bet there's an RfC going about this," and came here. I then spent a while polishing up my essay on editor time, before taking time to write this message. All in all, I probably spent a good hour doing this. Previously, I'd just been clicking the random article button and gnoming. So, the longwinded moral: yeah, this did eat up a lot of my editor time that could have and was being spent doing something else. And I'd do it again! It was important to do my research and to comment here. But in the future...maybe I won't react quite as excitedly to seeing that RfA notice. Maybe I'll feel a little pang of dread...wondering if its going to be a confirmation RfA. We can't pretend that confirmation RfA's are costless, and that we don't lose anything even if editors just ignore them. When run, it should be because they are necessary. CaptainEek⚓03:29, 17 December 2024 (UTC)
In short, a person should have a good reason to do a confirmation RfA. If you're going to stand up before the community and ask "do you trust me," that should be for a good reason. It shouldn't just be because you want the approval of your peers. Asking the community whether you still have their trust to be an administrator, which is what an reconfirmation RFA is, is a good reason. I expect getting a near-unanimous "yes" is good for one's ego, but that's just a (nice) side-effect of the far more important benefits to the entire community: a trusted administrator.
The time you claim is being eaten up unnecessarily by reconfirmation RFAs was actually taken up by you choosing to spend your time writing an essay about using time for things you don't approve of and then hunting out an RFC in which you wrote another short essay about using time on things you don't approve of. Absolutely none of that is a necessary consequence of reconfirmation RFAs - indeed the response consistent with your stated goals would have been to read the first two sentences of Hog Farm's RFA and then closed the tab and returned to whatever else it was you were doing. Thryduulf (talk) 09:16, 17 December 2024 (UTC)
WTT's and Hog Farm's RFAs would have been completely uncontentious, something I hope for at RfA and certainly the opposite of what I "dread" at RfA, if it were not for the people who attack the very concept of standing for RfA again despite policy being crystal clear that it is absolutely fine. I don't see how any blame for this situation can be put on WTT or HF. We can't pretend that dismissing uncontentious reconfirmation RfAs is costless; discouraging them removes one of the few remaining potentially wholesome bits about the process. —Kusma (talk) 09:53, 17 December 2024 (UTC)
@CaptainEek Would you find it better if Watchlist notices and similar said "(re?)confirmation RFA" instead of "RFA"? Say for all voluntary RFAs from an existing admin or someone who could have used BN?
As a different point, I would be quite against any social discouraging if we're not making a hard rule as such. Social discouraging is what got us the opposes at WTT/Hog Farm's RFAs, which I found quite distasteful and badgering. If people disagree with a process, they should change it. But if the process remains the same, I think it's important to not enable RFA's toxicity by encouraging others to namecall or re-argue the process in each RRFA. It's a short road from social discouragement to toxicity, unfortunately. Soni (talk) 18:41, 19 December 2024 (UTC)
Option 2 if people think there's a waste of community time, don't spend your time voting or discussing. Or add "reconfirmation" or similar to the watchlist notice. ~~ AirshipJungleman29 (talk) 15:08, 17 December 2024 (UTC)
Option 3 (which I think is a subset of option 2, so I'm okay with the status quo, but I want to endorse giving 'crats the option to SNOW). While they do come under scrutiny from time to time for the extensive dicsussions in the "maybe" zone following RfAs, this should be taken as an indiciation that they are unlikely to do something like close it as SNOW in the event there is real and substantial concerns being rasied. This is an okay tool to give the 'crats. As far as I can tell, no one has ever accused the them of moving too quickly in this direction (not criticism; love you all, keep up the good work). Bobby Cohn (talk) 17:26, 17 December 2024 (UTC)
Option 3 or Option 2. Further, if Option 2 passes, I expect it also ends all the bickering about lost community time. A consensus explicitly in favour of "This is allowed" should also be a consensus to discourage relitigation of this RFC. Soni (talk) 17:35, 17 December 2024 (UTC)
Option 2: Admins who do not exude entitlement are to be praised. Those who criticize this humility should have a look in the mirror before accusing those who ask for reanointment from the community of "arrogance". I agree that it wouldn't be a bad idea to mention in parentheses that the RFA is a reconfirmation (watchlist) and wouldn't see any problem with crats snow-closing after, say, 96 hours. -- SashiRolls18:48, 17 December 2024 (UTC)
I know. I see a sizable amount of commenters here starting to say that voluntary re-RfAs should be encouraged, and your first sentence can be easily read as implying that admins who use the BN route exude entitlement. I disagree with that (see my reply to Thryduulf below). Aaron Liu (talk) 12:56, 18 December 2024 (UTC)
One way to improve the reputation of RFA is for there to be more RFAs that are not terrible, such as reconfirmations of admins who are doing/have done a good job who sail through with many positive comments. There is no proposal to make RFA mandatory in circumstances it currently isn't, only to reaffirm that those who voluntarily choose RFA are entitled to do so. Thryduulf (talk) 21:06, 17 December 2024 (UTC)
I know it's not a proposal, but there's enough people talking about this so far that it could become a proposal. There's nearly nothing in between that could've lost the trust of the community. I'm sure there are many who do not want to be pressured into this without good reason. Aaron Liu (talk) 12:57, 18 December 2024 (UTC)
Absolutely nobody is proposing, suggesting or hinting here that reconfirmation RFAs should become mandatory - other than comments from a few people who oppose the idea of people voluntarily choosing to do something policy explicitly allows them to choose to do. The best way to avoid people being pressured into being accused of arrogance for seeking reconfirmation of their status from the community is to sanction those people who accuse people of arrogance in such circumstances as such comments are in flagrant breach of AGF and NPA. Thryduulf (talk) 14:56, 18 December 2024 (UTC)
Yes, I’m saying that they should not become preferred. There should be no social pressure to do RfA instead of BN, only pressure intrinsic to the candidate. Aaron Liu (talk) 15:37, 18 December 2024 (UTC)
Whether they should become preferred in any situation forms no part of this proposal in any way shape or form - this seeks only to reaffirm that they are permitted. A separate suggestion, completely independent of this one, is to encourage (explicitly not mandate) them in some (but explicitly not all) situations. All discussions on this topic would benefit if people stopped misrepresenting the policies and proposals - especially when the falsehoods have been explicitly called out. Thryduulf (talk) 15:49, 18 December 2024 (UTC)
I am talking and worrying over that separate proposal many here are suggesting. I don’t intend to oppose Option 2, and sorry if I came off that way. Aaron Liu (talk) 16:29, 18 December 2024 (UTC)
Option 2. In fact, I'm inclined to encourage an RRfA over BN, because nothing requires editors to participate in an RRfA, but the resulting discussion is better for reaffirming community consensus for the former admin or otherwise providing helpful feedback. --Pinchme123 (talk) 21:45, 17 December 2024 (UTC)
Option 2WP:RFA has said "Former administrators may seek reinstatement of their privileges through RfA..." for over ten years and this is not a problem. I liked the opportunity to be consulted in the current RfA and don't consider this a waste of time. Andrew🐉(talk) 22:14, 17 December 2024 (UTC)
2 - If an administrator gives up sysop access because they plan to be inactive for a while and want to minimize the attack surface of Misplaced Pages, they should be able to ask for permissions back the quickest way possible. If an administrator resigns because they do not intend to do the job anymore, and later changes their mind, they should request a community discussion. The right course of action depends on the situation. Jehochman14:00, 18 December 2024 (UTC)
Option 1. I've watched a lot of RFAs and re-RFAs over the years. There's a darn good reason why the community developed the "go to BN" option: saves time, is straightforward, and if there are issues that point to a re-RFA, they're quickly surfaced. People who refuse to take the community-developed process of going to BN first are basically telling the community that they need the community's full attention on their quest to re-admin. Yes, there are those who may be directed to re-RFA by the bureaucrats, in which case, they have followed the community's carefully crafted process, and their re-RFA should be evaluated from that perspective. Risker (talk) 02:34, 19 December 2024 (UTC)
Option 2 (status quo/no changes) per meh. This is bureaucratic rulemongering at its finest. Every time RFA reform comes up some editors want admins to be required to periodically reconfirm, then when some admins decide to reconfirm voluntarily, suddenly that's seen as a bad thing. The correct thing to do here is nothing. If you don't like voluntary reconfirmation RFAs, you are not required to participate in them. Ivanvector (/Edits) 19:34, 19 December 2024 (UTC)
Option 2 I would probably counsel just going to BN most of the time, however there are exceptions and edge cases. To this point these RfAs have been few in number, so the costs incurred are relatively minor. If the number becomes large then it might be worth revisiting, but I don't see that as likely. Some people will probably impose social costs on those who start them by opposing these RfAs, with the usual result, but that doesn't really change the overall analysis. Perhaps it would be better if our idiosyncratic internal logic didn't produce such outcomes, but that's a separate issue and frankly not really worth fighting over either. There's probably some meta issues here I'm unaware off, it's long since I've had my finger on the community pulse so to speak, but they tend to matter far less than people think they do. 184.152.68.190 (talk) 02:28, 20 December 2024 (UTC)
Option 1, per WP:POINT, WP:NOT#SOCIALNETWORK, WP:NOT#BUREAUCRACY, WP:NOTABOUTYOU, and related principles. We all have far better things to do that read through and argue in/about a totally unnecessary RfA invoked as a "Show me some love!" abuse of process and waste of community time and productivity. I could live with option 3, if option 1 doesn't fly (i.e. shut these silly things down as quickly as possible). But option 2 is just out of the question. — SMcCandlish☏¢ 😼 04:28, 22 December 2024 (UTC)
Except none of the re-RFAs complained about have been RfA invoked as a "Show me some love!" abuse of process, you're arguing against a strawman. Thryduulf (talk) 11:41, 22 December 2024 (UTC)
It's entirely a matter of opinion and perception, or A) this RfC wouldn't exist, and B) various of your fellow admins like TonyBallioni would not have come to the same conclusion I have. Whether the underlying intent (which no one can determine, lacking as we do any magical mind-reading powers) is solely egotistical is ultimately irrelevant. The actual effect (what matters) of doing this whether for attention, or because you've somehow confused yourself into think it needs to be done, is precisely the same: a showy waste of community volunteers' time with no result other than a bunch of attention being drawn to a particular editor and their deeds, without any actual need for the community to engage in a lengthy formal process to re-examine them. — SMcCandlish☏¢ 😼 05:49, 23 December 2024 (UTC)
or because you've somehow confused yourself into think it needs to be done
Option 2. I see no legitimate reason why we should be changing the status quo. Sure, some former admins might find it easier to go through BN, and it might save community time, and most former admins already choose the easier option. However, if a candidate last ran for adminship several years ago, or if issues were raised during their tenure as admin, then it may be helpful for them to ask for community feedback, anyway. There is no "wasted" community time in such a case. I really don't get the claims that this violates WP:POINT, because it really doesn't apply when a former admin last ran for adminship 10 or 20 years ago or wants to know if they still have community trust.On the other hand, if an editor thinks a re-RFA is a waste of community time, they can simply choose not to participate in that RFA. Opposing individual candidates' re-RFAs based solely on opposition to re-RFAs in general is a violation of WP:POINT. – Epicgenius (talk) 14:46, 22 December 2024 (UTC)
But this isn't the status quo? We've never done a re-RfA before now. The question is whether this previously unconsidered process, which appeared as an emergent behavior, is a feature or a bug. CaptainEek⚓23:01, 22 December 2024 (UTC)
There have been lots of re-RFAs, historically. There were more common in the 2000s. Evercat in 2003 is the earliest I can find, back before the re-sysopping system had been worked out fully. Croat Canuck back in 2007 was snow-closed after one day, because the nominator and applicant didn't know that they could have gone to the bureaucrats' noticeboard. For more modern examples, HJ Mitchell (2011) is relatively similar to the recent re-RFAs in the sense that the admin resigned uncontroversially but chose to re-RFA before getting the tools back. Immediately following and inspired by HJ Mitchell's, there was the slightly more controversial SarekOfVulcan. That ended successful re-RFAS until 2019's Floquenbeam, which crat-chatted. Since then, there have been none that I remember. There have been several re-RFAs from admins who were de-sysopped or at serious risk of de-sysopping, and a few interesting edge cases such as the potentially optional yet no-consensus SarekVulcan 3 in 2014 and the Rich Farmbrough case in 2015, but those are very different than what we're talking about today. GreenLipstickLesbian (talk) 00:01, 23 December 2024 (UTC)
Well thank you both, I've learned something new today. It turns out I was working on a false assumption. It has just been so long since a re-RfA that I assumed it was a truly new phenomenon, especially since there were two in short succession. I still can't say I'm thrilled by the process and think it should be used sparingly, but perhaps I was a bit over concerned. CaptainEek⚓16:47, 23 December 2024 (UTC)
Option 2 or 3 per Gnoming and CaptainEek. Such RfAs only require at most 30 seconds for one to decide whether or not to spend their time on examination. Unlike other prohibited timesinks, it's not like something undesirable will happen if one does not sink their time. Voluntary reconfirmation RfAs are socially discouraged, so there is usually a very good reason for someone to go back there, such as accountability for past statements in the case of WTT or large disputes during adminship in the case of Hog Farm. I don't think we should outright deny these, and there is no disruption incurred if we don't. Aaron Liu (talk) 15:44, 23 December 2024 (UTC)
Option 2 (fine with better labeling) These don't seem harmful to me and, if I don't have time, I'll skip one and trust the judgment of my fellow editors. No objection to better labeling them though, as discussed above. RevelationDirect (talk) 22:36, 23 December 2024 (UTC)
Option 1 because it's just a waste of time to go through and !vote on candidates who just want the mop restored when he or she or they could get it restored BN with no problems. But I can also see option 2 being good for a former mod not in good standing. Therapyisgood (talk) 23:05, 23 December 2024 (UTC)
If you think it is a waste of time to !vote on a candidate, just don't vote on that candidate and none of your time has been wasted. Thryduulf (talk) 23:28, 23 December 2024 (UTC)
Option 2 Just because someone may be entitled to get the bit back doesn't mean they necessarily should. Look at my RFA3. I did not resign under a cloud, so I could have gotten the bit back by request. However, the RFA established that I did not have the community support at that point, so it was a good thing that I chose that path. I don't particularly support option 3, but I could deal with it. --SarekOfVulcan (talk)16:05, 27 December 2024 (UTC)
Option 1 Asking hundreds of people to vet a candidate who has already passed a RfA and is eligible to get the tools back at BN is a waste of the community's time. -- Pawnkingthree (talk) 16:21, 27 December 2024 (UTC)
Option 2 I really don't think there's a problem that needs to be fixed here. I am grateful at least a couple administrators have asked for the support of the community recently. SportingFlyerT·C00:12, 29 December 2024 (UTC)
Option 2. Keep the status quo of any editor is free to re-request the tools through the requests for adminship process. Voluntary RfA are rare enough not to be a problem, it's not as though we are overburdened with RfAs. And it’s my time to waste. --Malcolmxl5 (talk) 17:58, 7 January 2025 (UTC)
Option 2 or Option 3. These are unlikely to happen anyway, it's not like they're going to become a trend. I'm already wasting my time here instead of other more important activities anyway, so what's a little more time spent giving an easy support?fanfanboy(blocktalk)16:39, 10 January 2025 (UTC)
Discussion
@Voorts: If option 2 gets consensus how would this RfC change the wording Regardless of the process by which the admin tools are removed, any editor is free to re-request the tools through the requests for adminship process. Or is this an attempt to see if that option no longer has consensus? If so why wasn't alternative wording proposed? As I noted above this feels premature in multiple ways. Best, Barkeep49 (talk) 21:43, 15 December 2024 (UTC)
I've re-opened this per a request on my talk page. If other editors think this is premature, they can !vote accordingly and an uninvolved closer can determine if there's consensus for an early close in deference to the VPI discussion. voorts (talk/contributions) 21:53, 15 December 2024 (UTC)
The discussion at VPI, which I have replied on, seems to me to be different enough from this discussion that both can run concurrently. That is, however, my opinion as a mere editor. — Jkudlick ⚓ (talk)22:01, 15 December 2024 (UTC)
@Voorts, can you please reword the RfC to make it clear that Option 2 is the current consensus version? It does not need to be clarified – it already says precisely what you propose. – bradv22:02, 15 December 2024 (UTC)
Question: May someone clarify why many view such confirmation RfAs as a waste of community time? No editor is obligated to take up their time and participate. If there's nothing to discuss, then there's no friction or dis-cussing, and the RfA smooth-sails; if a problem is identified, then there was a good reason to go to RfA. I'm sure I'm missing something here. Aaron Liu (talk) 22:35, 15 December 2024 (UTC)
The intent of RfA is to provide a comprehensive review of a candidate for adminship, to make sure that they meet the community's standards. Is that happening with vanity re-RfAs? Absolutely not, because these people don't need that level of vetting. I wouldn't consider a week long, publicly advertized back patting to be a productive use of volunteer time. -- Ajraddatz (talk) 23:33, 15 December 2024 (UTC)
Sure, but that logic could be used to justify any time sink. We're all volunteers and nobody is forced to do anything here, but that doesn't mean that we should promote (or stay silent with our criticism of, I suppose) things that we feel don't serve a useful purpose. I don't think this is a huge deal myself, but we've got two in a short period of time and I'd prefer to do a bit of push back now before they get more common. -- Ajraddatz (talk) 01:52, 16 December 2024 (UTC)
Except someone who has no need for advanced tools and is not going to use them in any useful fashion, would then skate through with nary a word said about their unsuitability, regardless of the foregone conclusion. The point of RFA is not to rubber-stamp. Unless their is some actual issue or genuine concern they might not get their tools back, they should just re-request them at BN and stop wasting people's time with pointless non-process wonkery. Only in death does duty end (talk) 09:05, 16 December 2024 (UTC)
I’m confused. Adminship requires continued use of the tools. If you think they’s suitable for BN, I don’t see how doing an RfA suddenly makes them unsuitable. If you have concerns, raise them. Aaron Liu (talk) 13:02, 16 December 2024 (UTC)
I don't think the suggested problem (which I acknowledge not everyone thinks is a problem) is resolved by these options. Admins can still run a re-confirmation RfA after regaining adminsitrative privileges, or even initiate a recall petition. I think as discussed on Barkeep49's talk page, we want to encourage former admins who are unsure if they continue to be trusted by the community at a sufficient level to explore lower cost ways of determining this. isaacl (talk) 00:32, 16 December 2024 (UTC)
In re the idea that RfAs use up a lot of community time: I first started editing Misplaced Pages in 2014. There were 62 RfAs that year, which was a historic low. Even counting all of the AElect candidates as separate RfAs, including those withdrawn before voting began, we're still up to only 53 in 2024 – counting only traditional RfAs it's only 18, which is the second lowest number ever. By my count we've has 8 resysop requests at BN in 2024; even if all of those went to RfA, I don't see how that would overwhelm the community. That would still leave us on 26 traditional RfAs per year, or (assuming all of them run the full week) one every other week. Caeciliusinhorto-public (talk) 10:26, 16 December 2024 (UTC)
What about an option 4 encouraging eligible candidates to go through BN? At the end of the Procedure section, add something like "Eligible users are encouraged to use this method rather than running a new request for adminship." The current wording makes re-RfAing sound like a plausible alternative to a BN request, when in actual fact the former rarely happens and always generates criticism. Giraffer (talk) 12:08, 16 December 2024 (UTC)
Discouraging RFAs is the second last thing we should be doing (after prohibiting them), rather per my comments here and in the VPI discussion we should be encouraging former administrators to demonstrate that they still have the approval of the community. Thryduulf (talk) 12:16, 16 December 2024 (UTC)
I think this is a good idea if people do decide to go with option 2, if only to stave off any further mixed messages that people are doing something wrong or rude or time-wasting or whatever by doing a second RfA, when it's explicitly mentioned as a valid thing for them to do. Gnomingstuff (talk) 15:04, 16 December 2024 (UTC)
If RFA is explicitly a valid thing for people to do (which it is, and is being reaffirmed by the growing consensus for option 2) then we don't need to (and shouldn't) discourage people from using that option. The mixed messages can be staved off by people simply not making comments that explicitly contradict policy. Thryduulf (talk) 15:30, 16 December 2024 (UTC)
This is not new. We've had sporadic "vanity" RfAs since the early days of the process. I don't believe they're particularly harmful, and think that it unlikely that we will begin to see so many of them that they pose a problem. As such I don't think this policy proposal solves any problem we actually have. UninvitedCompany21:56, 16 December 2024 (UTC)
This apparent negative feeling evoked at an RFA for a former sysop everyone agrees is fully qualified and trusted certainly will put a bad taste in the mouths of other former admins who might consider a reconfirmation RFA without first visiting BN. This comes in the wake of Worm That Turned's similar rerun. BusterD (talk) 23:29, 16 December 2024 (UTC)
Nobody should ever be discouraged from seeking community consensus for significant changes. Adminship is a significant change. Thryduulf (talk) 23:32, 16 December 2024 (UTC)
No argument from me. I was a big Hog Farm backer way back when he was merely one of Misplaced Pages's best content contributors. BusterD (talk) 12:10, 17 December 2024 (UTC)
I went looking for @Tamzin's comment because I know they had hung up the tools and came back, and I was interested in their perspective. But they've given me a different epiphany. I suddenly realize why people are doing confirmation RfAs: it's because of RECALL, and the one year immunity a successful RfA gives you. Maybe everyone else already figured that one out and is thinking "well duh Eek," but I guess I hadn't :) I'm not exactly sure what to do with that epiphany, besides note the emergent behavior that policy change can create. We managed to generate an entirely new process without writing a single word about it, and that's honestly impressive :P CaptainEek⚓18:18, 17 December 2024 (UTC)
Worm That Turned followed through on a pledge he made in January 2024, before the 2024 review of the request for adminship process began. I don't think a pattern can be extrapolated from a sample size of one (or even two). That being said, it's probably a good thing if admins occasionally take stock of whether or not they continue to hold the trust of the community. As I previously commented, it would be great if these admins would use a lower cost way of sampling the community's opinion. isaacl (talk) 18:31, 17 December 2024 (UTC)
If people decide to go through a community vote to get a one year immunity from a process that only might lead to a community vote which would then have a lower threshold then the one they decide to go through, and also give a year's immunity, then good for them. CMD (talk) 01:05, 22 December 2024 (UTC)
@CaptainEek I'm mildly bothered by this comment, mildly because I assume it's lighthearted and non-serious. But just in case anyone does feel this way - I was very clear about my reasons for RRFA, I've written a lot about it, anyone is welcome to use my personal recall process without prejudice, and just to be super clear - I waive my "1 year immunity" - if someone wants to start a petition in the next year, do not use my RRfA as a reason not to. I'll update my userpage accordingly. I can't speak for Hog Farm, but his reasoning seems similar to mine, and immunity isn't it. Worm(talk) 10:28, 23 December 2024 (UTC)
@Worm That Turned my quickly written comment was perhaps not as clear as it could have been :) I'm sorry, I didn't mean to suggest that y'all had run for dubious reasons. As I said in my !vote, Let me be clear: I am not suggesting that is why either Worm or Hogfarm re-upped, I'm just trying to create a general purpose rule here. I guess what I really meant was that the reason that we're having this somewhat spirited conversation seems to be the sense that re-RfA could provide a protection from recall. If not for recall and the one year immunity period, I doubt we'd have cared so much as to suddenly run two discussions about this. CaptainEek⚓16:59, 23 December 2024 (UTC)
I don't agree. No one else has raised a concern about someone seeking a one-year respite from a recall petition. Personally, I think essentially self-initiating the recall process doesn't really fit the profile of someone who wants to avoid the recall process. (I could invent some nefarious hypothetical situation, but since opening an arbitration case is still a possibility, I don't think it would work out as planned.) isaacl (talk) 05:19, 24 December 2024 (UTC)
I really don't think this is the reason behind WTT's and HF's reconfirmation RFA's. I don't think their RFA's had much utility and could have been avoided, but I don't doubt for a second that their motivations were anything other than trying to provide transparency and accountability for the community. BugGhost🦗👻12:04, 23 December 2024 (UTC)
I don't really care enough about reconf RFAs to think they should be restricted, but what about a lighter ORCP-like process (maybe even in the same place) where fewer editors can indicate, "yeah OK, there aren't really any concerns here, it would probably save a bit of time if you just asked at BN". Alpha3031 (t • c) 12:40, 19 December 2024 (UTC)
Is the "above 8000 words = split" an absolute rule?
Probably should be divided or trimmed, though the scope of a topic can sometimes justify the added reading material.
> 8,000 words
May need to be divided or trimmed; likelihood goes up with size.
< 6,000 words
Length alone does not justify division or trimming.
< 150 words
If an article or list has remained this size for over two months, consider merging it with a related article. Alternatively, the article could be expanded; see Misplaced Pages:Stub.
I have seen a few instances where, an editor will raise the issue that an article is too large at, say, 7500 words or 8100 words. We have multiple history pages (and medical/psychology pages) with well over 11,000+ words, even some with over 16000. Where does one draw the line? It seems like Misplaced Pages leaves it to the discretion of the editor after about 8000 words. Plasticwonder (talk) 07:21, 18 December 2024 (UTC)
Looking at the table, it's obvious that "above 8000 words=Split" is not "an absolute rule". I promise you that if it were, that table would say something that sounded remarkably like "if the article is above 8,000 words, then it absolutely must be split".
Where one draws the line is: In a place that makes sense for the topic of that specific article, having thoughtfully considered all the facts and circumstances that apply to that unique article. WhatamIdoing (talk) 07:41, 18 December 2024 (UTC)
In addition to the above, what matters for the technical aspects of article size is not the number of words but the number of bytes. Word count can only ever be an approximation of that as the length of the words used matters ("a" is 1 byte, "comprehensive" is 13), the number and size of included media matters very significantly more. Thryduulf (talk) 09:20, 18 December 2024 (UTC)
It isn't an absolute rule, but usually an article having an extremely long high word count is evidence of a bigger problem with WP:SUMMARYSTYLE -- that it's too dense or detailed for a reader to use it as a first-port-of-call summary. As such, usually, it's a wise move to create daughter articles for the detailed material, and strim it down to its essentials in the main article; this improves the readability of the main article and allows interested readers to follow up into the nitty-gritty. As Jo-Jo Eumerus rightly says above, though, there's not really such thing as an absolute rule in this place. UndercoverClassicist09:59, 18 December 2024 (UTC)
What we now know is that many readers are looking for specific information, with few reading from top to bottom, but the search engines send them to the mother article even when a more specific daughter article exists. So the first port of call needs to be the most highly detailed. The advice in WP:SUMMARYSTYLE is therefore considered well intentioned but obsolete; stripping the mother article and pushing information down to the daughter articles defeats our whole purpose in providing information. Hawkeye7(discuss)11:31, 22 December 2024 (UTC)
When you say “we know…”, “is considered” and similar, are you pointing to specific previous discussions, RfCs etc on this matter? “In the wild”, as it were, I still see these size limits regularly invoked, even if the conversation rarely ends at them. UndercoverClassicist09:17, 23 December 2024 (UTC)
Rather than draw a line, I'd rather just remove that chart. Can't imagine why a suite of concrete word counts and procedures would ever be very helpful. — Rhododendrites \\ 16:29, 18 December 2024 (UTC)
It absolutely makes sense to say at what page sizes that editors should start considering other options, as well as where splitting can be absolutely unnecessary. Nothing wrong with the table as long as it's clear those aren't hard or fast rules. Masem (t) 16:41, 18 December 2024 (UTC)
Agreed, I find it helpful because it helps me remember what is generally too long for mobile users (I understand that mobile is generally a blindspot for us as editors because the vast majority of us don't edit on mobile but most of the readers are actually on mobile) Horse Eye's Back (talk) 16:49, 18 December 2024 (UTC)
The optimal article size varies quite a lot, actually. Key things we need to consider include:
The likely readership. Someone who's looking up History of Libya under Muammar Gaddafi probably has time to read something long and thoughtful. Someone who's looking up emergency surgery might need basic facts, in simple words, very fast.
The cognitive load associated with the topic. Star Wars is (very) long but easy to understand; Fourier inversion theorem is much shorter, but I bet it takes you longer to read, unless you have unusual expertise in mathematics.
Misplaced Pages leaves it to the discretion of editors far far before 8,000 words. We have thousands of single sentence articles to attest to this. The average article is less than 700 words. CMD (talk) 17:15, 18 December 2024 (UTC)
I've always felt that the kB of readable prose was a better metric for page size (such as is produced by various page size gadgets). Turns out, bigger words take longer to read than shorter words :P Doing it just by wordcount encourages a certain verbosity. For me, my rule of thumb has always aimed to keep big articles under 100kb readable prose. But there's no hard and fast rule, and there shouldn't be. CaptainEek⚓23:08, 22 December 2024 (UTC)
If I'm being honest, what might be the best metric is starting at the top and lightly hammering the Page Down key for a bit. If I groan before reaching the References section, it's too long. Remsense ‥ 论23:10, 22 December 2024 (UTC)
26,000 words is 1.0 tomats. Another way to look at that table is by saying that if it's more than half the length of a book, it's pushing past being "an article" and edging up towards being "a book".
Or you can look at it in terms of how many minutes reading the whole thing would take. There's quite a bit of variation, but for easy math, 300 words per minute means that a 15,000-word-long article would take 50 minutes to read, which almost certainly exceeds the interest and attention span of most readers. WhatamIdoing (talk) 00:35, 23 December 2024 (UTC)
I think the most fundamental scalar isn't quite reading time or even visual size, but structural complexity—for an online encyclopedia article, being overlong expresses itself in my increasing inability to navigate an article comfortably to read or locate what I want, or to understand the structure of the scope covered by it at a glance. Remsense ‥ 论00:38, 23 December 2024 (UTC)
Come to think of it, one thing that makes an article feel longer than its word count is if its sections, media, and other landmarks have been laid out in a careless or unnatural way. Remsense ‥ 论00:48, 23 December 2024 (UTC)
No. And this was rather a pointless, self-answering question in the first place, not something for a VP thread. The answer to the posed question of 'Is the "above 8000 words=Split" an absolute rule?' is obviously "no", both by observing actual WP community practice, and just by reading the table the OP quoted: > 8,000 words — May need to be divided or trimmed; likelihood goes up with size. Is anyone here actually confused into believing that A) "must" and "may" are synonymous, or B) that a guideline, to which reasonable exceptions sometimes apply, is somehow a legal-level policy that must be obeyed at all costs? In reality, there is never any hurry to split a large article, and doing it properly often involves a tremendous amount of work, involving both repair of citations (sometimes in great detail), and resummarizing the background context in the side article while also resummarizing the side-matter in WP:SUMMARY style within the main article (and doing them distinctly enough that the results are not obnoxiously repetitive if the reader moves between the articles). Doing a good job of this can take several days up to a month or longer of tightly focused work, depending on the detail level of the material, the number citations, etc. It is not trivial, we're all volunteers here, and our readers are not going keel over and die if they reach a detailed article that's a bit longer than they were expecting or would prefer. Ultimately, an article that is ginormous usually should split, but there is no deadline, and it needs to be done properly (plus there are often conceptually different ways to go about it from a content-flow perspective, and that might require some consensus discussion). — SMcCandlish☏¢ 😼 01:22, 23 December 2024 (UTC)
I think I linked it once in Misplaced Pages:Policies and guidelines, years ago, and someone objected. I didn't follow up to see whether the objecting editor is one of the handful who think that should is a more polite and/or IAR-compliant way to say must, but as that's a fairly uncommon POV among editors, it probably wasn't. WhatamIdoing (talk) 05:41, 23 December 2024 (UTC)
The linked document pushes very hard on should, "here may exist valid reasons in particular circumstances to ignore a particular item, but the full implications must be understood and carefully weighed" is not a low bar. It sounds much like must except when IAR. CMD (talk) 09:39, 23 December 2024 (UTC)
1: no 2: I don’t see anything wrong with the chart if you just use it as a rule of thumb; 3: I don’t know why this needed to be discussed here, rather than a Q&A desk. Dronebogus (talk) 20:50, 28 December 2024 (UTC)
Guideline against use of AI images in BLPs and medical articles?
I have recently seen AI-generated images be added to illustrate both BLPs (e.g. Laurence Boccolini, now removed) and medical articles (e.g. Legionella#Mechanism). While we don't have any clear-cut policy or guideline about these yet, they appear to be problematic. Illustrating a living person with an AI-generated image might misinform as to how that person actually looks like, while using AI in medical diagrams can lead to anatomical inaccuracies (such as the lung structure in the second image, where the pleura becomes a bronnchiole twisting over the primary bronchi), or even medical misinformation. While a guideline against AI-generated images in general might be more debatable, do we at least have a consensus for a guideline against these two specific use cases?
I personally am strongly against using AI in biographies and medical articles - as you highlighted above, AI is absolutely not reliable in generating accurate imagery and may contribute to medical or general misinformation. I would 100% support a proposal banning AI imagery from these kinds of articles - and a recommendation to not use such imagery other than in specific scenarios. jolielover♥talk12:28, 30 December 2024 (UTC)
I'd prefer a guideline prohibiting the use of AI images full stop. There are too many potential issues with accuracy, honesty, copyright, etc. Has this already been proposed or discussed somewhere? – Joe (talk) 12:38, 30 December 2024 (UTC)
There is one very specific exception I would put to a very sensible blanket prohibition on using AI images to illustrate people, especially BLPs. That is where the person themselves is known to use that image, which I have encountered in Simon Ekpa. CMD (talk) 15:00, 30 December 2024 (UTC)
While the Ekpa portrait is just an upscale (and I'm not sure what positive value that has for us over its source; upscaling does not add accuracy, nor is it an artistic interpretation meant to reveal something about the source), this would be hard to translate to the general case. Many AI portraits would have copyright concerns, not just from the individual (who may have announced some appropriate release for it), but due to the fact that AI portraits can lean heavily on uncredited individual sources. --Nat Gertler (talk) 16:04, 30 December 2024 (UTC)
For the purposes of discussing whether to allow AI images at all, we should always assume that, for the purposes of (potential) policies and guidelines, there exist AI images we can legally use to illustrate every topic. We cannot use those that are not legal (including, but not limited to, copyright violations) so they are irrelevant. An image generator trained exclusively on public domain and cc0 images (and any other licenses that explicitly allow derivative works without requiring attribution) would not be subject to any copyright restrictions (other than possibly by the prompter and/or generator's license terms, which are both easy to determine). Similarly we should not base policy on the current state of the technology, but assume that the quality of its output will improve to the point it is equal to that of a skilled human artist. Thryduulf (talk) 17:45, 30 December 2024 (UTC)
The issue is, either there are public domain/CC0 images of the person (in which case they can be used directly) or there aren't, in which case the AI is making up how a person looks. Chaotic Enby (talk · contribs) 20:00, 30 December 2024 (UTC)
We tend to use art representations either where no photographs are available (in which case, AI will also not have access to photographs) or where what we are showing is an artist's insight on how this person is perceived, which is not something that AI can give us. In any case, we don't have to build policy now around some theoretical AI in the future; we can deal with the current reality, and policy can be adjusted if things change in the future. And even that theoretical AI does make it more difficult to detect copyvio -- Nat Gertler (talk) 20:54, 30 December 2024 (UTC)
I wouldn't call it an upscale given whatever was done appears to have removed detail, but we use that image as it was specifically it is the edited image which was sent to VRT. CMD (talk) 10:15, 31 December 2024 (UTC)
Is there any clarification on using purely AI-generated images vs. using AI to edit or alter images? AI tools have been implemented in a lot of photo editing software, such as to identify objects and remove them, or generate missing content. The generative expand feature would appear to be unreliable (and it is), but I use it to fill in gaps of cloudless sky produced from stitching together photos for a panorama (I don't use it if there are clouds, or for starry skies, as it produces non-existent stars or unrealistic clouds). Photos of Japan (talk) 18:18, 30 December 2024 (UTC)
Yes, my proposal is only about AI-generated images, not AI-altered ones. That could in fact be a useful distinction to make if we want to workshop a RfC on the matter. Chaotic Enby (talk · contribs) 20:04, 30 December 2024 (UTC)
I'm not sure if we need a clear cut policy or guideline against them... I think we treat them the same way as we would treat an editor's kitchen table sketch of the same figure. Horse Eye's Back (talk) 18:40, 30 December 2024 (UTC)
For those wanting to ban AI images full stop, well, you are too late. Most professional image editing software, including the software in one's smartphone as well as desktop, uses AI somewhere. Noise reduction software uses AI to figure out what might be noise and what might be texture. Sharpening software uses AI to figure out what should be smooth and what might have a sharp detail it can invent. For example, a bird photo not sharp enough to capture feather detail will have feather texture imagined onto it. Same for hair. Or grass. Any image that has been cleaned up to remove litter or dust or spots will have the cleaned area AI generated based on its surroundings. The sky might be extended with AI. These examples are a bit different from a 100% imagined image created from a prompt. But probably not in a way that is useful as a rule.
I think we should treat AI generated images the same as any user-generated image. It might be a great diagram or it might be terrible. Remove it from the article if the latter, not because someone used AI. If the image claims to photographically represent something, we may judge whether the creator has manipulated the image too much to be acceptable. For example, using AI to remove a person in the background of an image taken of the BLP subject might be perfectly fine. People did that with traditional Photoshop/Lightroom techniques for years. Using AI to generate what claims to be a photo of a notable person is on dodgy ground wrt copyright. -- Colin°19:12, 30 December 2024 (UTC)
I'm talking about the case of using AI to generate a depiction of a living person, not using AI to alter details in the background. That is why I only talk about AI-generated images, not AI-altered images. Chaotic Enby (talk · contribs) 20:03, 30 December 2024 (UTC)
Regarding some sort of brightline ban on the use of any such image in anything article medical related: absolutely not. For example, if someone wanted to use AI tools as opposed to other tools to make an image such as this one (as used in the "medical" article Fluconazole) I don't see a problem, so long as it is accurate. Accurate models and illustrations are useful and that someone used AI assistance as opposed to a chisel and a rock is of no concern. — xaosflux19:26, 30 December 2024 (UTC)
I believe that the appropriateness of AI images depends on how its used by the user. In BLP and medical articles, it is inappropriate for the images, but it is inappropriate to ban it completely across thw site. By the same logic, if you want full ban of AI, you are banning fire just because people can get burned, without considering cooking. JekyllTheFabulous (talk) 13:33, 31 December 2024 (UTC)
AI generated medical related image. No idea if this is accurate, but if it is I don't see what the problem would be compared to if this was made with ink and paper. — xaosflux00:13, 31 December 2024 (UTC)
I agree that AI-generated images should not be used in most cases. They essentially serve as misinformation. I also don't think that they're really comparable to drawings or sketches because AI-generation uses a level of photorealism that can easily trick the untrained eye into thinking it is real. Di (they-them) (talk) 20:46, 30 December 2024 (UTC)
AI doesn't need to be photorealistic though. I see two potential issues with AI. The first is images that might deceive the viewer into thinking they are photos, when they are not. The second is potential copyright issues. Outside of the copyright issues I don't see any unique concerns for an AI-generated image (that doesn't appear photorealistic). Any accuracy issues can be handled the same way a user who manually drew an image could be handled. Photos of Japan (talk) 21:46, 30 December 2024 (UTC)
AI-generated depictions of BLP subjects are often more "illustrative" than drawings/sketches of BLP subjects made by 'regular' editors like you and me. For example, compare the AI-generated image of Pope Francis and the user-created cartoon of Brigette Lundy-Paine. Neither image belongs on their respective bios, of course, but the AI-generated image is no more "misinformation" than the drawing. Some1 (talk) 00:05, 31 December 2024 (UTC)
I would argue the opposite: neither are made up, but the first one, because of its realism, might mislead readers into thinking that it is an actual photograph, while the second one is clearly a drawing. Which makes the first one less illustrative, as it carries potential for misinformation, despite being technically more detailed. Chaotic Enby (talk · contribs) 00:31, 31 December 2024 (UTC)
AI-generated images should always say "AI-generated image of " in the image caption. No misleading readers that way. Some1 (talk) 00:36, 31 December 2024 (UTC)
Yes, and they don't always do it, and we don't have a guideline about this either. The issue is, many people have many different proposals on how to deal with AI content, meaning we always end up with "no consensus" and no guidelines on use at all, even if most people are against it. Chaotic Enby (talk · contribs) 00:40, 31 December 2024 (UTC)
always end up with "no consensus" and no guidelines on use at all, even if most people are against it Agreed. Even a simple proposal to have image captions note whether an image is AI-generated will have editors wikilawyer over the definition of 'AI-generated.' I take back my recommendation of starting an RfC; we can already predict how that RfC will end. Some1 (talk) 02:28, 31 December 2024 (UTC)
We should absolutely not be including any AI images in anything that is meant to convey facts (with the obvious exception of an AI image illustrating the concept of an AI image). I also don't think we should be encouraging AI-altered images -- the line between "regular" photo enhancement and what we'd call "AI alteration" is blurry, but we shouldn't want AI edits for the same reason we wouldn't want fake Photoshop composites.
That said, I would assume good faith here: some of these images are probably being sourced from Commons, and Commons is dealing with a lot of undisclosed AI images. Gnomingstuff (talk) 23:31, 30 December 2024 (UTC)
Do you really mean to ban single images showing the way birds use their wings?
Sorry, should have been more clear -- composites that present themselves as the real thing, basically what people would use deepfakes for now. Gnomingstuff (talk) 20:20, 31 December 2024 (UTC)
I don't think any guideline, let alone policy, would be beneficial and indeed on balance is more likely to be harmful. There are always only two questions that matter when determining whether we should use an image, and both are completely independent of whether the image is AI-generated or not:
Can we use this image in this article? This depends on matters like copyright, fair use, whether the image depicts content that is legal for an organisation based in the United States to host, etc. Obviously if the answer is "no", then everything else is irrelevant, but as the law and WMF, Commons and en.wp policies stand today there exist some images in both categories we can use, and some images in both categories we cannot use.
Does using this image in this article improve the article? This is relative to other options, one of which is always not using any image, but in many cases also involves considering alternative images that we can use. In the case of depictions of specific, non-hypothetical people or objects one criteria we use to judge whether the image improves the article is whether it is an accurate representation of the subject. If it is not an accurate representation then it doesn't improve the article and thus should not be used, regardless of why it is inaccurate. If it is an accurate representation, then its use in the article will not be misrepresentative or misleading, regardless of whether it is or is not AI generated. It may or may not be the best option available, but if it is then it should be used regardless of whether it is or is not AI generated.
The potential harm I mentioned above is twofold, firstly Misplaced Pages is, by definition, harmed when an images exists we could use that would improve an article but we do not use it in that article. A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been.
Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. Thryduulf (talk) 00:52, 31 December 2024 (UTC)
I agree with almost the entirety of your post with a caveat on whether something "is an accurate representation". We can tell whether non-photorealistic images are accurate by assessing whether the image accurately conveys the idea of what it is depicting. Photos do more than convey an idea, they convey the actual look of something. With AI generated images that are photorealistic it is difficult to assess whether they accurately convey the look of something (the shading might be illogical in subtle ways, there could be an extra finger that goes unnoticed, a mole gets erased), but readers might be deceived by the photo-like presentation into thinking they are looking at an actual photographic depiction of the subject which could differ significantly from the actual subject in ways that go unnoticed. Photos of Japan (talk) 04:34, 31 December 2024 (UTC)
A policy or guideline against the use of AI images would, in some cases, prevent us from using an image that would improve an article. That's why I'm suggesting a guideline, not a policy. Guidelines are by design more flexible, and WP:IAR still does (and should) apply in edge cases.The second aspect is misidentification of an image as AI-generated when it isn't, especially when it leads to an image not being used when it otherwise would have been. In that case, there is a licensing problem. AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.Finally, all the proponents of a policy or guideline are assuming that the line between images that are and are not AI-generated is sharp and objective. Other commenters here have already shown that in reality the line is blurry and it is only going to get blurrier in the future as more AI (and AI-based) technology is built into software and especially firmware. In that case, it's mostly because the ambiguity in wording: AI-edited images are very common, and are sometimes called "AI-generated", but here we should focus on actual prompt outputs, of the style "I asked a model to generate me an image of a BLP". Chaotic Enby (talk · contribs) 11:13, 31 December 2024 (UTC)
Simply not having a completely unnecessary policy or guideline is infinitely better than relying on IAR - especially as this would have to be ignored every time it is relevant. When the AI image is not the best option (which obviously includes all the times its unsuitable or inaccurate) existing policies, guidelines, practice and frankly common sense mean it won't be used. This means the only time the guideline would be relevant is when an AI image is the best option and as we obviously should be using the best option in all cases we would need to ignore the guideline against using AI images.
AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated. The key words here are "supposed to be" and "shouldn't", editors absolutely will speculate that images are AI-generated and that the Commons labelling is incorrect. We are supposed to assume good faith, but this very discussion shows that when it comes to AI some editors simply do not do that.
Regarding your final point, that might be what you are meaning but it is not what all other commenters mean when they want to exclude all AI images. Thryduulf (talk) 11:43, 31 December 2024 (UTC)
For your first point, the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image), but the model likely doesn't have any available image either and most likely just made it up. As my proposal is essentially limited to that (I don't include AI-edited images, only those that are purely generated by a model), I don't think there will be many cases where IAR would be needed.Regarding your two other points, you are entirely correct, and while I am hoping for nuance on the AI issue, it is clear that some editors might not do that. For the record, I strongly disagree with a blanket ban of "AI images" (which includes both blatant "prompt in model" creations and a wide range of more subtle AI retouching tools) or anything like that. Chaotic Enby (talk · contribs) 11:49, 31 December 2024 (UTC)
the guideline is mostly to take care of the "prompt fed in model" BLP illustrations, where it is technically hard to prove that the person doesn't look like that (as we have no available image). There are only two possible scenarios regarding verifiability:
The image is an accurate representation and we can verify that (e.g. by reference to non-free photos).
Verifiability is no barrier to using the image, whether it is AI generated or not.
If it is the best image available, and editors agree using it is better than not having an image, then it should be used whether it is AI generated or not.
The image is either not an accurate representation, or we cannot verify whether it is or is not an accurate representation
The only reasons we should ever use the image are:
It has been the subject of notable commentary and we are presenting it in that context.
The subject verifiably uses it as a representation of themselves (e.g. as an avatar or logo)
This is already policy, whether the image is AI generated or not is completely irrelevant.
In your first scenario, there is the issue of an accurate AI-generated image misleading people into thinking it is an actual photograph of the person, especially as they are most often photorealistic. Even besides that, a mostly accurate representation can still introduce spurious details, and this can mislead readers as they do not know to what level it is actually accurate. This scenario doesn't really happen with drawings (which are clearly not photographs), and is very much a consequence of AI-generated photorealistic pictures being a thing.In the second scenario, if we cannot verify that it is not an accurate representation, it can be hard to remove the image with policy-based reasons, which is why a guideline will again be helpful. Having a single guideline against fully AI-generated images takes care of all of these scenarios, instead of having to make new specific guidelines for each case that emerges because of them. Chaotic Enby (talk · contribs) 13:52, 31 December 2024 (UTC)
If the image is misleading or unverifiable it should not be used, regardless of why it is misleading or unverifiable. This is existing policy and we don't need anything specifically regarding AI to apply it - we just need consensus that the image is misleading or unverifiable. Whether it is or is not AI generated is completely irrelevant. Thryduulf (talk) 15:04, 31 December 2024 (UTC)
AI-generated images on Commons are supposed to be clearly labeled as such. There is no guesswork here, and we shouldn't go hunting for images that might have been AI-generated.
I mean... yes, we should? At the very least Commons should go hunting for mislabeled images -- that's the whole point of license review. The thing is that things are absolutely swamped over there and there are hundreds of thousands of images waiting for review of some kind. Gnomingstuff (talk) 20:35, 31 December 2024 (UTC)
I just mean that given the reality of the backlogs, there are going to be mislabeled images, and there are almost certainly going to be more of them over time. That's just how it is. We don't have control over that, but we do have control over what images go into articles, and if someone has legitimate concerns about an image being AI-generated, then they should be raising those. Gnomingstuff (talk) 20:45, 31 December 2024 (UTC)
Support blanket ban on AI-generated images on Misplaced Pages. As others have highlighted above, the is not just a slippery slope but an outright downward spiral. We don't use AI-generated text and we shouldn't use AI-generated images: these aren't reliable and they're also WP:OR scraped from who knows what and where. Use only reliable material from reliable sources. As for the argument of 'software now has AI features', we all know that there's a huge difference between someone using a smoothing feature and someone generating an image from a prompt. :bloodofox: (talk) 03:12, 31 December 2024 (UTC)
Reply, the section of WP:OR concerning images is WP:OI which states "Original images created by a Wikimedian are not considered original research, so long as they do not illustrate or introduce unpublished ideas or arguments". Using AI to generate an image only violates WP:OR if you are using it to illustrate unpublished ideas, which can be assessed just by looking at the image itself. COPYVIO, however, cannot be assessed from looking at just the image alone, which AI could be violating. However, some images may be too simple to be copyrightable, for example AI-generated images of chemicals or mathematical structures potentially. Photos of Japan (talk) 04:34, 31 December 2024 (UTC)
Prompt generated images are unquestionably violation of WP:OR and WP:SYNTH: Type in your description and you get an image scraping who knows what and from who knows where, often Misplaced Pages. Misplaced Pages isn't an WP:RS. Get real. :bloodofox: (talk) 23:35, 1 January 2025 (UTC)
"Unquestionably"? Let me question that, @Bloodofox. ;-)
If an editor were to use an AI-based image-generating service and the prompt is something like this:
"I want a stacked bar chart that shows the number of games won and lost by FC Bayern Munich each year. Use the team colors, which are red #DC052D, blue #0066B2, and black #000000. The data is:
2014–15: played 34 games, won 25, tied 4, lost 5
2015–16: played 34 games, won 28, tied 4, lost 2
2016–17: played 34 games, won 25, tied 7, lost 2
2017–18: played 34 games, won 27, tied 3, lost 4
2018–19: played 34 games, won 24, tied 6, lost 4
2019–20: played 34 games, won 26, tied 4, lost 4
2020–21: played 34 games, won 24, tied 6, lost 4
2021–22: played 34 games, won 24, tied 5, lost 5
2022–23: played 34 games, won 21, tied 8, lost 5
2023–24: played 34 games, won 23, tied 3, lost 8"
I would expect it to produce something that is not a violation of either OR in general or OR's SYNTH section specifically. What would you expect, and why do you think it would be okay for me to put that data into a spreadsheet and upload a screenshot of the resulting bar chart, but you don't think it would be okay for me to put that same data into a image generator, get the same thing, and upload that?
Assuming you'd even get what you requested the model without fiddling with the prompt for a while, these sort of 'but we can use it for graphs and charts' devil's advocate scenarios aren't helpful. We're discussing generating images of people, places, and objects here and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH. As for the charts and graphs, there are any number of ways to produce these. :bloodofox: (talk) 03:07, 2 January 2025 (UTC)
We're discussing generating images of people, places, and objects here The proposal contains no such limitation. and in those cases, yes, this would unquestionably be a form of WP:OR & WP:SYNTH. Do you have a citation for that? Other people have explained better than I can how that it is not necessarily true, and certainly not unquestionable. Thryduulf (talk) 03:14, 2 January 2025 (UTC)
As you're well aware, these images are produced by scraping and synthesized material from who knows what and where: it's ultimately pure WP:OR to produce these fake images and they're a straightforward product of synthesis of multiple sources (WP:SYNTH) - worse yet, these sources are unknown because training data is by no means transparent. Personally, I'm strongly for a total ban on generative AI on the site exterior to articles on the topic of generative AI. Not only do I find this incredible unethical, I believe it is intensely detrimental to Misplaced Pages, which is an already a flailing and shrinking project. :bloodofox: (talk) 03:23, 2 January 2025 (UTC)
So you think the lead image at Gisèle Pelicot is a SYNTH violation? Its (human) creator explicitly says "This is not done from one specific photo. As I usually do when I draw portraits of people that I can't see in person, I look at a lot of photos of them and then create my own rendition" in the image description, which sounds like the product of synthesis of multiple sources" to me, and "these sources are unknown because" the the images the artist looked at are not disclosed.
A lot of my concern about blanket statements is the principle that what's sauce for the goose is sauce for the gander, too. If it's okay for a human to do something by hand, then it should be okay for a human using a semi-automated tool to do it, too.
(Just in case you hadn't heard, the rumors that the editor base is shrinking have been false for over a decade now. Compared to when you created your account in mid-2005, we have about twice as many high-volume editors.) WhatamIdoing (talk) 06:47, 2 January 2025 (UTC)
Review WP:SYNTH and your attempts at downplaying a prompt-generated image as "semi-automated" shows the root of the problem: if you can't detect the difference between a human sketching from a reference and a machine scraping who-knows-what on the internet, you shouldn't be involved in this discussion. As for editor retention, this remains a serious problem on the site: while the site continues to grow (and becomes core fodder for AI-scraping) and becomes increasingly visible, editorial retention continues to drop. :bloodofox: (talk) 09:33, 2 January 2025 (UTC)
Please scroll down below SYNTH to the next section titled "What is not original research" which begins with WP:OI, our policies on how images relate to OR. OR (including SYNTH) only applies to images with regards to if they illustrate "unpublished ideas or arguments". It does not matter, for instance, if you synthesize an original depiction of something, so long as the idea of that thing is not original. Photos of Japan (talk) 09:55, 2 January 2025 (UTC)
Yes, which explicitly states:
It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.
Using a machine to generate a fake image of someone is far beyond "manipulation" and it is certainly "false". Clearly we need explicit policies on AI-generated images of people or we wouldn't be having this discussion, but this as it stands clarly also falls under WP:SYNTH: there is zero question that this is a result of "synthesis of published material", even if the AI won't list what it used. Ultimately it's just a synthesis of a bunch of published composite images of who-knows-what (or who-knows-who?) the AI has scraped together to produce a fake image of a person. :bloodofox: (talk) 10:07, 2 January 2025 (UTC)
The latter images you describe should be SVG regardless. If there are models that can generate that, that seems totally fine since it can be semantically altered by hand. Any generation with photographic or "painterly" characteristics (e.g. generating something in the style of a painting or any other convention of visual art that communicates aesthetic particulars and not merely abstract visual particulars) seems totally unacceptable. Remsense ‥ 论07:00, 31 December 2024 (UTC)
100 dots: 99 chocolate-colored dots and 1 baseball-shaped dot
@Bloodofox, here's an image I created. It illustrates the concept of 1% in an article. I made this myself, by typing 100 emojis and taking a screenshot. Do you really mean to say that if I'd done this with an image-generating AI tool, using a prompt like "Give me 100 dots in a 10 by 10 grid. Make 99 a dark color and 1, randomly placed, look like a baseball" that it would be hopelessly tainted, because AI is always bad? Or does your strongly worded statement mean something more moderate?
I'd worry about photos of people (including dead people). I'd worry about photos of specific or unique objects that have to be accurate or they're worse than worthless (e.g., artwork, landmarks, maps). But I'm not worried about simple graphs and charts like this one, and I'm not worried about ordinary, everyday objects. If you want to use AI to generate a photorealistic image of a cookie, or a spoon, and the output you get genuinely looks like those objects, I'm not actually going to worry about it. WhatamIdoing (talk) 06:57, 31 December 2024 (UTC)
As you know, Misplaced Pages has the unique factor of being entirely volunteer-ran. Misplaced Pages has fewer and fewer editors and, long-term, we're seeing plummeting birth rates in areas where most Misplaced Pages editors do exist. I wouldn't expect a wave of new ones aimed at keeping the site free of bullshit in the near future.
In addition, the Wikimedia Foundation's hair-brained continued effort to turn the site into its political cash machine is no doubt also not helping, harming the site's public perception and leading to fewer new editors.
Over the course of decades (I've been here for around 20 years), it seems clear that the site will be negatively impacted by all this, especially in the face of generative AI.
As a long-time editor who has frequently stumbled upon intense WP:PROFRINGE content, fended off armies of outside actors looking to shape the site into their ideological image (and sent me more than a few death threats), and who has identified large amount of politically-motivated nonsense explicitly designed to fool non-experts in areas I know intimately well (such as folklore and historical linguistics topics), I think it need be said that the use of generative AI for content is especially dangerous because of its capabilities of fooling Misplaced Pages readers and Misplaced Pages editors alike.
Misplaced Pages is written by people for people. We need to draw a line in the sand to keep from being flooded by increasingly accessible hoax-machines.
A blanket ban on generative AI resolves this issue or at least hands us another tool with which to attempt to fight back. We don't need what few editors we have here wasting what little time they can give the project checking over an ocean of AI-generated slop: we need more material from reliable sources and better tools to fend off bad actors usable by our shrinking editor base (anyone at the Wikimedia Foundation listening?), not more waves of generative AI garbage. :bloodofox: (talk) 07:40, 31 December 2024 (UTC)
A blanket ban doesn't actually resolve most of the issues though, and introduces new ones. Bad usages of AI can already be dealt with by existing policy, and malicious users will ignore a blanket ban anyways. Meanwhile, a blanket ban would harm many legitimate usages for AI. For instance, the majority of professional translators (at least Japanese to English) incorporate AI (or similar tools) into their workflow to speed up translations. Just imagine a professional translator who uses AI to help generate rough drafts of foreign language Misplaced Pages articles, before reviewing and correcting them, and another editor learning of this and mass reverting them for breaking the blanket ban, and ultimately causing them to leave. Many authors (particularly with carpal tunnel) use AI now to control their voice-to-text (you can train the AI on how you want character names spelled, the formatting of dialogue and other text, etc.). A wikipedia editor could train an AI to convert their voice into Misplaced Pages-formatted text. AI is subtly incorporated now into spell-checkers, grammar-checkers, photo editors, etc., in ways many people are not aware of. A blanket AI ban has the potential to cause many issues for a lot of people, without actually being that affective at dealing with malicious users. Photos of Japan (talk) 08:26, 31 December 2024 (UTC)
I think this is the least convincing one I've seen here yet: It contains the ol' 'there are AI features in programs now' while also attempting to invoke accessibility and a little bit of 'we must have machines to translate!'.
As a translator myself, I can only say: Oh please. Generative AI is notoriously terrible at translating and that's not likely to change. And I mean ever beyond a very, very basic level. Due to the complexities of communication and little matters like nuance, all machine translated material must be thoroughly checked and modified by, yes, human translators, who often encounter it spitting out complete bullshit scraped from who-knows-where (often Misplaced Pages itself).
I get that this topic attracts a lot of 'but what if generative AI is better than humans?' from the utopian tech crowd but the reality is that anyone who needs a machine to invent text and visuals for whatever reason simply shouldn't be using it on Misplaced Pages.
Either you, a human being, can contribute to the project or you can't. Slapping a bunch of machine-generated (generative AI) visuals and text (much of it ultimately coming from Misplaced Pages in the first place!) isn't some kind of human substitute, it's just machine-regurgitated slop and is not helping the project.
Over three thousand full-time professional translators from around the world responded to the surveys, which were broken into a survey for CAT tool users and one for those who do not use any CAT tool at all.
88% of respondents use at least one CAT tool for at least some of their translation tasks.
Of those using CAT tools, 83% use a CAT tool for most or all of their translation work.
Mind you, traditionally CAT tools didn't use AI, but many do now, which only adds to potential sources of confusion in a blanket ban of AI. Photos of Japan (talk) 17:26, 31 December 2024 (UTC)
You're barking up the tree with the pro-generative AI propaganda in response to me. I think we're all quite aware that generative AI tool integration is now common and that there's also a big effort to replace human translators — and anything that can be "written" with machines-generated text. I'm also keenly aware that generative AI is absolutely horrible at translation and all of it must be thoroughly checked by humans, as you would be if you were a translator yourself. :bloodofox: (talk) 22:20, 31 December 2024 (UTC)
"all machine translated material must be thoroughly checked and modified by, yes, human translators"
There are translators (particularly with non-creative works) who are using these tools to shift more towards reviewing. It should be up to them to decide what they think is the most efficient method for them. Photos of Japan (talk) 06:48, 1 January 2025 (UTC)
And any translator who wants to use generative AI to attempt to translate can do so off the site. We're not here to check it for them. I strongly support a total ban on any generative AI used on the site exterior to articles on generative AI. :bloodofox: (talk) 11:09, 1 January 2025 (UTC)
I wonder what you mean by "on the site". The question here is "Is it okay for an editor to go to a completely different website, generate an image all by themselves, upload it to Commons, and put it in a Misplaced Pages article?" The question here is not "Shall we put AI-generating buttons on Misplaced Pages's own website?" WhatamIdoing (talk) 02:27, 2 January 2025 (UTC)
I'm talking about users slapping machine-translated and/or machine-generated nonsense all over the site, only for us to have to go behind and not only check it but correct it. It takes users minutes to do this and it's already happening. It's the same for images. There are very few of us who volunteer here and our numbers are growing fewer. We need to be spending our time improving the site rather than opening the gate as wide as possible for a flood of AI-generated/rendered garbage. The site has enough problems that compound every day rather than having to fend off users armed with hoax machines at every corner. :bloodofox: (talk) 03:20, 2 January 2025 (UTC)
Sure, we're all opposed to "nonsense", but my question is: What about when the machine happens to generate something that is not "nonsense"?
I have some worries about AI content. I worry, for example, that they'll corrupt our sources. I worry that List of scholarly publishing stings will get dramatically longer, and also that even more undetected, unconfessed, unretracted papers will get published and believed to be true and trustworthy. I worry that academia will go back to a model in which personal connections are more important, because you really can't trust what's published. I worry that scientific journals will start refusing to publish research unless it comes from someone employed by a trusted institution, that is willing to put its reputation on the line by saying they have directly verified that the work described in the paper was actually performed to their standards, thus scuttling the citizen science movement and excluding people whose institutions are upset with them for other reasons (Oh, you thought you'd take a job elsewhere? Well, we refuse to certify the work you did for the last three years...).
But I'm not worried about a Misplaced Pages editor saying "Hey AI, give me a diagram of swingset" or "Make a chart for me out of the data I'm going to give you". In fact, if someone wants to pull the numbers out of Template:Misplaced Pages editor graph (100 per month), feed it to an AI, and replace the template's contents with an AI-generated image (until they finally fix the Graphs extension), I'd consider that helpful. WhatamIdoing (talk) 07:09, 2 January 2025 (UTC)
Translators are not using generative AI for translation, the applicability of LLMs to regular translation is still in its infancy and regardless will not be implementing any generative faculties to its output since that is the exact opposite of what translation is supposed to do. JoelleJay (talk) 02:57, 2 January 2025 (UTC)
Translators are not using generative AI for translation this entirely depends on what you mean by "generative". There are at least three contradictory understandings of the term in this one thread alone. Thryduulf (talk) 03:06, 2 January 2025 (UTC)
Please, you can just go through the entire process with a simple prompt command now. The results are typically shit but you can generate a ton of it quickly, which is perfect for flooding a site like this one — especially without a strong policy against it. I've found myself cleaning up tons of AI-generated crap (and, yes, rendered) stuff here and elsewhere, and now I'm even seeing AI-generated responses to my own comments. It's beyond ridiculous. :bloodofox: (talk) 03:20, 2 January 2025 (UTC)
Ban AI-generated from all articles, AI anything from BLP and medical articles is the position that seems it would permit all instances where there are plausible defenses that AI use does not fabricate or destroy facts intended to be communicated in the context of the article. That scrutiny is stricter with BLP and medical articles in general, and the restriction should be stricter to match. Remsense ‥ 论06:53, 31 December 2024 (UTC)
I think my previous comment is operative: almost anything we can see AI used programmatically to generate should be SVG, not raster—even if it means we are embedding raster images in SVG to generate examples like the above. I do not know if there are models that can generate SVG, but if there are I happily state I have no problem with that. I think I'm at risk of seeming downright paranoid—but understanding how errors can propagate and go unnoticed in practice, if we're to trust a black box, we need to at least be able to check what the black box has done on a direct structural level. Remsense ‥ 论07:02, 31 December 2024 (UTC)
Makes perfect sense that there would be. Again, maybe I come off like a paranoid lunatic, but I really need either the ability to check what the thing is doing, or the ability to check and correct exactly what a black box has done. (In my estimation, if you want to know what procedures person has done, theoretically you can ask them to get a fairly satisfactory result, and the pre-AI algorithms used in image manipulation are canonical and more or less transparent. Acknowledging human error etc., with AI there is not even the theoretical promise that one can be given a truthful account of how it decided to do what it did.) Remsense ‥ 论07:18, 31 December 2024 (UTC)
Like everyone said, there should be a de facto ban on using AI images in Misplaced Pages articles. They are effectively fake images pretending to be real, so they are out of step with the values of Misplaced Pages.--♦IanMacM♦08:20, 31 December 2024 (UTC)
Except, not everybody has said that, because the majority of those of us who have refrained from hyperbole have pointed out that not all AI images are "fake images pretending to be real" (and those few that are can already be removed under existing policy). You might like to try actually reading the discussion before commenting further. Thryduulf (talk) 10:24, 31 December 2024 (UTC)
@Remsense, exactly how much "ability to check what the thing is doing" do you need to be able to do, when the image shows 99 dots and 1 baseball, to illustrate the concept of 1%? If the image above said {{pd-algorithm}} instead of {{cc-by-sa-4.0}}, would you remove if from the article, because you just can't be sure that it shows 1%? WhatamIdoing (talk) 02:33, 2 January 2025 (UTC)
The above is a useful example to an extent, but it is a toy example. I really do think i is required in general when we aren't dealing with media we ourselves are generating. Remsense ‥ 论04:43, 2 January 2025 (UTC)
How do we differentiate in policy between a "toy example" (that really would be used in an article) and "real" examples? Is it just that if I upload it, then you know me, and assume I've been responsible? WhatamIdoing (talk) 07:13, 2 January 2025 (UTC)
There definitely exist generative AI for SVG files. Here's an example: I used generative AI in Adobe Illustrator to generate the SVG gear in File:Pinwheel scheduling.svg (from Pinwheel scheduling) before drawing by hand the more informative parts of the image. The gear drawing is not great (a real gear would have uniform tooth shape) but maybe the shading is better than I would have done by hand, giving an appearance of dimensionality and surface material while remaining deliberately stylized. Is that the sort of thing everyone here is trying to forbid?
I can definitely see a case for forbidding AI-generated photorealistic images, especially of BLPs, but that's different from human oversight of AI in the generation of schematic images such as this one. —David Eppstein (talk) 01:15, 1 January 2025 (UTC)
I'd include BDPs, too. I had to get a few AI-generated images of allegedly Haitian presidents deleted a while ago. The "paintings" were 100% fake, right down to the deformed medals on their military uniforms. An AI-generated "generic person" would be okay for some purposes. For a few purposes (e.g., illustrations of Obesity) it could even be preferable to have a fake "person" than a real one. But for individual/named people, it would be best not to have anything unless it definitely looks like the named person. WhatamIdoing (talk) 07:35, 2 January 2025 (UTC)
Of course, that's why I'm only looking at specific cases and refrain from proposing a blanket ban on generative AI. Regarding Donald Trump, we do have one AI-generated image of him that is reasonable to allow (in Springfield pet-eating hoax), as the image itself was the subject of relevant commentary. Of course, this is different from using an AI-generated image to illustrate Donald Trump himself, which is what my proposal would recommend against. Chaotic Enby (talk · contribs) 11:32, 31 December 2024 (UTC)
That's certainly true, but others are adopting much more extreme positions than you are, and it was the more extreme views that I wished to challenge.—S MarshallT/C11:34, 31 December 2024 (UTC)
Going off WAID's example above, perhaps we should be trying to restrict the use of AI where image accuracy/precision is essential, as it would be for BLP and medical info, among other cases, but in cases where we are talking generic or abstract concepts, like the 1% image, it's use is reasonable. I would still say we should strongly prefer am image made by a human with high control of the output, but when accuracy is not as important as just the visualization, it's reasonable to turn to AI to help. Masem (t) 15:12, 31 December 2024 (UTC)
Support total ban of AI imagery - There are probable copyright problems and veracity problems with anything coming out of a machine. In a word of manipulated reality, Misplaced Pages will be increasingly respected for holding a hard line against synthetic imagery. Carrite (talk) 15:39, 31 December 2024 (UTC)
For both issues AI vs not AI is irrelevant. For copyright, if the image is a copyvio we can't use it regardless of whether it is AI or not AI, if it's not a copyvio then that's not a reason to use or not use the image. If the images is not verifiably accurate then we already can (and should) exclude it, regardless of whether it is AI or not AI. For more detail see the extensive discussion above you've either not read or ignored. Thryduulf (talk) 16:34, 31 December 2024 (UTC)
Yes, we absolutely should ban the use of AI-generated images in these subjects (and beyond, but that's outside the scope of this discussion). AI should not be used to make up a simulation of a living person. It does not actually depict the person and may introduce errors or flaws that don't actually exist. The picture does not depict the real person because it is quite simply fake.
Even worse would be using AI to develop medical images in articles in any way. The possibility for error there is unacceptable. Yes, humans make errors too, but there there is a) someone with the responsibility to fix it and b) someone conscious who actually made the picture, rather than a black box that spat it out after looking at similar training data. Cremastra 🎄 u — c 🎄 20:08, 31 December 2024 (UTC)
It's incredibly disheartening to see multiple otherwise intelligent editors who have apparently not read and/or not understood what has been said in the discussion but rather responding with what appears to be knee-jerk reactions to anti-AI scaremongering. The sky will not fall in, Misplaced Pages is not going to be taken over by AI, AI is not out to subvert Misplaced Pages, we already can (and do) remove (and more commonly not add in the first placE) false and misleading information/images. Thryduulf (talk) 20:31, 31 December 2024 (UTC)
So what benefit does allowing AI images bring? We shouldn't be forced to decide these on a case-by-case basis.
I'm sorry to dishearten you, but I still respectfully disagree with you. And I don't think this is "scaremongering" (although I admit that if it was, I would of course claim it wasn't). Cremastra 🎄 u — c 🎄 21:02, 31 December 2024 (UTC) Cremastra 🎄 u — c 🎄 20:56, 31 December 2024 (UTC)
Determining what benefits any image brings to Misplaced Pages can only be done on a case-by-case basis. It is literally impossible to know whether any image improves the encyclopaedia without knowing the context of which portion of what article it would illustrate, and what alternative images are and are not available for that same spot.
The benefit of allowing AI images is that when an AI image is the best option for a given article we use it. We gain absolutely nothing by prohibiting using the best image available, indeed doing so would actively harm the project without bringing any benefits. AI images that are misleading, inaccurate or any of the other negative things any image can be are never the best option and so are never used - we don't need any policies or guidelines to tell us that. Thryduulf (talk) 21:43, 31 December 2024 (UTC)
Support blanket ban on AI-generated text or images in articles, except in contexts where the AI-generated content is itself the subject of discussion (in a specific or general sense). Generative AI is fundamentally at odds with Misplaced Pages's mission of providing reliable information, because of its propensity to distort reality or make up information out of whole cloth. It has no place in our encyclopedia. —pythoncoder (talk | contribs) 21:34, 31 December 2024 (UTC)
Support blanket ban on AI-generated images except in ABOUTSELF contexts. This is especially a problem given the preeminence Google gives to Misplaced Pages images in its image search. JoelleJay (talk) 22:49, 31 December 2024 (UTC)
Ban across the board, except in articles which are actually about AI-generated imagery or the tools used to create them, or the image itself is the subject of substantial commentary within the article for some reason. Even in those cases, clearly indicating that the image is AI-generated should be required. Seraphimblade00:29, 1 January 2025 (UTC)
Oppose blanket bans that would forbid the use of AI assistance in creating diagrams or other deliberately stylized content. Also oppose blanket bans that would forbid AI illustrations in articles about AI illustrations. I am not opposed to banning photorealistic AI-generated images in non-AI-generation contexts or banning AI-generated images from BLPs unless the image itself is specifically relevant to the subject of the BLP. —David Eppstein (talk) 01:27, 1 January 2025 (UTC)
Oppose blanket bans AI is just a new buzzword so, for example, Apple phones now include "Apple Intelligence" as a standard feature. Does this means that photographs taken using Apple phones will be inadmissable? That would be silly because legacy technologies are already rife with issues of accuracy and verification. For example, there's an image on the main page right now (right). This purports to be a particular person ("The Father of Australia") but, if you check the image description, you find that it may have been his brother and even the attribution to the artist is uncertain. AI features may help in exposing such existing weaknesses in our image use and so we should be free to use them in an intelligent way. Andrew🐉(talk) 08:03, 1 January 2025 (UTC)
So, you expect an the AI, notoriously trained on Misplaced Pages (and whatever else is floating around on the internet), to correct Misplaced Pages where humans have failed... using the data it scraped from Misplaced Pages (and who knows where else)? :bloodofox: (talk) 11:12, 1 January 2025 (UTC)
I tried using the Deep Research option of Gemini to assess the attribution of the Macquarie portrait. Its stated methodology seemed quite respectable and sensible.
The Opie Portrait of Lachlan Macquarie: An Examination of its Attribution: Methodology
To thoroughly investigate the attribution of the Opie portrait of Lachlan Macquarie, a comprehensive research process was undertaken. This involved several key steps:
Gathering information on the Opie portrait: This included details about its history, provenance, and any available information on its cost.
Reviewing scholarly articles and publications: This step focused on finding academic discussions specifically addressing the attribution of the portrait to John Opie.
Collecting expert opinions: Statements and opinions from art experts and historians were gathered to understand the range of perspectives on the certainty of the attribution.
Examining historical documents and records: This involved searching for any records that could shed light on the portrait's origins and authenticity, such as Macquarie's personal journals or contemporary accounts.
Exploring scientific and technical analyses: Information was sought on any scientific or technical analyses conducted on the portrait, such as pigment analysis or canvas dating, to determine its authenticity.
Comparing the portrait to other Opie works: This step involved analyzing the style and technique of the Opie portrait in comparison to other known portraits by Opie to identify similarities and differences.
It was quite transparent in listing and citing the sources that it used for its analysis. These included the Misplaced Pages image but if one didn't want that included, it would be easy to exclude it.
So, AIs don't have to be inscrutable black boxes. They can have programmatic parameters like the existing bots and scripts that we use routinely on Misplaced Pages. Such power tools seem needed to deal with the large image backlogs that we have on Commons. Perhaps they could help by providing captions and categories where these don't exist.
They don't have to be black boxes but they are by design: they exist in a legally dubious area and thus hide what they're scraping to avoid further legal problems. That's no secret. We know for example that Misplaced Pages is a core data set for likely most AIs today. They also notoriously and quite confidently spit out a lie ("hallucinate") and frequently spit out total nonsense. Add to that that they're restricted to whatever is floating around on the internet or whatever other data set they've been fed (usually just more internet), and many specialist topics, like texts on ancient history and even standard reference works, are not accessible on the internet (despite Google's efforts). :bloodofox: (talk) 09:39, 2 January 2025 (UTC)
While its stated methodology seems sensible, there's no evidence that it actually followed that methodology. The bullet points are pretty vague, and are pretty much the default methodologies used to examine actual historical works. Chaotic Enby (talk · contribs) 17:40, 2 January 2025 (UTC)
Yes, there's evidence. As I stated above, the analysis is transparent and cites the sources that it used. And these all seem to check out rather than being invented. So, this level of AI goes beyond the first generation of LLM and addresses some of their weaknesses. I suppose that image generation is likewise being developed and improved and so we shouldn't rush to judgement while the technology is undergoing rapid development. Andrew🐉(talk) 17:28, 4 January 2025 (UTC)
Oppose blanket ban: best of luck to editors here who hope to be able to ban an entirely undefined and largely undetectable procedure. The term 'AI' as commonly used is no more than a buzzword - what exactly would be banned? And how does it improve the encyclopedia to encourage editors to object to images not simply because they are inaccurate, or inappropriate for the article, but because they subjectively look too good? Will the image creator be quizzed on Commons about the tools they used? Will creators who are transparent about what they have created have their images deleted while those who keep silent don’t? Honestly, this whole discussion is going to seem hopelessly outdated within a year at most. It’s like when early calculators were banned in exams because they were ‘cheating’, forcing students to use slide rules. MichaelMaggs (talk) 12:52, 1 January 2025 (UTC)
I am genuinely confused as to why this has turned into a discussion about a blanket ban, even though the original proposal exclusively focused on AI-generated images (the kind that is generated by an AI model from a prompt, which are already tagged on Commons, not regular images with AI enhancement or tools being used) and only in specific contexts. Not sure where the "subjectively look too good" thing even comes from, honestly. Chaotic Enby (talk · contribs) 12:58, 1 January 2025 (UTC)
That just show how ill-defined the whole area is. It seem you restrict the term 'AI-generated' to mean "images generated solely(?) from a text prompt". The question posed above has no such restriction. What a buzzword means is largely in the mind of the reader, of course, but to me and I think to many, 'AI-generated' means generated by AI. MichaelMaggs (talk) 13:15, 1 January 2025 (UTC)
I used the text prompt example because that is the most common way to have an AI model generate an image, but I recognize that I should've clarified it better. There is definitely a distinction between an image being generated by AI (like the Laurence Boccolini example below) and an image being altered or retouched by AI (which includes many features integrated in smartphones today). I don't think it's a "buzzword" to say that there is a meaningful difference between an image being made up by an AI model and a preexisting image being altered in some way, and I am surprised that many people understand "AI-generated" as including the latter. Chaotic Enby (talk · contribs) 15:24, 1 January 2025 (UTC)
Oppose as unenforceable. I just want you to imagine enforcing this policy against people who have not violated it. All this will do is allow Wikipedians who primarily contribute via text to accuse artists of using AI because they don't like the results to get their contributions taken down. I understand the impulse to oppose AI on principle, but the labor and aesthetic issues don't actually have anything to do with Misplaced Pages. If there is not actually a problem with the content conveyed by the image—for example, if the illustrator intentionally corrected any hallucinations—then someone objecting over AI is not discussing page content. If the image was not even made with AI, they are hallucinating based on prejudices that are irrelevant to the image. The bottom line is that images should be judged on their content, not how they were made. Besides all the policy-driven stuff, if Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? Categorical bans of this kind are ill-advised and anti-illustrator. lethargilistic (talk) 15:41, 1 January 2025 (UTC)
And the same applies to photography, of course. If in my photo of a garden I notice there is a distracting piece of paper on the lawn, nobody would worry if I used the old-style clone-stamp tool to remove it in Photoshop, adding new grass in its place (I'm assuming here that I don't change details of the actual landscape in any way). Now, though, Photoshop uses AI to achieve essentially the same result while making it simpler for the user. A large proportion of all processed photos will have at least some similar but essentially undetectable "generated AI" content, even if only a small area of grass. There is simply no way to enforce the proposed policy, short of banning all high-quality photography – which requires post-processing by design, and in which similar encyclopedically non-problematic edits are commonplace. MichaelMaggs (talk) 17:39, 1 January 2025 (UTC)
Before anyone objects that my example is not "an image generated from a text prompt", note that there's no mention of such a restriction in the proposal we are discussing. Even if there were, it makes no difference. Photoshop can already generate photo-realistic areas from a text prompt. If such use is non-misleading and essentially undetectable, it's fine; if if changes the image in such a way as to make it misleading, inaccurate or non-encycpopedic in any way it can be challenged on that basis. MichaelMaggs (talk) 17:58, 1 January 2025 (UTC)
As I said previously, the text prompt is just an example, not a restriction of the proposal. The point is that you talk about editing an existing image (which is what you talk about, as you say if if changes the image), while I am talking about creating an image ex nihilo, which is what "generating" means. Chaotic Enby (talk · contribs) 18:05, 1 January 2025 (UTC)
I'm talking about a photograph with AI-generated areas within it. This is commonplace, and is targeted by the proposal. Categorical bans of the type suggested are indeed ill-advised. MichaelMaggs (talk) 18:16, 1 January 2025 (UTC)
Even if the ban is unenforceable, there are many editors who will choose to use AI images if they are allowed and just as cheerfully skip them if they are not allowed. That would mean the only people posting AI images are those who choose to break the rule and/or don't know about it. That would probably add up to many AI images not used. Darkfrog24 (talk) 22:51, 3 January 2025 (UTC)
Support blanket ban because "AI" is a fundamentally unethical technology based on the exploitation of labor, the wanton destruction of the planetary environment, and the subversion of every value that an encyclopedia should stand for. ABOUTSELF-type exceptions for "AI" output that has already been generated might be permissible, in order to document the cursed time in which we live, but those exceptions are going to be rare. How many examples of Shrimp Jesus slop do we need? XOR'easter (talk) 23:30, 1 January 2025 (UTC)
Support blanket ban - Primarily because of the "poisoning the well"/"dead internet" issues created by it. FOARP (talk) 14:30, 2 January 2025 (UTC)
Support that WP:POLICY applies to images: images should be verifiable, neutral, and absent of original research. AI is just the latest quickest way to produce images that are original, unverifiable, and potentially biased. Is anyone in their right mind saying that we allow people to game our rules on WP:OR and WP:V by using images instead of text? Shooterwalker (talk) 17:04, 3 January 2025 (UTC)
As an aside on this: in some cases Commons is being treated as a way of side-stepping WP:NOR and other restrictions. Stuff that would get deleted if it were written content on WP gets in to WP as images posted on Commons. The worst examples are those conflict maps that are created from a bunch of Twitter posts (eg the Syrian civil war one). AI-generated imagery is another field where that appears to be happening. FOARP (talk) 10:43, 4 January 2025 (UTC)
Support temporary blanket ban with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. I support an exception for the when the article is about the image itself and that image is notable, such as the photograph of the black-and-blue/gold-and-white dress in The Dress and/or examples of AI images in articles in which they are relevant. E.g. "here is what a hallucination is: count the fingers." Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
First, I think any guidance should avoid referring to specific technology, as that changes rapidly and is used for many different purposes. Second, assuming that the image in question has a suitable copyright status for use on Misplaced Pages, the key question is whether or not the reliability of the image has been established. If the intent of the image is to display 100 dots with 99 having the same appearance and 1 with a different appearance, then ordinary math skills are sufficient and so any Misplaced Pages editor can evaluate the reliability without performing original research. If the intent is to depict a likeness of a specific person, then there needs to be reliable sources indicating that the image is sufficiently accurate. This is the same for actual photographs, re-touched ones, drawings, hedcuts, and so forth. Typically this can be established by a reliable source using that image with a corresponding description or context. isaacl (talk) 17:59, 4 January 2025 (UTC)
Support Blanket Ban on AI generated imagery per most of the discussion above. It's a very slippery slope. I might consider a very narrow exception for an AI generated image of a person that was specifically authorized or commissioned by the subject. -Ad Orientem (talk) 02:45, 5 January 2025 (UTC)
Oppose blanket ban It is far too early to take an absolutist position, particularly when the potential is enormous. Misplaced Pages is already is image desert and to reject something that is only at the cusp of development is unwise. scope_creep20:11, 5 January 2025 (UTC)
Support blanket ban on AI-generated images except in ABOUTSELF contexts. An encyclopedia should not be using fake images. I do not believe that further nuance is necessary. LEPRICAVARK (talk) 22:44, 5 January 2025 (UTC)
Support blanket ban as the general guideline, as accuracy, personal rights, and intellectual rights issues are very weighty, here (as is disclosure to the reader). (I could see perhaps supporting adoption of a sub-guideline for ways to come to a broad consensus in individual use cases (carve-outs, except for BLPs) which address all the weighty issues on an individual use basis -- but that needs to be drafted and agreed to, and there is no good reason to wait to adopt the general ban in the meantime). Alanscottwalker (talk) 15:32, 8 January 2025 (UTC)
Which parts of this photo are real?
Support indefinite blanket ban except ABOUTSELF and simple abstract examples (such as the image of 99 dots above). In addition to all the issues raised above, including copyvio and creator consent issues, in cases of photorealistic images it may never be obvious to all readers exactly which elements of the image are guesswork. The cormorant picture at the head of the section reminded me of the first video of a horse in gallop, in 1878. Had AI been trained on paintings of horses instead of actual videos and used to "improve" said videos, we would've ended up with serious delusions about the horse's gait. We don't know what questions -- scientific or otherwise -- photography will be used to settle in the coming years, but we do know that consumer-grade photo AI has already been trained to intentionally fake detail to draw sales, such as on photos of the Moon. I think it's unrealistic to require contributors to take photos with expensive cameras or specially-made apps, but Misplaced Pages should act to limit its exposure to this kind of technology as far as is feasible. DaßWölf20:57, 9 January 2025 (UTC)
BLPs
CONSENSUS AGAINST
There is clear consensus against using AI-generated imagery to depict BLP subjects. Marginal cases (such as major AI enhancement or where an AI-generated image of a living person is itself notable) can be worked out on a case-by-case basis. I will add a sentence reflecting this consensus to the image use policy and the BLP policy. —Ganesha811 (talk) 14:02, 8 January 2025 (UTC)
The following discussion is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Are AI-generated images (generated via text prompts, see also: text-to-image model) okay to use to depict BLP subjects? The Laurence Boccolini example was mentioned in the opening paragraph. The image was created using Grok / Aurora, a text-to-image model developed by xAI, to generate images...As with other text-to-image models, Aurora generates images from natural language descriptions, called prompts.AI-generated image of Laurence BoccoliniSome1 (talk) 12:34, 31 December 2024 (UTC)AI-generated cartoon portrait of Germán Larrea Mota-Velasco
03:58, January 3, 2025: Note: that these images can either be photorealistic in style (such as the Laurence Boccolini example) or non-photorealistic in style (see the Germán Larrea Mota-Velasco example, which was generated using DALL-E, another text-to-image model).
No. I don't think they are at all, as, despite looking photorealistic, they are essentially just speculation about what the person might look like. A photorealistic image conveys the look of something up to the details, and giving a false impression of what the person looks like (or, at best, just guesswork) is actively counterproductive. (Edit 21:59, 31 December 2024 (UTC): clarified bolded !vote since everyone else did it) Chaotic Enby (talk · contribs) 12:46, 31 December 2024 (UTC)
There are plenty of non-free images of Laurence Boccolini with which this image can be compared. Assuming at least most of those are accurate representations of them (I've never heard of them before and have no other frame of reference) the image above is similar to but not an accurate representation of them (most obviously but probably least significantly, in none of the available images are they wearing that design of glasses). This means the image should not be used to identify them unless they use it to identify themselves. It should not be used elsewhere in the article unless it has been the subject of notable commentary. That it is an AI image makes absolutely no difference to any of this. Thryduulf (talk) 16:45, 31 December 2024 (UTC)
No. Well, that was easy.They are fake images; they do not actually depict the person. They depict an AI-generated simulation of a person that may be inaccurate. Cremastra 🎄 u — c 🎄 20:00, 31 December 2024 (UTC)
No, with the caveat that its mostly on the grounds that we don't have enough information and when it comes to BLP we are required to exercise caution. If at some point in the future AI generated photorealistic simulacrums living people become mainstream with major newspapers and academic publishers it would be fair to revisit any restrictions, but in this I strongly believe that we should follow not lead. Horse Eye's Back (talk) 20:37, 31 December 2024 (UTC)
No. The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person. —pythoncoder (talk | contribs) 21:30, 31 December 2024 (UTC)
Yes, when that image is an accurate representation and better than any available alternative, used by the subject to represent themselves, or the subject of notable commentary. However, as these are the exact requirements to use any image to represent a BLP subject this is already policy. Thryduulf (talk) 21:46, 31 December 2024 (UTC)
How well can we determine how accurate a representation it is? Looking at the example above, I'd argue that the real Laurence Boccolini has a somewhat rounder/pointier chin, a wider mouth, and possibly different eye wrinkles, although the latter probably depends quite a lot on the facial expression.
How well can we determine how accurate a representation it is? in exactly the same way that we can determine whether a human-crafted image is an accurate representation. How accurate a representation any image is is ultimately a matter of editor opinion. Whether an image is AI or not is irrelevant. I agree the example image above is not sufficiently accurate, but we wouldn't ban photoshopped images because one example was not deemed accurate enough, because we are rational people who understand that one example is not representative of an entire class of images - at least when the subject is something other than AI. Thryduulf (talk) 23:54, 31 December 2024 (UTC)
I think except in a few exceptional circumstances of actual complex restorations, human photoshopping is not going to change or distort a person's appearance in the same way an AI image would. Modifications done by a person who is paying attention to what they are doing and merely enhancing an image, by person who is aware, while they are making changes, that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator. Cremastra 🎄 u — c 🎄 00:14, 1 January 2025 (UTC)
A photo of a person can be connected to a specific time, place, and subject that existed. It can be compared to other images sharing one or more of those properties. A photo that was PhotoShopped is still either a generally faithful reproduction of a scene that existed, or has significant alterations that can still be attributed to a human or at least to a specific algorithm, e.g. filters. The artistic license of a painting can still be attributed to a human and doesn't run much risk of being misidentified as real, unless it's by Chuck Close et al. An AI-generated image cannot be connected to a particular scene that ever existed and cannot be attributable to a human's artistic license (and there is legal precedent that such images are not copyrightable to the prompter specifically because of this). Individual errors in a human-generated artwork are far more predictable, understandable, identifiable, traceable... than those in AI-generated images. We have innate assumptions when we encounter real images or artwork that are just not transferable. These are meaningful differences to the vast majority of people: according to a Getty poll, 87% of respondents want AI-generated art to at least be transparent, and 98% consider authentic images "pivotal in establishing trust". And even if you disagree with all that, can you not see the larger problem of AI images on Misplaced Pages getting propagated into generative AI corpora? JoelleJay (talk) 04:20, 2 January 2025 (UTC)
I agree that our old assumptions don't hold true. I think the world will need new assumptions. We will probably have those in place in another decade or so.
Absolutely no fake/AI images of people, photorealistic or otherwise. How is this even a question? These images are fake. Readers need to be able to trust Misplaced Pages, not navigate around whatever junk someone has created with a prompt and presented as somehow representative. This includes text. :bloodofox: (talk) 22:24, 31 December 2024 (UTC)
For the requested clarification by Some1, no AI-generated images (except when the image itself is specifically discussed in the article, and even then it should not be the lead image and it should be clearly indicated that the image is AI-generated), no drawings, no nothing of that sort. Actual photographs of the subject, nothing else. Articles are not required to have images at all; no image whatsoever is preferable to something which is not an image of the person. Seraphimblade05:42, 3 January 2025 (UTC)
No, but with exceptions. I could imagine a case where a specific AI-generated image has some direct relevance to the notability of the subject of a BLP. In such cases, it should be included, if it could be properly licensed. But I do oppose AI-generated images as portraits of BLP subjects. —David Eppstein (talk) 01:27, 1 January 2025 (UTC)
Since I was pinged on this point: when I wrote "I do oppose AI-generated images as portraits", I meant exactly that, including all AI-generated images, such as those in a sketchy or artistic style, not just the photorealistic ones. I am not opposed to certain uses of AI-generated images in BLPs when they are not the main portrait of the subject, for instance in diagrams (not depicting the subject) to illustrate some concept pioneered by the subject, or in case someone becomes famous for being the subject of an AI-generated image. —David Eppstein (talk) 05:41, 3 January 2025 (UTC)
No, and no exceptions or do-overs. Better to have no images (or Stone-Age style cave paintings) than Frankenstein images, no matter how accurate or artistic. Akin to shopped manipulated photographs, they should have no room (or room service) at the WikiInn. Randy Kryn (talk) 01:34, 1 January 2025 (UTC)
Some "shopped manipulated photographs" are misleading and inaccurate, others are not. We can and do exclude the former from the parts of the encyclopaedia where they don't add value without specific policies and without excluding them where they are relevant (e.g. Photograph manipulation) or excluding those that are not misleading or inaccurate. AI images are no different. Thryduulf (talk) 02:57, 1 January 2025 (UTC)
Assuming we know. Assuming it's material. The infobox image in – and the only extant photo of – Blind Lemon Jefferson was "photoshopped" by a marketing team, maybe half a century before Adobe Photoshop was created. They wanted to show him wearing a necktie. I don't think that this level of manipulation is actually a problem. WhatamIdoing (talk) 07:44, 2 January 2025 (UTC)
No Not at all relevant for pictures of people, as the accuracy is not enough and can misrepresent. Also (and I'm shocked as it seems no one has mentioned this), what about Copyright issues? Who holds the copyright for an AI-generated image? The user who wrote the prompt? The creator(s) of the AI model? The creator(s) of the images in the database that the AI used to create the images? It's sounds to me such a clusterfuck of copyright issues that I don't understand how this is even a discussion. --SuperJew (talk) 07:10, 1 January 2025 (UTC)
Under the US law / copyright office, machine-generated images including those by AI cannot be copyrighted. That also means that AI images aren't treated as derivative works. What is still under legal concern is whether the use of bodies of copyrighted works without any approve or license from the copyright holders to train AI models is under fair use or not. There are multiple court cases where this is the primary challenge, and none have yet to reach a decision yet. Assuming the courts rule that there was no fair use, that would either require the entity that owns the AI to pay fines and ongoing licensing costs, or delete their trained model to start afresh with free licensed/works, but in either case, that would not impact how we'd use any resulting AI image from a copyright standpoint. — Masem (t) 14:29, 1 January 2025 (UTC)
No, I'm in agreeance with Seraphimblade here. Whether we like it or not, the usage of a portrait on an article implies that it's just that, a portrait. It's incredibly disingenuous to users to represent an AI generated photo as truth. Doawk7 (talk) 09:32, 1 January 2025 (UTC)
So you just said a portrait can be used because wikipedia tells you it's a portrait, and thus not a real photo. Can't AI be exactly the same? As long as we tell readers it is an AI representation? Heck, most AI looks closer to the real thing than any portrait. Fyunck(click) (talk) 10:07, 2 January 2025 (UTC)
To clarify, I didn't mean "portrait" as in "painting," I meant it as "photo of person."
However, I really want to stick to what you say at the end there: Heck, most AI looks closer to the real thing than any portrait.
That's exactly the problem: by looking close to the "real thing" it misleads users into believing a non-existent source of truth.
Per the wording of the RfC of "depict BLP subjects," I don't think there would be any valid case to utilize AI images. I hold a strong No. Doawk7 (talk) 04:15, 3 January 2025 (UTC)
No. We should not use AI-generated images for situations like this, they are basically just guesswork by a machine as Quark said and they can misinform readers as to what a person looks like. Plus, there's a big grey area regarding copyright. For an AI generator to know what somebody looks like, it has to have photos of that person in its dataset, so it's very possible that they can be considered derivative works or copyright violations. Using an AI image (derivative work) to get around the fact that we have no free images is just fair use with extra steps. Di (they-them) (talk) 19:33, 1 January 2025 (UTC)Gisèle Pelicot?
Maybe There was a prominent BLP image which we displayed on the main page recently. (right) This made me uneasy because it was an artistic impression created from photographs rather than life. And it was "colored digitally". Functionally, this seems to be exactly the same sort of thing as the Laurence Boccolini composite. The issue should not be whether there's a particular technology label involved but whether such creative composites and artists' impressions are acceptable as better than nothing. Andrew🐉(talk) 08:30, 1 January 2025 (UTC)
Except it is clear to everyone that the illustration to the right is a sketch, a human rendition, while in the photorealistic image above, it is less clear. Cremastra (u — c) 14:18, 1 January 2025 (UTC)
Except it says right below it "AI-generated image of Laurence Boccolini." How much more clear can it be when it say point-blank "AI-generated image." Fyunck(click) (talk) 10:12, 2 January 2025 (UTC)
People taking a quick glance at an infobox image that looks pretty like a photograph are not going to scrutinize commons tagging. Cremastra (u — c) 14:15, 2 January 2025 (UTC)
Keep in mind that many AIs can produce works that match various styles, not just photographic quality. It is still possible for AI to produce something that looks like a watercolor or sketched drawing. — Masem (t) 14:33, 1 January 2025 (UTC)
Same thing I wrote above, but for "photoshopping" read "drawing": (Bold added for emphasis)
...human is not going to change or distort a person's appearance in the same way an AI image would. done by a person who is paying attention to what they are doing by person who is aware, while they are making , that they might be distorting the image and is, I only assume, trying to minimise it – those careful modifications shouldn't be equated with something made up by an AI image generator.Cremastra (u — c) 20:56, 1 January 2025 (UTC)
@Cremastra then why are you advocating for a ban on AI images rather than a ban on distorted images? Remember that with careful modifications by someone who is aware of what they are doing that AI images can be made more accurate. Why are you assuming that a human artist is trying to minimise the distortions but someone working with AI is not? Thryduulf (talk) 22:12, 1 January 2025 (UTC)
I believe that AI-generated images are fundamentally misleading because they are a simulation by a machine rather than a drawing by a human. To quote pythoncoder above: The use of AI-generated images to depict people (living or otherwise) is fundamentally misleading, because the images are not actually depicting the person.Cremastra (u — c) 00:16, 2 January 2025 (UTC)
Once again your actual problem is not AI, but with misleading images. Which can be, and are, already a violation of policy. Thryduulf (talk) 01:17, 2 January 2025 (UTC)
I think all AI-generated images, except simple diagrams as WhatamIdoing point out above, are misleading. So yes, my problem is with misleading images, which includes all photorealistic images generated by AI, which is why I support this proposal for a blanket ban in BLPs and medical articles. Cremastra (u — c) 02:30, 2 January 2025 (UTC)
Despite the fact that not all AI-generated images are misleading, not all misleading images are AI-generated and it is not always possible to tell whether an image is or is not AI-generated? Thryduulf (talk) 02:58, 2 January 2025 (UTC)
Enforcement is a separate issue. Whether or not all (or the vast majority) of AI images are misleading is the subject of this dispute.
I'm not going to mistreat the horse further, as we've each made our points and understand where the other stands. Cremastra (u — c) 15:30, 2 January 2025 (UTC)
Even "simple diagrams" are not clear-cut. The process of AI-generating any image, no matter how simple, is still very complex and can easily follow any number of different paths to meet the prompt constraints. These paths through embedding space are black boxes and the likelihood they converge on the same output is going to vary wildly depending on the degrees of freedom in the prompt, the dimensionality of the embedding space, token corpus size, etc. The only thing the user can really change, other than switching between models, is the prompt, and at some point constructing a prompt that is guaranteed to yield the same result 100% of the time becomes a Borgesian exercise. This is in contrast with non-generative AI diagram-rendering software that follow very fixed, reproducible, known paths. JoelleJay (talk) 04:44, 2 January 2025 (UTC)
Why does the path matter? If the output is correct it is correct no matter what route was taken to get there. If the output is incorrect it is incorrect no matter what route was taken to get there. If it is unknown or unknowable whether the output is correct or not that is true no matter what route was taken to get there. Thryduulf (talk) 04:48, 2 January 2025 (UTC)
If I use BioRender or GraphPad to generate a figure, I can be confident that the output does not have errors that would misrepresent the underlying data. I don't have to verify that all 18,000 data points in a scatter plot exist in the correct XYZ positions because I know the method for rendering them is published and empirically validated. Other people can also be certain that the process of getting from my input to the product is accurate and reproducible, and could in theory reconstruct my raw data from it. AI-generated figures have no prescribed method of transforming input beyond what the prompt entails; therefore I additionally have to be confident in how precise my prompt is and confident that the training corpus for this procedure is so accurate that no error-producing paths exist (not to mention absolutely certain that there is no embedded contamination from prior prompts). Other people have all those concerns, and on top of that likely don't have access to the prompt or the raw data to validate the output, nor do they necessarily know how fastidious I am about my generative AI use. At least with a hand-drawn diagram viewers can directly transfer their trust in the author's knowledge and reliability to their presumptions about the diagram's accuracy. JoelleJay (talk) 05:40, 2 January 2025 (UTC)
The original "simple geometric diagrams" comment was referring to your 100 dots image. I don't think increasing the dots materially changes the discussion beyond increasing the laboriousness of verifying the accuracy of the image. Photos of Japan (talk) 07:56, 2 January 2025 (UTC)
Yes, but since "the laboriousness of verifying the accuracy of the image" is exactly what she doesn't want to undertake for 18,000 dots, then I think that's very relevant. WhatamIdoing (talk) 07:58, 2 January 2025 (UTC)
And where is that cutoff supposed to be? 1000 dots? A single straight line? An atomic diagram? What is "simple" to someone unfamiliar with a topic may be more complex.And I don't want to count 100 dots either! JoelleJay (talk) 17:43, 2 January 2025 (UTC)
Maybe you don't. But I know for certain that you can count 10 across, 10 down, and multiply those two numbers to get 100. That's what I did when I made the image, after all. WhatamIdoing (talk) 07:44, 3 January 2025 (UTC)
Comment: when you Google search someone (at least from the Chrome browser), often the link to the Misplaced Pages article includes a thumbnail of the lead photo as a preview. Even if the photo is labelled as an AI image in the article, people looking at the thumbnail from Google would be misled (if the image is chosen for the preview). Photos of Japan (talk) 09:39, 1 January 2025 (UTC)
This is why we should not use inaccurate images, regardless of how the image was created. It has absolutely nothing to do with AI. Thryduulf (talk) 11:39, 1 January 2025 (UTC)
Already opposed a blanket ban: It's unclear to me why we have a separate BLP subsection, as BLPs are already included in the main section above. Anyway, I expressed my views there. MichaelMaggs (talk)
No For at least now, let's not let the problems of AI intrude into BLP articles which need to have the highest level of scrutiny to protect the person represented. Other areas on WP may benefit from AI image use, but let's keep it far out of BLP at this point. --Masem (t) 14:35, 1 January 2025 (UTC)
I am not a fan of “banning” AI images completely… but I agree that BLPs require special handling. I look at AI imagery as being akin to a computer generated painting. In a BLP, we allow paintings of the subject, but we prefer photos over paintings (if available). So… we should prefer photos over AI imagery. That said, AI imagery is getting good enough that it can be mistaken for a photo… so… If an AI generated image is the only option (ie there is no photo available), then the caption should clearly indicate that we are using an AI generated image. And that image should be replaced as soon as possible with an actual photograph. Blueboar (talk) 14:56, 1 January 2025 (UTC)
The issue with the latter is that Misplaced Pages images get picked up by Google and other search engines, where the caption isn't there anymore to add the context that a photorealistic image was AI-generated. Chaotic Enby (talk · contribs) 15:27, 1 January 2025 (UTC)
We're here to build an encyclopedia, not to protect commercial search engine companies.
I think my view aligns with Blueboar's (except that I find no firm preference for photos over classical portrait paintings): We shouldn't have inaccurate AI images of people (living or dead). But the day appears to be coming when AI will generate accurate ones, or at least ones that are close enough to accurate that we can't tell the difference unless the uploader voluntarily discloses that information. Once we can no longer tell the difference, what's the point in banning them? Images need to look like the thing being depicted. When we put an photorealistic image in an article, we could be said to be implicitly claiming that the image looks like whatever's being depicted. We are not necessarily warranting that the image was created through a specific process, but the image really does need to look like the subject. WhatamIdoing (talk) 03:12, 2 January 2025 (UTC)
You are presuming that sufficient accuracy will prevent us from knowing whether someone is uploading an AI photo, but that is not the case. For instance, if someone uploads large amounts of "photos" of famous people, and can't account for how they got them (e.g. can't give a source where they scraped them from, or dates or any Exif metadata at all for when they were taken), then it will still be obvious that they are likely using AI. Photos of Japan (talk) 17:38, 3 January 2025 (UTC)
As another editor pointed out in their comment, there's the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet, especially on a site such as Misplaced Pages and especially on their own biography. WP:BLP says the bios must be written conservatively and with regard for the subject's privacy.Some1 (talk) 18:37, 3 January 2025 (UTC)
Once we can no longer tell the difference, what's the point in banning them? Sounds like a wolf's in sheep's clothing to me. Just because the surface appeal of fake pictures gets better, doesn't mean we should let the horse in. Cremastra (u — c) 18:47, 3 January 2025 (UTC)
If there are no appropriately-licensed images of a person, then by definition any AI-generated image of them will be either a copyright infringement or a complete fantasy. JoelleJay (talk) 04:48, 2 January 2025 (UTC)
Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant: If an image is a copyvio we can't use it and it is irrelevant why it is a copyvio. If an image is a "complete fantasy" then it is exactly as unusable as a complete fantasy generated by non-AI means, so again AI is irrelevant. I've had to explain this multiple times in this discussion, so read that for more detail and note the lack of refutation. Thryduulf (talk) 04:52, 2 January 2025 (UTC)
Ooooh, I'm not sure that we can assume that humans aren't blatantly copying something. We can assume that they meant to be helpful, but that's not quite the same thing. WhatamIdoing (talk) 07:48, 2 January 2025 (UTC)
What this conversation is really circling around is banning entire skillsets from contributing to Misplaced Pages merely because some of us are afraid of AI images and some others of us want to engineer a convenient, half-baked, policy-level "consensus" to point to when they delete quality images from Misplaced Pages. Every time someone generates text based on a source, they are doing some acceptable level of interpretation to extract facts or rephrase it around copyright law, and I don't think illustrations should be considered so severely differently as to justify a categorical ban. For instance, the Gisele Pelicot portrait is based on non-free photos of her. Once the illustration exists, it is trivial to compare it to non-free images to determine if it is an appropriate likeness, which it is. That's no different than judging contributed text's compliance with fact and copyright by referring to the source. It shouldn't be treated differently just because most Wikipedians contribute via text. Additionally, referring to interpretive skillsets that synthesize new information like, random example, statistical analysis. Excluding those from Misplaced Pages is current practice and not controversial. Meanwhile, I think the ability to create images is more fundamental than that. It's not (inheretly) synthesizing new information. A portrait of a person (alongside the other examples in this thread) contains verifiable information. It is current practice to allow them to fill the gaps where non-free photos can't. That should continue. Honestly, it should expand.
Additionally, in direct response to "these images are fake": All illustrations of a subject could be called "fake" because they are not photographs. (Which can also be faked.) The standard for the inclusion of an illustration on Misplaced Pages has never been photorealism, medium, or previous publication in a RS. The standard is how adequately it reflects the facts which it claims to depict. If there is a better image that can be imported to Misplaced Pages via fair use or a license, then an image can be easily replaced. Until such a better image has been sourced, it is absolutely bewildering to me that we would even discuss removing images of people from their articles. What a person looked like is one of the most basic things that people want to know when they look someone up on Misplaced Pages. Including an image of almost any quality (yes, even a cartoon) is practically by definition an improvement to the article and addressing an important need. We should be encouraging artists to continue filling the gaps that non-free images cannot fill, not creating policies that will inevitably expand into more general prejudices against all new illustrations on Misplaced Pages. lethargilistic (talk) 15:59, 1 January 2025 (UTC)
By "Oppose", I'm assuming your answer to the RfC question is "Yes". And this RfC is about using AI-generated images (generated via text prompts, see also: text-to-image model) to depict BLP subjects, not regarding human-created drawings/cartoons/sketches, etc. of BLPs. Some1 (talk) 16:09, 1 January 2025 (UTC)
I've changed it to "yes" to reflect the reversed question. I think all of this is related because there is no coherent distinguishing point; AI can be used to create images in a variety of styles. These discussions have shown that a policy of banning AI images will be used against non-AI images of all kinds, so I think it's important to say these kinds of things now. lethargilistic (talk) 16:29, 1 January 2025 (UTC)
Photorealistic images scraped from who knows where from who knows what sources are without question simply fake photographs and also clear WP:OR and outright WP:SYNTH. There's no two ways about it. Articles do not require images: An article with some Frankenstein-ed image scraped from who knows what, where and, when that you "created" from a prompt is not an improvement over having no image at all. If we can't provide a quality image (like something you didn't cook up from a prompt) then people can find quality, non-fake images elsewhere. :bloodofox: (talk) 23:39, 1 January 2025 (UTC)
I really encourage you to read the discussion I linked before because it is on the WP:NOR talk page. Images like these do not inherently include either OR or SYNTH, and the arguments that they do cannot be distinguished from any other user-generated image content. But, briefly, I never said articles required images, and this is not about what articles require. It is about improvements to the articles. Including a relevant picture where none exists is almost always an improvement, especially for subjects like people. Your disdain for the method the person used to make an image is irrelevant to whether the content of the image is actually verifiable, and the only thing we ought to care about is the content. lethargilistic (talk) 03:21, 2 January 2025 (UTC)
Images like these are absolutely nothing more than synthesis in the purest sense of the world and are clearly a violation of WP:SYNTH: Again, you have no idea what data was used to generate these images and you're going to have a very hard time convincing anyone to describe them as anything other than outright fakes.
A reminder that WP:SYNTH shuts down attempts at manipulation of images ("It is not acceptable for an editor to use photo manipulation to distort the facts or position illustrated by an image. Manipulated images should be prominently noted as such. Any manipulated image where the encyclopedic value is materially affected should be posted to Misplaced Pages:Files for discussion. Images of living persons must not present the subject in a false or disparaging light.") and generating a photorealistic image (from who knows what!) is far beyond that.
Fake images of people do not improve our articles in any way and only erode reader trust. What's next, an argument for the fake sources LLMs also love to "hallucinate"? :bloodofox: (talk) 03:37, 2 January 2025 (UTC)
So, if you review the first sentence of SYNTH, you'll see it has no special relevance to this discussion: Do not combine material from multiple sources to state or imply a conclusion not explicitly stated by any of the sources.. My primary example has been a picture of a person; what a person looks like is verifiable by comparing the image to non-free images that cannot be used on Misplaced Pages. If the image resembles the person, it is not SYNTH. An illustration of a person created and intended to look like that person is not a manipulation. The training data used to make the AI is irrelevant to whether the image in fact resembles the person. You should also review WP:NOTSYNTH because SYNTH is not a policy; NOR is the policy: If a putative SYNTH doesn't constitute original research, then it doesn't constitute SYNTH. Additionally, not all synthesis is even SYNTH. A categorical rule against AI cannot be justified by SYNTH because it does not categorically apply to all use cases of AI. To do so would be illogical on top of ill-advised. lethargilistic (talk) 08:08, 2 January 2025 (UTC)
"training data used to make the AI is irrelevant" — spoken like a true AI evangelist! Sorry, 'good enough' photorealism is still just synthetic slop, a fake image presented as real of a human being. A fake image of someone generated from who-knows-what that 'resembles' an article's subject is about as WP:SYNTH as it gets. Yikes. As for the attempts to pass of prompt-generated photorealistic fakes of people as somehow the same as someone's illustration, you're completely wasting your time. :bloodofox: (talk) 09:44, 2 January 2025 (UTC)
NOR is a content policy and SYNTH is content guidance within NOR. Because you have admitted that this is not about the content for you, NOR and SYNTH are irrelevant to your argument, which boils down to WP:IDONTLIKEIT and, now, inaccurate personal attacks. Continuing this discussion between us would be pointless. lethargilistic (talk) 09:52, 2 January 2025 (UTC)
This is in fact entirely about content (why the hell else would I bother?) but it is true that I also dismissed your pro-AI 'it's just like a human drawing a picture!' as outright nonsense a while back. Good luck convincing anyone else with that line - it didn't work here. :bloodofox: (talk) 09:59, 2 January 2025 (UTC)
Maybe: there is an implicit assumption with this RFC that an AI generated image would be photorealistic. There hasn't been any discussion of an AI generated sketch. If you asked an AI to generate a sketch (that clearly looked like a sketch, similar to the Gisèle Pelicot example) then I would potentially be ok with it. Photos of Japan (talk) 18:14, 1 January 2025 (UTC)
That's an interesting thought to consider. At the same time, I worry about (well-intentioned) editors inundating image-less BLP articles with AI-generated images in the style of cartoons/sketches (if only photorealistic ones are prohibited) etc. At least requiring a human to draw/paint/whatever creates a barrier to entry; these AI-generated images can be created in under a minute using these text-to-image models. Editors are already wary about human-created cartoon portraits (see the NORN discussion), now they'll be tasked with dealing with AI-generated ones in BLP articles. Some1 (talk) 20:28, 1 January 2025 (UTC)
It sounds like your problem is not with AI but with cartoon/sketch images in BLP articles, so AI is once again completely irrelevant. Thryduulf (talk) 22:14, 1 January 2025 (UTC)
That is a good concern you brought up. There is a possibility of the spamming of low quality AI-generated images which would be laborious to discuss on a case-by-case basis but easy to generate. At the same time though that is a possibility, but not yet an actuality, and WP:CREEP states that new policies should address current problems rather than hypothetical concerns. Photos of Japan (talk) 22:16, 1 January 2025 (UTC)
Easy no for me. I am not against the use of AI images wholesale, but I do think that using AI to represent an existent thing such as a person or a place is too far. Even a tag wouldn't be enough for me. Cessaune19:05, 1 January 2025 (UTC)
No obviously, per previous discussions about cartoonish drawn images in BLPs. Same issue here as there, it is essentially original research and misrepresentation of a living person's likeness. Zaathras (talk) 22:19, 1 January 2025 (UTC)
No to photorealistic, no to cartoonish... this is not a hard choice. The idea that "this has nothing to do with AI" when "AI" magnifies the problem to stupendous proportions is just not tenable. XOR'easter (talk) 23:36, 1 January 2025 (UTC)
While AI might "amplify" the thing you dislike, that does not make AI the problem. The problem is whatever underlying thing is being amplified. Thryduulf (talk) 01:16, 2 January 2025 (UTC)
That is arguable, but banning the amplifier does not do anything to solve the problem. In this case, banning the amplifier would cause multiple other problems that nobody supporting this proposal as even attempted to address, let alone mitigate. Thryduulf (talk) 03:04, 2 January 2025 (UTC)
No - We should not be hosting faked images (except as notable fakes). We should also not be hosting copyvios ("Whether it would be a copyright infringement or not is both an unsettled legal question and not relevant" is just totally wrong - we should be steering clear of copyvios, and if the issue is unsettled then we shouldn't use them until it is).
If people upload faked images to WP or Commons the response should be as it is now. The fact that fakes are becoming harder to detect simply from looking at them hardly affects this - we simply confirm when the picture was supposed to have been taken and examine the plausibility of it from there. FOARP (talk) 14:39, 2 January 2025 (UTC) FOARP (talk) 14:39, 2 January 2025 (UTC)
we should be steering clear of copyvio we do - if an image is a copyright violation it gets deleted, regardless of why it is a copyright violation. What we do not do is ban using images that are not copyright violations because they are copyright violations. Currently the WMF lawyers and all the people on Commons who know more about copyright than I do say that at least some AI images are legally acceptable for us to host and use. If you want to argue that, then go ahead, but it is not relevant to this discussion.
if people upload faked images the response should be as it is now in other words you are saying that the problem is faked images not AI, and that current policies are entirely adequate to deal with the problem of faked images. So we don't need any specific rules for AI images - especially given that not all AI images are fakes. Thryduulf (talk) 15:14, 2 January 2025 (UTC)
The idea that current policies are entirely adequate is like saying that a lab shouldn't have specific rules about wearing eye protection when it already has a poster hanging on the wall that says "don't hurt yourself". XOR'easter (talk) 18:36, 2 January 2025 (UTC)
"in other words you are saying that the problem is faked images not AI" - AI generated images *are* fakes. This is merely confirming that for the avoidance of doubt.
"at least some AI images are legally acceptable for us" - Until they decide which ones that isn't much help. FOARP (talk) 19:05, 2 January 2025 (UTC)
Those specific rules exist because generic warnings have proven not to be sufficient. Nobody has presented any evidence that the current policies are not sufficient, indeed quite the contrary. Thryduulf (talk) 19:05, 2 January 2025 (UTC)
Noting that I think that no AI-generated images are acceptable in BLP articles, regardless of whether they are photorealistic or not. JuxtaposedJacob (talk) | :) | he/him | 15:40, 3 January 2025 (UTC)
No, unless the AI image has encyclopedic significance beyond "depicts a notable person". AI images, if created by editors for the purpose of inclusion in Misplaced Pages, convey little reliable information about the person they depict, and the ways in which the model works are opaque enough to most people as to raise verifiability concerns. ModernDayTrilobite (talk • contribs) 15:25, 2 January 2025 (UTC)
To clarify, do you object to uses of an AI image in a BLP when the subject uses that image for self-identification? I presume that AI images that have been the subject of notable discussion are an example of "significance beyond depict a notable person"? Thryduulf (talk) 15:54, 2 January 2025 (UTC)
If the subject uses the image for self-identification, I'd be fine with it - I think that'd be analogous to situations such as "cartoonist represented by a stylized self-portrait", which definitely has some precedent in articles like Al Capp. I agree with your second sentence as well; if there's notable discussion around a particular AI image, I think it would be reasonable to include that image on Misplaced Pages. ModernDayTrilobite (talk • contribs) 19:13, 2 January 2025 (UTC)
No, with obvious exceptions, including if the subject theyrself uses the image as a their representation, or if the image is notable itself. Not including the lack of a free aleternative, if there is no free alternative... where did the AI find data to build an image... non free too. Not including images generated by WP editors (that's kind of original research... - Nabla (talk) 18:02, 2 January 2025 (UTC
Maybe I think the question is unfair as it is illustrated with what appears to be a photo of the subject but isn't. People are then getting upset that they've been misled. As others note, there are copyright concerns with AI reproducing copyrighted works that in turn make an image that is potentially legally unusable. But that is more a matter for Commons than for Misplaced Pages. As many have noted, a sketch or painting never claims to be an accurate depiction of a person, and I don't care if that sketch or painting was done by hand or an AI prompt. I strongly ask Some1 to abort the RFC. You've asked people to give a yes/no vote to what is a more complex issue. A further problem with the example used is the unfortunate prejudice on Misplaced Pages against user-generated content. While the text-generated AI of today is crude and random, there will come a point where many professionally published photos illustrating subjects, including people, are AI generated. Even today, your smartphone can create a groupshot where everyone is smiling and looking at the camera. It was "trained" on the 50 images it quickly took and responded to the build-in "text prompt" of "create a montage of these photos such that everyone is smiling and looking at the camera". This vote is a knee jerk reaction to content that is best addressed by some other measure (such as that it is a misleading image). And a good example of asking people to vote way too early, when the issues haven't been throught out -- Colin°18:17, 2 January 2025 (UTC)
No This would very likely set a dangerous precedent. The only exception I think should be if the image itself is notable. If we move forward with AI images, especially for BLPs, it would only open up a whole slew of regulations and RfCs to keep them in check. Better no image than some digital multiverse version of someone that is "basically" them but not really. Not to mention the ethics/moral dilemma of creating fake photorealistic pictures of people and putting them on the internet. Tepkunset (talk) 18:31, 2 January 2025 (UTC)
No. LLMs don't generate answers, they generate things that look like answers, but aren't; a lot of the time, that's good enough, but sometimes it very much isn't. It's the same issue for text-to-image models: they don't generate photos of people, they generate things that look like photos. Using them on BLPs is unacceptable. DS (talk) 19:30, 2 January 2025 (UTC)
No. I would be pissed if the top picture of me on Google was AI-generated. I just don't think it's moral for living people. The exceptions given above by others are okay, such as if the subject uses the picture themselves or if the picture is notable (with context given). win8x (talk) 19:56, 2 January 2025 (UTC)
No. Uploading alone, although mostly a Commons issue, would already a problem to me and may have personality rights issues. Illustrating an article with a fake photo (or drawing) of a living person, even if it is labeled as such, would not be acceptable. For example, it could end up being shown by search engines or when hovering over a Misplaced Pages link, without the disclaimer. ~ ToBeFree (talk) 23:54, 2 January 2025 (UTC)
I was going to say no... but we allow paintings as portraits in BLPs. What's so different between an AI generated image, and a painting? Arguments above say the depiction may not be accurate, but the same is true of some paintings, right? (and conversely, not true of other paintings) ProcrastinatingReader (talk) 00:48, 3 January 2025 (UTC)
A painting is clearly a painting; as such, the viewer knows that it is not an accurate representation of a particular reality. An AI-generated image made to look exactly like a photo, looks like a photo but is not.
Not all paintings are clearly paintings. Not all AI-generated images are made to look like photographs. Not all AI-generated images made to look like photos do actually look like photos. This proposal makes no distinction. Thryduulf (talk) 02:55, 3 January 2025 (UTC)
Not to mention, hyper-realism is a style an artist may use in virtually any medium. Colored pencils can be used to make extremely realistic portraits. If Misplaced Pages would accept an analog substitute like a painting, there's no reason Misplaced Pages shouldn't accept an equivalent painting made with digital tools, and there's no reason Misplaced Pages shouldn't accept an equivalent painting made with AI. That is, one where any obvious defects have been edited out and what remains is a straightforward picture of the subject. lethargilistic (talk) 03:45, 3 January 2025 (UTC)
For the record (and for any media watching), while I personally find it fascinating that a few editors here are spending a substantial amount of time (in the face of an overwhelming 'absolutely not' consensus no less) attempting to convince others that computer-generated (that is, faked) photos of human article subjects are somehow a good thing, I also find it interesting that these editors seem to express absolutely no concern for the intensely negative reaction they're already seeing from their fellow editors and seem totally unconcerned about the inevitable trust drop we'd experience from Misplaced Pages readers when they would encounter fake photos on our BLP articles especially. :bloodofox: (talk) 03:54, 3 January 2025 (UTC)
Misplaced Pages's reputation would not be affected positively or negatively by expanding the current-albeit-sparse use of illustrations to depict subjects that do not have available pictures. In all my writing about this over the last few days, you are the only one who has said anything negative about me as a person or, really, my arguments themselves. As loath as I am to cite it, WP:AGF means assuming that people you disagree with are not trying to hurt Misplaced Pages. Thryduulf, I, and others have explained in detail why we think our ultimate ideas are explicit benefits to Misplaced Pages and why our opposition to these immediate proposals comes from a desire to prevent harm to Misplaced Pages. I suggest taking a break to reflect on that, matey. lethargilistic (talk) 04:09, 3 January 2025 (UTC)
Look, I don't know if you've been living under a rock or what for the past few years but the reality is that people hate AI images and dumping a ton of AI/fake images on Misplaced Pages, a place people go for real information and often trust, inevitably leads to a huge trust issue, something Misplaced Pages is increasingly suffering from already. This is especially a problem when they're intended to represent living people (!). I'll leave it to you to dig up the bazillion controversies that have arisen and continue to arise since companies worldwide have discovered that they can now replace human artists with 'AI art' produced by "prompt engineers" but you can't possibly expect us to ignore that reality when discussing these matters. :bloodofox: (talk) 04:55, 3 January 2025 (UTC)
Those trust issues are born from the publication of hallucinated information. I have only said that it should be OK to use an image on Misplaced Pages when it contains only verifiable information, which is the same standard we apply to text. That standard is and ought to be applied independently of the way the initial version of an image was created. lethargilistic (talk) 06:10, 3 January 2025 (UTC)
To my eye, the distinction between AI images and paintings here is less a question of medium and more of verifiability: the paintings we use (or at least the ones I can remember) are significant paintings that have been acknowledged in sources as being reasonable representations of a given person. By contrast, a purpose-generated AI image would be more akin to me painting a portrait of somebody here and now and trying to stick that on their article. The image could be a faithful representation (unlikely, given my lack of painting skills, but let's not get lost in the metaphor), but if my painting hasn't been discussed anywhere besides Misplaced Pages, then it's potentially OR or UNDUE to enshrine it in mainspace as an encyclopedic image. ModernDayTrilobite (talk • contribs) 05:57, 3 January 2025 (UTC)
An image contains a collection of facts, and those facts need to be verifiable just like any other information posted on Misplaced Pages. An image that verifiably resembles a subject as it is depicted in reliable sources is categorically not OR. Discussion in other sources is not universally relevant; we don't restrict ourselves to only previously-published images. If we did that, Misplaced Pages would have very few images. lethargilistic (talk) 06:18, 3 January 2025 (UTC)
Verifiable how? Only by the editor themselves comparing to a real photo (which was probably used by the LLM to create the image…).
Verifiable by comparing them to a reliable source. Exactly the same as what we do with text. There is no coherent reason to treat user-generated images differently than user-generated text, and the universalist tenor of this discussion has damaging implications for all user-generated images regardless of whether they were created with AI. Honestly, I rarely make arguments like this one, but I think it could show some intuition from another perspective: Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures. The text editors say the artists cannot contribute ANYTHING to Misplaced Pages because their images that have not been previously published are not verifiable. That is a double-standard that privileges the contributions of text-editors simply because most users are text-editors and they are used to verifying text; that is not a principled reason to treat text and images differently. Moreover, that is simply not what happened—The opposite happend, and images are treated as verifiable based on their contents just like text because that's a common sense reading of the rule. It would have been madness if images had been treated differently. And yet that is essentially the fundamentalist position of people who are extending their opposition to AI with arguments that apply to all images. If they are arguing verifiability seriously at all, they are pretending that the sort of degenerate situation I just described already exists when the opposite consensus has been reached consistently for years. In the related NOR thread, they even tried to say Wikipedians had "turned a blind eye" to these image issues as if negatively characterizing those decisions would invalidate the fact that those decisions were consensus. The motivated reasoning of these discussions has been as blatant as that. At the bottom of this dispute, I take issue with trying to alter the rules in a way that creates a new double-standard within verifiability that applies to all images but not text. That's especially upsetting when (despite my and others' best efforts) so many of us are still focusing SOLELY on their hatred for AI rather than considering the obvious second-order consequences for user-generated images as a whole. Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake." The issue has always been verifiability, not provenance or falsity. Sometimes, IMO, that has lead to disaster and Misplaced Pages saying things I know to be factually untrue despite the contents of reliable sources. But that is the policy. We compare the contents of Misplaced Pages to reliable sources, and the contents of Misplaced Pages are considered verifiable if they cohere. I ask again: If Misplaced Pages's response to the creation of AI imaging tools is to crack down on all artistic contributions to Misplaced Pages (which seems to be the inevitable direction of these discussions), what does that say? If our negative response to AI tools is to limit what humans can do on Misplaced Pages, what does that say? Are we taking a stand for human achievements, or is this a very heated discussion of cutting off our nose to save our face? lethargilistic (talk) 23:31, 4 January 2025 (UTC)
"Verifiable by comparing them to a reliable source" - comparing two images and saying that one looks like the other is not "verifying" anything. The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing.
"Frankly, in no other context has any Wikipedian ever allowed me to say text they wrote was "fake" or challenge an image based on whether it was "fake."" - Try presenting a paraphrasing as a quotation and see what happens.
"Imagine it's 2002 and Misplaced Pages is just starting. Most users want to contribute text to the encyclopedia, but there is a cadre of artists who want to contribute pictures..." - This basically happened, and is the origin of WP:NOTGALLERY. Misplaced Pages is not a host for original works. FOARP (talk) 22:01, 6 January 2025 (UTC)
Comparing two images and saying that one looks like the other is not "verifying" anything. Comparing text to text in a reliable source is literally the same thing.
The text equivalent is presenting something as a quotation that is actually a user-generated paraphrasing. No it isn't. The text equivalent is writing a sentence in an article and putting a ref tag on it. Perhaps there is room for improving the referencing of images in the sense that they should offer example comparisons to make. But an image created by a person is not unverifiable simply because it is user-generated. It is not somehow more unverifiable simply because it is created in a lifelike style.
Try presenting a paraphrasing as a quotation and see what happens. Besides what I just said, nobody is even presenting these images as equatable to quotations. People in this thread have simply been calling them "fake" of their own initiative; the uploaders have not asserted that these are literal photographs to my knowledge. The uploaders of illustrations obviously did not make that claim either. (And, if the contents of the image is a copyvio, that is a separate issue entirely.)
This basically happened, and is the origin of WP:NOTGALLERY. That is not the same thing. User-generated images that illustrate the subject are not prohibited by WP:NOTGALLERY. Misplaced Pages is a host of encyclopedic content, and user-generated images can have encyclopedic content. lethargilistic (talk) 02:41, 7 January 2025 (UTC)
Images are way more complex than text. Trying to compare them in the same way is a very dangerous simplification. Cremastra (u — c) 02:44, 7 January 2025 (UTC)
Assume only non-free images exist of a person. An illustrator refers to those non-free images and produces a painting. From that painting, you see a person who looks like the person in the non-free photographs. The image is verified as resembling the person. That is a simplification, but to call it "dangerous" is disingenuous at best. The process for challenging the image is clear. Someone who wants to challenge the veracity of the image would just need to point to details that do not align. For instance, "he does not typically have blue hair" or "he does not have a scar." That is what we already do, and it does not come up much because it would be weird to deliberately draw an image that looks nothing like the person. Additionally, someone who does not like the image for aesthetic reasons rather than encyclopedic ones always has the option of sourcing a photograph some other way like permission, fair use, or taking a new one themself. This is not an intractable problem. lethargilistic (talk) 02:57, 7 January 2025 (UTC)
So a photorealistic AI-generated image would be considered acceptable until someone identifies a "big enough" difference? How is that anything close to ethical? An portrait that's got an extra mole or slightly wider nose bridge or lacks a scar is still not an image of the person regardless of whether random Misplaced Pages editors notice. And while I don't think user-generated non-photorealistic images should ever be used on biographies either, at least those can be traced back to a human who is ultimately responsible for the depiction, who can point to the particular non-free images they used as references, and isn't liable to average out details across all time periods of the subject. And that's not even taking into account the copyright issues. JoelleJay (talk) 22:52, 7 January 2025 (UTC)
+1 to what JoelleJay said. The problem is that AI-generated images are simulations trying to match existing images, sometimes, yes, with an impressive degree of accuracy. But they will always be inferior to a human-drawn painting that's trying to depict the person. We're a human encyclopedia, and we're built by humans doing human things and sometimes with human errors. Cremastra (u — c) 23:18, 7 January 2025 (UTC)
You can't just raise this to an "ethical" issue by saying the word "ethical." You also can't just invoke copyright without articulating an actual copyright issue; we are not discussing copyvio. Everyone agrees that a photo with an actual copyvio in it is subject to that policy.
But to address your actual point: Any image—any photo—beneath the resolution necessary to depict the mole would be missing the mole. Even with photography, we are never talking about science-fiction images that perfectly depict every facet of a person in an objective sense. We are talking about equipment that creates an approximation of reality. The same is true of illustrations and AI imagery.
Finally, a human being is responsible for the contents of the image because a human is selecting it and is responsible for correcting any errors. The result is an image that someone is choosing to use because they believe it is an appropriate likeness. We should acknowledge that human decision and evaluate it naturally—Is it an appropriate likeness?lethargilistic (talk) 10:20, 8 January 2025 (UTC)
(Second comment because I'm on my phone.) I realize I should also respond to this in terms of additive information. What people look like is not static in the way your comment implies. Is it inappropriate to use a photo because they had a zit on the day it was taken? Not necessarily. Is an image inappropriate because it is taken at a bad angle that makes them look fat? Judging by the prolific ComicCon photographs (where people seem to make a game of choosing the worst-looking options; seriously, it's really bad), not necessarily. Scars and bruises exist and then often heal over time. The standard for whether an image with "extra" details is acceptable would still be based on whether it comports acceptably with other images; we literally do what you have capriciously described as "unethical" and supplement it with our compassionate desire to not deliberately embarrass BLPs. (The ComicCon images aside, I guess.) So, no, I would not be a fan of using images that add prominent scars where the subject is not generally known to have one, but that is just an unverifiable fact that does not belong in a Misplaced Pages image. Simple as. lethargilistic (talk) 10:32, 8 January 2025 (UTC)
We don't evaluate the reliability of a source solely by comparing it to other sources. For example, there is an ongoing discussion at the baseball WikiProject talk page about the reliability of a certain web site. It lists no authors nor any information on its editorial control policy, so we're not able to evaluate its reliability. The reliability of all content being used as a source, including images, needs to be considered in terms of its provenance. isaacl (talk) 23:11, 7 January 2025 (UTC)
Still no, I thought I was clear on that but we should not be using AI-generated images in articles for anything besides representing the concept of AI-generated images, or if an AI-generated image is notable or irreplaceable in its own right -- e.g, a musician uses AI to make an album cover.
(this isn't even a good example, it looks more like Steve Bannon)
I still think no. My opposition isn't just to the fact that AI images are misinformation, but also that they essentially serve as a loophole for getting around Enwiki's image use policy. To know what somebody looks like, an AI generator needs to have images of that person in its dataset, and it draws on those images to generate a derivative work. If we have no free images of somebody and we use AI to make one, that's just using a fair use copyrighted image but removed by one step. The image use policy prohibits us from using fair use images for BLPs so I don't think we should entertain this loophole. If we do end up allowing AI images in BLPs, that just disqualifies the rationale of not allowing fair use in the first place. Di (they-them) (talk) 04:40, 3 January 2025 (UTC)
No those are not okay, as this will just cause arguments from people saying a picture is obviously AI-generated, and that it is therefore appropriate. As I mentionned above, there are some exceptions to this, which Gnomingstuff perfectly describes. Fake sketches/cartoons are not appropriate and provide little encyclopedic value. win8x (talk) 05:27, 3 January 2025 (UTC)
No to this as well, with the same carveout for individual images that have received notable discussion. Non-photorealistic AI images are going to be no more verifiable than photorealistic ones, and on top of that will often be lower-quality as images. ModernDayTrilobite (talk • contribs) 05:44, 3 January 2025 (UTC)
No, and that image should be deleted before anyone places it into a mainspace article. Changing the RfC intro long after its inception seems a second bite at an apple that's not aged well. Randy Kryn (talk) 09:28, 3 January 2025 (UTC)
The RfC question has not been changed; another editor was complaining that the RfC question did not make a distinction between photorealistic/non-photorealistic AI-generated images, so I had to add a note to the intro and ping the editors who'd voted !No to clarify things. It has only been 3 days; there's still 27 more days to go. Some1 (talk) 11:18, 3 January 2025 (UTC)
Also answering No to this one per all the arguments above. "It has only been 3 days" is not a good reason to change the RfC question, especially since many people have already !voted and the "30 days" is mostly indicative rather than an actual deadline for a RfC. Chaotic Enby (talk · contribs) 14:52, 3 January 2025 (UTC)
No. We're the human encyclopedia. We should have images drawn or taken by real humans who are trying to depict the subject, not by machines trying to simulate an image. Besides, the given example is horribly drawn. Cremastra (u — c) 15:03, 3 January 2025 (UTC)
I like these even less than the photorealistic ones... This falls into the same basket for me: if we wouldn't let a random editor who drew this at home using conventional tools add it to the article why would we let a random editor who drew this at home using AI tools at it to the article? (and just to be clear the AI generated image of Germán Larrea Mota-Velasco is not recognizable as such) Horse Eye's Back (talk) 16:06, 3 January 2025 (UTC)
No Having such images as said above means the AI had to use copyrighted pictures to create it and we shouldn't use it. --SuperJew (talk) 01:12, 5 January 2025 (UTC)
Still no. If for no other reason than that it's a bad precedent. As others have said, if we make one exception, it will just lead to arguments in the future about whether something is "realistic" or not. I also don't see why we would need cartoon/illustrated-looking AI pictures of people in BLPs. Tepkunset (talk) 20:43, 6 January 2025 (UTC)
Absolutely not. These images are based on whatever the AI could find on the internet, with little to no regard for copyright. Misplaced Pages is better than this. Retswerb (talk) 10:16, 3 January 2025 (UTC)
Comment The RfC question should not have been fiddled with, esp. for such a minor argument that the complai9nmant could have simply included in their own vote. I have no need to re-confirm my own entry. Zaathras (talk) 14:33, 3 January 2025 (UTC)
The RfC question hasn't been modified; I've only added a 03:58, January 3, 2025: Note clarifying that these images can either be photorealistic in style or non-photorealistic in style. I pinged all the !No voters to make them aware. I could remove the Note if people prefer that I do (but the original RfC question is the exact same as it is now, so I don't think the addition of the Note makes a whole ton of difference). Some1 (talk) 15:29, 3 January 2025 (UTC)
No At this point it feels redundant, but I'll just add to the horde of responses in the negative. I don't think we can fully appreciate the issues that this would cause. The potential problems and headaches far outweigh whatever little benefit might come from AI images for BLPs. pillowcrow21:34, 3 January 2025 (UTC)
Support temporary blanket ban with a posted expiration/requred rediscussion date of no more than two years from closing. AI as the term is currently used is very, very new. Right now these images would do more harm than good, but it seems likely that the culture will adjust to them. Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
No. Misplaced Pages is made by and for humans. I don't want to become Google. Adding an AI-generated image to a page whose topic isn't about generative AI makes me feel insulted. SWinxy (talk) 00:03, 4 January 2025 (UTC)
No. Generative AI may have its place, and it may even have a place on Misplaced Pages in some form, but that place isn't in BLPs. There's no reason to use images of someone that do not exist over a real picture, or even something like a sketch, drawing, or painting. Even in the absence of pictures or human-drawn/painted images, I don't support using AI-generated images; they're not really pictures of the person, after all, so I can't support using them on articles of people. Using nothing would genuinely be a better choice than generated images. SmittenGalaxy | talk!01:07, 4 January 2025 (UTC)
No. Even if you are willing to ignore the inherently fraught nature of using AI-generated anything in relation to BLP subjects, there is simply little to no benefit that could possibly come from trying something like this. There's no guarantee the images will actually look like the person in question, and therefore there's no actual context or information that the image is providing the reader. What a baffling proposal. Ithinkiplaygames (talk) 19:53, 4 January 2025 (UTC)
There's no guarantee the images will actually look like the person in question there is no guarantee any image will look like the person in question. When an image is not a good likeness, regardless of why, we don't use it. When am image is a good likeness we consider using it. Whether an image is AI-generated or not it is completely independent of whether it is a good likeness. There are also reason other then identification why images are used on BLP-articles. Thryduulf (talk) 20:39, 4 January 2025 (UTC)
Foreseeably there may come a time when people's official portraits are AI-enhanced. That time might not be very far in the future. Do we want an exception for official portraits?—S MarshallT/C01:17, 5 January 2025 (UTC)
Yes, depending on specific case. One can use drawings by artists, even such as caricature. The latter is an intentional distortion, one could say an intentional misinformation. Still, such images are legitimate on many pages. Or consider numerous images of Jesus. How realiable are they? I am not saying we must deliberatly use AI images on all pages, but they may be fine in some cases. Now, speaking on "medical articles"... One might actually use the AI generated images of certain biological objects like proteins or organelles. Of course a qualified editorial judgement is always needed to decide if they would improve a specific page (frequently they would not), but making a blanket ban would be unacceptable, in my opinion. For example, the images of protein models generatated by AlphaFold would be fine. The AI-generated images of biological membranes I saw? I would say no. It depends. My very best wishes (talk) 02:50, 5 January 2025 (UTC)
This is complicated of course. For example, there are tools that make an image of a person that (mis)represents him as someone much better and clever than he really is in life. That should be forbidden as an advertisement. This is a whole new world, but I do not think that a blanket rejection would be appropriate. My very best wishes (talk) 03:19, 5 January 2025 (UTC)
No Too risky for BLP's. Besides if people want AI generated content over editor made content, we should make it clear they are in the wrong place, and readers should be given no doubt as to our integrity, sincerity and effort to give them our best, not a program's. Alanscottwalker (talk) 14:51, 5 January 2025 (UTC)
No, as AI's grasp on the Internet takes hold stronger and stronger, it's important Misplaced Pages, as the online encyclopedia it sets out to be, remains factual and real. Using AI images on Wiki would likely do more harm than good, further thinning the boundaries between what's real and what's not. – zmbro(talk) (cont)16:52, 5 January 2025 (UTC)
No, not at the moment. I think it will hard to avoid portraits that been enhanced by AI, as it already been on-going for a number of years and there is no way to avoid it, but I don't want arbitary generated AI portraits of any type. scope_creep20:19, 5 January 2025 (UTC)
No for natural images (e.g. photos of people). Generative AI by itself is not a reliable source for facts. In principle, generating images of people and directly sticking them in articles is no different than generating text and directly sticking it in articles. In practice, however, generating images is worse: Text can at least be discussed, edited, and improved afterwards. In contrast, we have significantly less policy and fewer rigorous methods of discussing how AI-generated images of natural objects should be improved (e.g. "make his face slightly more oblong, it's not close enough yet"). Discussion will devolve into hunches and gut feelings about the fidelity of images, all of which essentially fall under WP:OR. spintheer (talk) 20:37, 5 January 2025 (UTC)
No I'm appalled that even a small minority of editors would support such an idea. We have enough credibility issues already; using AI-generated images to represent real people is not something that a real encyclopedia should even consider. LEPRICAVARK (talk) 22:26, 5 January 2025 (UTC)
No I understand the comparison to using illustrations in BLP articles, but I've always viewed that as less preferable to no picture in all honestly. Images of a person are typically presented in context, such as a performer on stage, or a politician's official portrait, and I feel like there would be too many edge cases to consider in terms of making it clear that the photo is AI generated and isn't representative of anything that the person specifically did, but is rather an approximation. Tpdwkouaa (talk) 06:50, 6 January 2025 (UTC)
No - Too often the images resemble caricatures. Real caricatures may be included in articles if the caricature (e.g., political cartoon) had significant coverage and is attributed to the artist. Otherwise, representations of living persons should be real representations taken with photographic equipment. Robert McClenon (talk) 02:31, 7 January 2025 (UTC)
No - Not only is this effectively guesswork that usually includes unnatural artefacts, but worse, it is also based on unattributed work of photographers who didn't release their work into public domain. I don't care if it is an open legal loophole somewhere, IMO even doing away with the fair use restriction on BLPs would be morally less wrong. I suspect people on whose work LLMs in question were trained would also take less offense to that option. DaßWölf23:25, 7 January 2025 (UTC)
No – WP:NFC says that Non-free content should not be used when a freely licensed file that serves the same purpose can reasonably be expected to be uploaded, as is the case for almost all portraits of living people. While AI images may not be considered copyrightable, it could still be a copyright violation if the output resembles other, copyrighted images, pushing the image towards NFC. At the very least, I feel the use of non-free content to generate AI images violates the spirit of the NFC policy. (I'm assuming copyrighted images of a person are used to generate an AI portrait of them; if free images of that person were used, we should just use those images, and if no images of the person were used, how on Earth would we trust the output?) RunningTiger123 (talk) 02:43, 8 January 2025 (UTC)
The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Expiration date?
"AI," as the term is currently used, is very new. It feels like large language models and the type of image generators under discussion just got here in 2024. (Yes, I know it was a little earlier.) The culture hasn't completed its initial response to them yet. Right now, these images do more harm than good, but that may change. Either we'll come up with a better way of spotting hallucinations or the machines will hallucinate less. Their copyright status also seems unstable. I suggest that any ban decided upon here have some expiration date or required rediscussion date. Two years feels about right to me, but the important thing would be that the ban has a number on it. Darkfrog24 (talk) 23:01, 3 January 2025 (UTC)
No need for any end-date. If there comes a point where consensus on this changes, then we can change any ban then. FOARP (talk) 05:27, 5 January 2025 (UTC)
An end date is a positive suggestion. Consensus systems like Misplaced Pages's are vulnerable to half-baked precedential decisions being treated as inviolate. With respect, this conversation does not inspire confidence that this policy proposal's consequences are well-understood at this time. If Misplaced Pages goes in this direction, it should be labeled as primarily reactionary and open to review at a later date. lethargilistic (talk) 10:22, 5 January 2025 (UTC)
Agree with FOARP, no need for an end date. If something significantly changes (e.g. reliable sources/news outlets such as the New York Times, BBC, AP, etc. start using text-to-image models to generate images of living people for their own articles) then this topic can be revisited later. Editors will have to go through the usual process of starting a new discussion/proposal when that time comes. Some1 (talk) 11:39, 5 January 2025 (UTC)
Seeing as this discussion has not touched at all on what other organizations may or may not do, it would not be accurate to describe any consensus derived from this conversation in terms of what other organizations may or may not be doing. That is, there has been no consensus that we ought to be looking to the New York Times as an example. Doing so would be inadvisable for several reasons. For one, they have sued an AI company over semi-related issues and they have teams explicitly working on what the future of AI in news ought to look like, so they have some investment in what the future of AI looks like and they are explicitly trying to shape its norms. For another, if they did start to use AI in a way that may be controversial, they would have no positive reason to disclose that and many disincentives. They are not a neutral signal on this issue. Misplaced Pages should decide for itself, preferably doing so while not disrupting the ability of people to continue creating user-generated images. lethargilistic (talk) 03:07, 6 January 2025 (UTC)
No need per others. Additionally, if practices change, it doesn't mean editors will decide to follow new practices. As for the technology, it seems the situation has been fairly stable for the past two years: we can detect some fakes and hallucinations immediately, many more in the past, but certainly not all retouched elements and all generated photos available right now, even if there was a readily accessible tool or app that enabled ordinary people to reliably do so.
Through the history, art forgeries have been fairly reliably detected, but rarely quickly. Relatedly, I don't see why the situation with AI images would change in the next 24 months or any similar time period. DaßWölf22:17, 9 January 2025 (UTC)
Non-Admin XFD Close as Delete
There is a contentious Deletion Review currently resulting from a Non-administrative close of a Redirect for Discussion in which the closer found that the consensus was Delete. The closer then tagged the redirect with G6, in particular {{db-xfd}}. It was then deleted by an admin who had taken part in the deletion discussion. The guideline on non-administrative closes says that a non-administrative close of Delete is not permitted, because the closer cannot press the Delete button. The first question at DRV seems to be whether DRV must vacate the close and allow a new close by an uninvolved administrator, or whether DRV can endorse the close and leave the close standing. My opinion is that a DRV endorsement of a non-admin close is as good a close as a regular admin close, but that is only my opinion.
The second question that is raised by the DRV discussion is about the existing practice that non-admins sometimes make Delete closes at CFD. Should this practice be stopped, because the guideline says that non-admins may not make Delete closes, or should the guideline be revised, or should the guideline be left as is, but with such closes being sometimes allowed? My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion.
On the first question, I think that whatever decision DRV makes at Misplaced Pages:Deletion review#Clock/calendar will be 'legal'. They are not required to vacate the close, no matter how much one editor might like to have a second bite at that apple.
On your second question, I prefer the existing rules. It is not necessary to allow NACs (non-admin closures) of 'delete'. Good admins will not blindly trust anyone else's decision, so a NAC to delete does not necessarily save any time, and if the admin disagrees, then it could cause drama. NACs to delete should be gently but firmly discouraged. WhatamIdoing (talk) 07:30, 31 December 2024 (UTC)
As I said at the Deletion Review, I support non-admins closing RfDs as Delete. If TfDs have been made an exception, RfDs can be too. Closing a heavily discussed nomination at RfD is more about the reading, analysis and thought process at arriving at the outcome, and less about the technicality of the subsequent page actions. It will help making non-admins mentally prepared to advance to admin roles. Jay 💬17:28, 1 January 2025 (UTC)
It seems dumb to think that a close can go through DRV and 'pass' only for it to be vacated because the closer didn't have the right credentials. If the close is found to be good, does it matter who closed it? If bad Delete closes by non-admins were regular occurrences, then maybe, but I don't imagine this is the case. Cessaune19:12, 1 January 2025 (UTC)
The only problem is that if it becomes a regular occurrence, it creates more work overall. An admin can delete and carry out the delete. A non-admin can say it needs to be deleted, but still needs an admin to carry out the delete. That's why this should be discouraged - if it becomes commonplace it will generate a lot more work, but a one-off can clearly be endorsed at DRV. SportingFlyerT·C19:26, 1 January 2025 (UTC)
I think it's time for the long-standing "it creates more work" argument to be retired. In the first scenario, person 1 does A and B. In the second scenario, person 1 does A and person 2 does B. That does not create more work overall, it's the same amount of work overall, and it reduces work for person 1. Splitting work between two people doesn't create more work. Levivich (talk) 14:55, 4 January 2025 (UTC)
If person 2 here did B without doing any additional work whatsoever, then person 2 shouldn't be able to do B. We expect admins to look at what they're deleting. Plus, you're creating additional work for persons 3-20, who are watching CAT:CSD and don't appreciate demands to go sanity-check low-urgency, possibly-complex closes at unfamiliar deletion venues mixed into the copyright infringement, spam, and attack pages they're trying to prioritize. —Cryptic15:15, 4 January 2025 (UTC)
Discussion of How Much Attention Admins Pay to What They Are Deleting
No, we don't expect admins to look at what they're deleting. Anyone familiar with the admin deletion stats (as you are) knows that every day, admins delete many pages without ever looking at them. Person 2 can do B without A. It's OK for person 2 to rely on person 1 to do A correctly. It's not true that in order for person 2 to do B then person 2 must also have done A, and it's not how we operate with other deletions. Non-admins are perfectly capable of closing RfCs and many other discussions; there is nothing about a deletion discussion that suddenly makes non-admins unable to summarize consensus. There is no reason an admin can't rely on a non-admins summary of consensus, just as admins rely on non-admins CSD tagging. Levivich (talk) 15:21, 4 January 2025 (UTC)
We absolutely do expect admins to look at what they're deleting. At most a NAC delete close can save an admin the trouble of writing the close themself, but if an admin is blindly deleting without verifying that the CSD tag is actually valid for CSD then sooner or later they're going to wind up at WP:ANI. Anomie⚔15:49, 4 January 2025 (UTC)
Levivich, I agree with your conclusion, but not with your analogy. As Anomie pointed out, we do not blindly delete pages tagged as CSD. WP:CSD specifically instructs us to verify that the page meets a speedy deletion criterion, rather than just appeared as such to one user. This is a very different situation to an AfD that garnered consensus among multiple editors over the course of at least seven days, where the admin's job is just to verify that the NAC read consensus correctly. Owen×☎16:01, 4 January 2025 (UTC)
We can say it all we want but we can't argue with WP:ADMINSTATS. The admin who has deleted over 1 million pages did not read 1 million pages. Nor did the admin who deleted 800,000 pages read 800,000 pages. An admin who has deleted 600,000 pages--no doubt without reading even half of them--just got elected to arbcom. Nobody is taking those admins to ANI or thinks they're doing anything wrong (including me).
So no, admins don't read the pages they delete, and no, we don't expect them to, as proven by the massive number of deletions, and no, admins who delete without reading aren't taken to ANI, they're promoted. This includes CSDs.
More broadly, there is no reason not to allow admins to rely on non-admin XfD closures when making deletion decisions. We already do this for multiple types of XfDs, we can and should do it for AfDs. Levivich (talk) 16:05, 4 January 2025 (UTC)
Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD. He had to review almost a million XfD discussions to make sure consensus was to delete, which is exactly what he does when closing. And the majority of CSD deletions are of clumsy, unsourced self-promotion pages that take less than ten seconds to assess and confirm as such. I know for a fact that Liz -- number #3 on that list -- carefully reviews every speedy-tagged page before deleting it, and routinely rejects such requests when they do not meet CSD. Levivich, you are making some serious accusations here, with zero evidence to support them. I don't think this will help your case here. Owen×☎16:24, 4 January 2025 (UTC)
I have no case here and I'm making no accusations. If you want to believe that a person has read over a million XfDs, you go ahead and believe that. I don't, because even over 15 years, that would be 182 XfDs a day every day with no days off, and I don't believe anyone does, or is capable of doing, that much XfD reading. Levivich (talk) 17:03, 4 January 2025 (UTC)
Levivich You're completely wrong, because you're missing a number of very obvious issues with those statistics.
Not even a majority of Explicit's deletions are XfDs - most are speedies
Many are G13 deletions, which don't need any analysis, they're simply done on timeframe. You can do those in seconds. Similarly U1, R2 and F8
Most articles have a talk page, which also needs to be deleted (G8), so deleting most articles means two deletions.
RfDs don't take very long to close at all; most are unanimous
Of Explicit's last 500 deletions, only 58 have been XfDs (and their associated talk pages where they existed, making 97 deletions).
The vast majority of the rest have been G13, G8, U1, R2 and F8.
Owen: Explicit didn't have to read over one million pages, because most of those deletions were the result of an XfD, not a CSD
BK: Not even a majority of Explicit's deletions are XfDs - most are speedies
I don't know which one of you is wrong but it doesn't matter. Explicit did not read 1 million pages over the last 15 years prior to deleting them, whether they were XfDs or CSDs. Nobody is reading 182 Misplaced Pages pages 7 days a week for 15 years. Nobody has read a million Misplaced Pages pages. No human can thoroughly review 182 things a day. It's mathematics, guys. If a person spends 5 minutes on each review -- which isn't a thorough review of anything -- that's 15 hours per day to do 182 reviews. Nobody is spending that much time, 7 days a week, for 15 years. Even if the person spends just 1 minute, that's over 3 hours a day... every day for 15 years. The math proves that Explicit is spending maybe 1 minute per deletion.
Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page.
The math and the stats don't lie. The suggestion that admins carefully review every page before deleting them is plainly not true. The suggestion that if admins didn't do that, they'd be taken to ANI, is also plainly not true. We have admins spending a minute or less per deletion and not being taken to ANI. These are facts. Levivich (talk) 19:31, 4 January 2025 (UTC)
Your "math" is based on a lot of faulty assumptions and oversimplifications, which you seem to be persisting in despite others trying to correct you. Anomie⚔20:42, 4 January 2025 (UTC)
Those are not facts, because your data is faulty. Your reply simply tells me that you didn't read what I wrote. Someone with the editing pattern of Explicit isn't reviewing 182 things a day. Nowhere near that. Quite apart from the talk page issue (which, if every page had a talk page, would immediately halve the number of reviews) in some of the speedy categories I mention there's nothing to review; it's simply pressing a button. Indeed, deleting the articles in the stale G13 queue, orphaned G8 queue, or the F5 or F8 category, can result in dozens - even hundreds - of deletions in one button press. As an example, on the 3rd January alone, Explicit deleted 113 F8 images, plus 83 talk pages of those images. That's 196 deletions, all done in a few seconds, as there's nothing to review. In comparison, the number of XfDs he closed that day was 25. Black Kite (talk)21:21, 4 January 2025 (UTC)
Cryptic: We expect admins to look at what they're deleting.
BK: That's 196 deletions, all done in a few seconds, as there's nothing to review.
I disagreed with Cryptic's point, and thank you BK for providing an example of exactly what I'm talking about. We do not expect admins to review (or "look at") what they're deleting, sometimes there's not even anything to look at. Admins delete things without reviewing what they're deleting all the time, and they're not hauled off to ANI for it. BK, you're arguing with me, but you're not actually disagreeing with what I'm saying. You're not arguing, as others have said above, that all admins review everything they delete before they delete it, or that this is the community expectation. Levivich (talk) 22:24, 4 January 2025 (UTC)
I'm simply pointing out that the claim you have made The math proves that Explicit is spending maybe 1 minute per deletion. Now: an admin spending 1 minute per deletion is not providing any real kind of level of oversight that can't be provided by a non-admin closing the XfD and the admin then spending 1 minute reviewing the close and deleting the page. is not correct; Explicit is not spending 1 minute per XfD, he is spending 1 minute per deletion, and because in many cases the admin pressing the button is simply completing an automated process (in the case of G13, that the article has not been edited for six months; in the case of F8, that the identical file exists at Commons), and deleting many files in one button-press, that skews the data. Now, if you are saying that an admin is closing AfDs or deleting G7 or G11 speedies at a high rate (not just "deleting things"), and their speed suggests they aren't reviewing them carefully - then you have a point. Black Kite (talk)23:33, 4 January 2025 (UTC)
Not actually reviewing deletions to make sure they were correct was one of the two major factors that resulted in Arbcom desysopping RHaworth (the other was a refusal to engage with good-faith queries about his actions and refusing to engage at all with IP editors). As others have said, how long it takes to ensure that what you are deleting should be deleted varies considerably. For G13s it's as simple as checking that bot has correctly determined that a given timestamp was more than 6 months ago - either the entire batch will be correct or the entire batch will be incorrect. Most of the deletions I do are the result of RfDs, after determining that the consensus is to delete (which is usually very simple) I delete the page. The software then tells me that page has a talk page, at least 9 times out of 10 (maybe more) it takes less than a second to verify there isn't any any reason they are G8 exempt. There is no excuse for not doing the reviewing properly though because there are exceptions. Thryduulf (talk) 00:22, 5 January 2025 (UTC)
I didn't say Explicit is spending 1 minute per XfD, I said "per deletion." And your point about "many files in one button-press" is literally the same as my point, which is that admins don't carefully review every single thing they delete, they sometimes delete many files in one button press (196 deletions in a few seconds is an example). So, you agree with me that "we expect admins to look at what they're deleting" is not correct, it's actually disproven by the data. Levivich (talk) 00:37, 5 January 2025 (UTC)
Admins are expected to review everything they delete. It's just that in some cases many pages can be reviewed together very quickly. It is also possible to spend time carefully reviewing many pages in detail, assembling a list of which should be deleted and then deleting them the pages on that together with a single click. Thryduulf (talk) 01:08, 5 January 2025 (UTC)
It was in the context of XfDs, however ("If you want to believe that a person has read over a million XfDs, you go ahead and believe that"). Black Kite (talk)08:03, 5 January 2025 (UTC)
That was in response to someone saying they were mostly XfDs. The same point holds if they were mostly CSDs. That's why I said it doesn't matter whether they were mostly XfDs or CSDs. Regardless of whether it's XfD or CSD, when someone makes 500k or 1 million deletions, we know they didn't look at each and every individual thing (page, file, whatever) that was deleted, nor do we expect them to. (Which I said in response to people saying we expect admins to look at every single thing they delete.) Levivich (talk) 13:18, 5 January 2025 (UTC)
By pressing the delete button you are asserting that at least one of the following is true:
The page met the specified speedy deletion criterion (e.g. if the deletion log says G12 you are asserting the page, including all of its old revisions, was copyvio).
The page was eligible for PROD, this was the first time that it was prodded and nobody has objected to the prod.
The deletion of the page was discussed a the relevant XfD (or, exceptionally, in an RfC) and that the consensus of that discussion was to delete the page.
If an admin is not prepared to put their name to the truthfulness of that assertion then they should not be deleting the page. Thryduulf (talk) 16:12, 4 January 2025 (UTC)
My own opinion is that if it is necessary sometimes to allow a practice that is contrary to the guideline, the guideline should be revised, so as to reduce the load at DRV, but that is only my opinion - actually, Robert McClenon, your opinion is solidly anchored in policy. WP:NOTBURO tells us: the written rules themselves do not set accepted practice. Rather, they document already-existing community consensus regarding what should be accepted and what should be rejected. If CfD is working fine as it is, let's update policy to reflect the practice. Owen×☎16:09, 2 January 2025 (UTC)
Is there a guideline that says that unregistered editors (IP addresses) should not edit in Misplaced Pages space (project space)? We had am MFD discussion in which an unregistered editor asked a registered editor to nominate an essay for deletion. The registered editor did as requested, which I think is known as proxying. As I understand, unregistered editors cannot create new pages in either article space or project space, and an AFD or MFD discussion is its own page. The MFD was then closed as a Speedy Keep 1, because no rationale was given. The question has to do with a comment made by one of the MFD regular editors that IP editors should not edit in project space. Another editor questioned whether there was a guideline to that effect. I cannot recall having seen a guideline that restricts or discourages unregistered editors from editing in project space. Is there such a guideline? Robert McClenon (talk) 00:39, 1 January 2025 (UTC)
No, and anyone who claims there is can be safely disregarded as full of shit. (Not that it's the first time that people confidently claim false authority.) Gnomingstuff (talk) 08:11, 1 January 2025 (UTC)
Thank you. Three trouts were then in order. One to the unregistered editor, for not giving a reason for the deletion request. Two to the registered editor who was proxying, for making an MFD nomination without stating a reason. Three to the editor who said that IPs should stay out of project space. I think that the third editor would have had a case to argue that policy should be changed and the English Misplaced Pages should follow the Portuguese example of not permitting IP editing, but that is only my opinion and is an unrelated issue. Robert McClenon (talk) 16:30, 1 January 2025 (UTC)
Using AI to write your comments in a discussion makes it difficult for others to assume that you are discussing in good faith, rather than trying to use AI to argue someone into exhaustion (see example of someone using AI in their replies "Because I don't have time to argue with, in my humble opinion, stupid PHOQUING people"). More fundamentally, WP:AGF can't apply to the AI itself as AI lacks intentionality, and it is difficult for editors to assess how much of an AI-generated comment reflects the training of the AI vs. the actual thoughts of the editor.
No. As with all the other concurrent discussions (how many times do we actually need to discuss the exact same FUD and scaremongering?) the problem is not AI, but rather inappropriate use of AI. What we need to do is to (better) explain what we actually want to see in discussions, not vaguely defined bans of swathes of technology that, used properly, can aid communication. Thryduulf (talk) 01:23, 2 January 2025 (UTC)
Note that this topic is discussing using AI to generate replies, as opposed to using it as an aid (e.g. asking it to edit for grammar, or conciseness). As the above concurrent discussion demonstrates, users are already using AI to generate their replies in AfD, so it isn't scaremongering but an actual issue.
WP:DGF also does not ban anything ("Showing good faith is not required"), but offers general advice on demonstrating good faith. So it seems like the most relevant place to include mention of the community's concerns regarding AI-generated comments, without outright banning anything. Photos of Japan (talk) 01:32, 2 January 2025 (UTC)
And as pointed out, multiple times in those discussions, different people understand different things from the phrase "AI-generated". The community's concern is not AI-generated comments, but comments that do not clearly and constructively contribute to a discussion - some such comments are AI-generated, some are not. This proposal would, just as all the other related ones, cause actual harm when editors falsely accuse others of using AI (and this will happen). Thryduulf (talk) 02:34, 2 January 2025 (UTC)
Nobody signed up to argue with bots here. If you're pasting someone else's comment into a prompt and asking the chatbot to argue against that comment and just posting it in here, that's a real problema and absolutely should not be acceptable. :bloodofox: (talk) 03:31, 2 January 2025 (UTC)
Thank you for the assumption of bad faith and demonstrating one of my points about the harm caused. Nobody is forcing you to engage with bad-faith comments, but whether something is or is not bad faith needs to be determined by its content not by its method of generation. Simply using an AI demonstrates neither good faith nor bad faith. Thryduulf (talk) 04:36, 2 January 2025 (UTC)
I don't see why we have any particular to reason to suspect a respected and trustworthy editor of using AI. Cremastra (u — c) 14:31, 2 January 2025 (UTC)
I'm one of those people who clarified the difference between AI-generated vs. edited, and such a difference could be made explicit with a note. Editors are already accusing others of using AI. Could you clarify how you think addressing AI in WP:DGF would cause actual harm? Photos of Japan (talk) 04:29, 2 January 2025 (UTC)
By encouraging editors to accuse others of using AI, by encouraging editors to dismiss or ignore comments because they suspect that they are AI-generated rather than engaging with them. @Bloodofox has already encouraged others to ignore my arguments in this discussion because they suspect I might be using an LLM and/or be a bot (for the record I'm neither). Thryduulf (talk) 04:33, 2 January 2025 (UTC)
Given your relentlessly pro-AI comments here, it seems that you'd be A-OK with just chatting with a group of chatbots here — or leaving the discussion to them. However, most of us clearly are not. In fact, I would immediately tell someone to get lost were it confirmed that indeed that is what is happening. I'm a human being and find the notion of wasting my time with chatbots on Misplaced Pages to be incredibly insulting and offensive. :bloodofox: (talk) 04:38, 2 January 2025 (UTC)
My comments are neither pro-AI nor anti-AI, indeed it seems that you have not understood pretty much anything I'm saying. Thryduulf (talk) 04:43, 2 January 2025 (UTC)
Funny, you've done nothing here but argue for more generative AI on the site and now you seem to be arguing to let chatbots run rampant on it while mocking anyone who doesn't want to interface with chatbots on Misplaced Pages. Hey, why not just sell the site to Meta, am I right? :bloodofox: (talk) 04:53, 2 January 2025 (UTC)
I haven't been arguing for more generative AI on the site. I've been arguing against banning it on the grounds that such a ban would be unclear, unenforceable, wouldn't solve any problems (largely because whether something is AI or not is completely irrelevant to the matter at hand) but would instead cause harm. Some of the issues identified are actual problems, but AI is not the cause of them and banning AI won't fix them.
I'm not mocking anybody, nor am I advocating to let chatbots run rampant. I'm utterly confused why you think I might advocate for selling Misplaced Pages to Meta (or anyone else for that matter)? Are you actually reading anything I'm writing? You clearly are not understanding it. Thryduulf (talk) 05:01, 2 January 2025 (UTC)
So we're now in 'everyone else is the problem, not me!' territory now? Perhaps try communicating in a different way because your responses here are looking very much like the typical AI apologetics one can encounter on just about any contemporary LinkedIn thread from your typical FAANG employee. :bloodofox: (talk) 05:13, 2 January 2025 (UTC)
No, this is not a everyone else is the problem, not me issue because most other people appear to be able to understand my arguments and respond to them appropriately. Not everybody agrees with them, but that's not an issue.
I'm not familiar with Linkedin threads (I don't use that platform) nor what a "FAANG employee" is (I've literally never heard the term before now) so I have no idea whether your characterisation is a compliment or a personal attack, but given your comments towards me and others you disagree with elsewhere I suspect it's closer to the latter.
AI is a tool. Just like any other tool it can be used in good faith or in bad faith, it can be used well and it can be used badly, it can be used in appropriate situations and it can be used in inappropriate situations, the results of using the tool can be good and the results of using the tool can be bad. Banning the tool inevitably bans the good results as well as the bad results but doesn't address the reasons why the results were good or bad and so does not resolve the actual issue that led to the bad outcomes. Thryduulf (talk) 12:09, 2 January 2025 (UTC)
In the context of generating comments to other users though, AI is much easier to use for bad faith than for good faith. LLMs don't understand Misplaced Pages's policies and norms, and so are hard to utilize to generate posts that productively address them. By contrast, bad actors can easily use LLMs to make low quality posts to waste people's time or wear them down.
In the context of generating images, or text for articles, it's easy to see how the vast majority of users using AI for those purposes is acting in good faith as these are generally constructive tasks, and most people making bad faith changes to articles are either obvious vandals who won't bother to use AI because they'll be reverted soon anyways, or trying to be subtle (povpushers) in which case they tend to want to carefully write their own text into the article.
It's true that AI "is just a tool", but when that tool is much easier to use for bad faith purposes (in the context of discussions) then it raises suspicions about why people are using it. Photos of Japan (talk) 22:44, 2 January 2025 (UTC)
Not really – I agree with Thryduulf's arguments on this one. Using AI to help tweak or summarize or "enhance" replies is of course not bad faith – the person is trying hard. Maybe English is their second language. Even for replies 100% AI-generated the user may be an ESL speaker struggling to remember the right words (I always forget 90% of my French vocabulary when writing anything in French, for example). In this case, I don't think we should make a blanket assumption that using AI to generate comments is not showing good faith. Cremastra (u — c) 02:35, 2 January 2025 (UTC)
Yes because generating walls of text is not good faith. People "touching up" their comments is also bad (for starters, if you lack the English competency to write your statements in the first place, you probably lack the competency to tell if your meaning has been preserved or not). Exactly what AGF should say needs work, but something needs to be said, and AGFDGF is a good place to do it. XOR'easter (talk) 02:56, 2 January 2025 (UTC)
Not all walls of text are generated by AI, not all AI generated comments are walls of text. Not everybody who uses AI to touch up their comments lacks the competencies you describe, not everybody who does lack those competencies uses AI. It is not always possible to tell which comments have been generated by AI and which have not. This proposal is not particularly relevant to the problems you describe. Thryduulf (talk) 03:01, 2 January 2025 (UTC)
Someone has to ask: Are you generating all of these pro-AI arguments using ChatGPT? It'd explain a lot. If so, I'll happily ignore any and all of your contributions, and I'd advise anyone else to do the same. We're not here to be flooded with LLM-derived responses. :bloodofox: (talk) 03:27, 2 January 2025 (UTC)
That you can't tell whether my comments are AI-generated or not is one of the fundamental problems with these proposals. For the record they aren't, nor are they pro-AI - they're simply anti throwing out babies with bathwater. Thryduulf (talk) 04:25, 2 January 2025 (UTC)
I'd say it also illustrates the serious danger: We can no longer be sure that we're even talking to other people here, which is probably the most notable shift in the history of Misplaced Pages. :bloodofox: (talk) 04:34, 2 January 2025 (UTC)
How is that a "serious danger"? If a comment makes a good point, why does it matter whether ti was AI generated or not? If it doesn't make a good point, why does it matter if it was AI generated or not? How will these proposals resolve that "danger"? How will they be enforceable? Thryduulf (talk) 04:39, 2 January 2025 (UTC)
Misplaced Pages is made for people, by people, and I like most people will be incredibly offended to find that we're just playing some kind of LLM pong with a chatbot of your choice. You can't be serious. :bloodofox: (talk) 04:40, 2 January 2025 (UTC)
"why does it matter if it was AI generated or not?"
Because it takes little effort to post a lengthy, low quality AI-generated post, and a lot of effort for human editors to write up replies debunking them.
"How will they be enforceable? "
WP:DGF isn't meant to be enforced. It's meant to explain to people how they can demonstrate good faith. Posting replies to people (who took the time to write them) that are obviously AI-generated harms the ability of those people to assume good faith. Photos of Japan (talk) 05:16, 2 January 2025 (UTC)
The linked "example of someone using AI in their replies" appears – to me – to be a non-AI-generated comment. I think I preferred the allegedly AI-generated comments from that user (example). The AI was at least superficially polite. WhatamIdoing (talk) 04:27, 2 January 2025 (UTC)
Obviously the person screaming in all caps that they use AI because they don't want to waste their time arguing is not using AI for that comment. Their first post calls for the article to be deleted for not "offering new insights or advancing scholarly understanding" and "merely" reiterating what other sources have written.
Yes, after a human had wasted their time explaining all the things wrong with its first post, then the bot was able to write a second post which looks ok. Except it only superficially looks ok, it doesn't actually accurately describe the articles. Photos of Japan (talk) 04:59, 2 January 2025 (UTC)
Multiple humans have demonstrated in these discussions that humans are equally capable of writing posts which superficially look OK but don't actually accurately relate to anything they are responding to. Thryduulf (talk) 05:03, 2 January 2025 (UTC)
But I can assume that everyone here is acting in good faith. I can't assume good faith in the globally-locked sock puppet spamming AfD discussions with low effort posts, whose bot is just saying whatever it can to argue for the deletion of political pages the editor doesn't like. Photos of Japan (talk) 05:09, 2 January 2025 (UTC)
True, but I think that has more to do with the "globally-locked sock puppet spamming AfD discussions" part than with the "some of it might be " part. WhatamIdoing (talk) 07:54, 2 January 2025 (UTC)
All of which was discovered because of my suspicions from their inhuman, and meaningless replies. "Reiteration isn't the problem; redundancy is," maybe sounds pithy in a vacuum, but this was written in reply to me stating that we aren't supposed to be doing OR but reiterating what the sources say.
"Your criticism feels overly prescriptive, as though you're evaluating this as an academic essay" also sounds good, until you realize that the bot is actually criticizing its own original post.
The fact that my suspicions about their good faith were ultimately validated only makes it even harder for me to assume good faith in users who sound like ChatGPT. Photos of Japan (talk) 08:33, 2 January 2025 (UTC)
I wonder if we need some other language here. I can understand feeling like this is a bad interaction. There's no sense that the person cares; there's no feeling like this is a true interaction. A contract lawyer would say that there's no meeting of the minds, and there can't be, because there's no mind in the AI, and the human copying from the AI doesn't seem to be interested in engaging their brain.
The user's talk page has a header at the top asking people not to template them because it is "impersonal and disrespectful", instead requesting "please take a moment to write a comment below in your own words"
Does this look like acting in good faith to you? Requesting other people write personalized responses to them while they respond with an LLM? Because it looks to me like they are trying to waste other people's time. Photos of Japan (talk) 09:35, 2 January 2025 (UTC)
"Being hypocritical" in the abstract isn't the problem, it's the fact that asking people to put effort into their comments, while putting in minimal effort into your own comments appears bad faith, especially when said person says they don't want to waste time writing comments to stupid people. The fact you are arguing AGF for this person is both astounding and disappointing. Photos of Japan (talk) 16:08, 3 January 2025 (UTC)
It feels like there is a lack of reciprocity in the interaction, even leaving aside the concern that the account is a block-evading sock.
But I wonder if you have read AGF recently. The first sentence is "Assuming good faith (AGF) means assuming that people are not deliberately trying to hurt Misplaced Pages, even when their actions are harmful."
So we've got some of this (e.g., harmful actions). But do you really believe this person woke up in the morning and decided "My main goal for today is to deliberately hurt Misplaced Pages. I might not be successful, but I sure am going to try hard to reach my goal"? WhatamIdoing (talk) 23:17, 4 January 2025 (UTC)
Trying to hurt Misplaced Pages doesn't mean they have to literally think "I am trying to hurt Misplaced Pages", it can mean a range of things, such as "I am trying to troll Wikipedians". A person who thinks a cabal of editors is guarding an article page, and that they need to harass them off the site, may think they are improving Misplaced Pages, but at the least I wouldn't say that they are acting in good faith. Photos of Japan (talk) 23:27, 4 January 2025 (UTC)
The issues with AI in discussions is not related to good faith, which is narrowly defined to intent. CMD (talk) 04:45, 2 January 2025 (UTC)
In my mind, they are related inasmuch as it is much more difficult for me to ascertain good faith if the words are eminently not written by the person I am speaking to in large part, but instead generated based on an unknown prompt in what is likely a small fraction of the expected time. To be frank, in many situations it is difficult to avoid the conclusion that the disparity in effort is being leveraged in something less than good faith. Remsense ‥ 论05:02, 2 January 2025 (UTC)
Assume good faith, don't ascertain! Llm use can be deeply unhelpful for discussions and the potential for mis-use is large, but the most recent discussion I've been involved with where I observed an llm post was responded to by an llm post, I believe both the users were doing this in good faith. CMD (talk) 05:07, 2 January 2025 (UTC)
All I mean to say is it should be licit that unhelpful LLM use should be something that can be mentioned like any other unhelpful rhetorical pattern. Remsense ‥ 论05:09, 2 January 2025 (UTC)
The fact that everyone (myself included) defending "LLM use" says "use" rather than "generated", is a pretty clear sign that no one really wants to communicate with someone using "LLM generated" comments. We can argue about bans (not being proposed here), how to know if someone is using LLM, the nuances of "LLM use", etc., but at the very least we should be able to agree that there are concerns with LLM generated replies, and if we can agree that there are concerns then we should be able to agree that somewhere in policy we should be able to find a place to express those concerns. Photos of Japan (talk) 05:38, 2 January 2025 (UTC)
For instance, I am OK with someone using a LLM to post a productive comment on a talk page. I am also OK with someone generating a reply with a LLM that is a productive comment to post to a talk page. I am not OK with someone generating text with an LLM to include in an article, and also not OK with someone using a LLM to contribute to an article.
Most people already assume good faith in those making productive contributions. In situations where good faith is more difficult to assume, would you trust someone who uses an LLM to generate all of their comments as much as someone who doesn't? Photos of Japan (talk) 09:11, 2 January 2025 (UTC)
Given that LLM-use is completely irrelevant to the faith in which a user contributes, yes. Of course what amount that actually is may be anywhere between completely and none. Thryduulf (talk) 11:59, 2 January 2025 (UTC)
LLM-use is relevant as it allows bad faith users to disrupt the encyclopedia with minimal effort. Such a user posted in this thread earlier, as well as started a disruptive thread here and posted here, all using AI. I had previously been involved in a debate with another sock puppet of theirs, but at that time they didn't use AI. Now it seems they are switching to using an LLM just to troll with minimal effort. Photos of Japan (talk) 21:44, 2 January 2025 (UTC)
LLMs are a tool that can be used by good and bad faith users alike. Using an LLM tells you nothing about whether a user is contributing in good or bad faith. If somebody is trolling they can be, and should be, blocked for trolling regardless of the specifics of how they are trolling. Thryduulf (talk) 21:56, 2 January 2025 (UTC)
A can of spray paint, a kitchen knife, etc., are tools that can be used for good or bad, but if you bring them some place where they have few good uses and many bad uses then people will be suspicious about why you brought them. You can't just assume that a tool in any context is equally harmless. Using AI to generate replies to other editors is more suspicious than using it to generate a picture exemplifying a fashion style, or a description of a physics concept. Photos of Japan (talk) 23:09, 2 January 2025 (UTC)
WP:AGF is not a death pact though. At times you should be suspicious. Do you think that if a user, who you already have suspicions of, is also using an LLM to generate their comments, that that doesn't have any effect on those suspicions? Photos of Japan (talk) 21:44, 2 January 2025 (UTC)
So… If you suspect that someone is not arguing in good faith… just stop engaging them. If they are creating walls of text but not making policy based arguments, they can be ignored. Resist the urge to respond to every comment… it isn’t necessary to “have the last word”. Blueboar (talk) 21:57, 2 January 2025 (UTC)
That they've been banned for disruption indicates we can do everything we need to do to deal with bad faith users of LLMs without assuming that everyone using an LLM is doing so in bad faith. Thryduulf (talk) 00:33, 3 January 2025 (UTC)
I don't believe we should assume everyone using an LLM is doing so in bad faith, so I'm glad you think my comment indicates what I believe. Photos of Japan (talk) 01:09, 3 January 2025 (UTC)
No -- whatever you think of LLMs, the reason they are so popular is that the people who use them earnestly believe they are useful. Claiming otherwise is divorced from reality. Even people who add hallucinated bullshit to articles are usually well-intentioned (if wrong). Gnomingstuff (talk) 06:17, 2 January 2025 (UTC)
Yes I find it incredibly rude for someone to procedurally generate text and then expect others to engage with it as if they were actually saying something themselves. Simonm223 (talk) 14:34, 2 January 2025 (UTC)
Yes, mention that use of an LLM should be disclosed and that failure to do so is like not telling someone you are taping the call. Selfstudier (talk) 14:43, 2 January 2025 (UTC)
I could support general advice that if you're using machine translation or an LLM to help you write your comments, it can be helpful to mention this in the message. The tone to take, though, should be "so people won't be mad at you if it screwed up the comment" instead of "because you're an immoral and possibly criminal person if you do this". WhatamIdoing (talk) 07:57, 3 January 2025 (UTC)
No. When someone publishes something under their own name, they are incorporating it as their own statement. Plagiarism from an AI or elsewhere is irrelevant to whether they are engaging in good faith. lethargilistic (talk) 17:29, 2 January 2025 (UTC)
Comment LLMs know a few tricks about logical fallacies and some general ways of arguing (rhetoric), but they are incredibly dumb at understanding the rules of Misplaced Pages. You can usually tell this because it looks like incredibly slick and professional prose, but somehow it cannot get even the simplest points about the policies and guidelines of Misplaced Pages. I would indef such users for lacking WP:CIR. tgeorgescu (talk) 17:39, 2 January 2025 (UTC)
That guideline states "Sanctions such as blocks and bans are always considered a last resort where all other avenues of correcting problems have been tried and have failed." Gnomingstuff (talk) 19:44, 2 January 2025 (UTC)
I blocked that user as NOTHERE a few minutes ago after seeing them (using ChatGPT) make suggestions for text to live pagespace while their previous bad behaviors were under discussion. AGF is not a suicide pact. BusterD (talk) 20:56, 2 January 2025 (UTC)
Yes Using a 3rd party service to contribute to the Misplaced Pages on your behalf is clearly bad-faith, analogous to paying someone to write your article. Zaathras (talk) 14:39, 3 January 2025 (UTC)
Its a stretch to say that a newbie writing a comment using AI is automatically acting in bad faith and not here to build an encyclopedia. PackMecEng (talk) 16:55, 3 January 2025 (UTC)
Comment Large language model AI like Chat GPT are in their infancy. The culture hasn't finished its initial reaction to them yet. I suggest that any proposal made here have an automatic expiration/required rediscussion date two years after closing. Darkfrog24 (talk) 22:42, 3 January 2025 (UTC)
No – It is a matter of how you use AI. I use Google translate to add trans-title parameters to citations, but I am careful to check for Google's output making for good English as well as reflecting the foreign title when it is a language I somewhat understand. I like to think that I am careful, and I do not pretend to be fluent in a language I am not familiar with, although I usually don't announce the source of such a translation. If an editor uses AI profligately and without understanding the material generated, then that is the sin; not AI itself. Dhtwiki (talk) 05:04, 5 January 2025 (UTC)
There's a legal phrase, "when the exception swallows the rule", and I think we might be headed there with the recent LLM/AI discussions.
We start off by saying "Let's completely ban it!" Then in discussion we add "Oh, except for this very reasonable thing... and that reasonable thing... and nobody actually meant this other reasonable thing..."
Do you want us to reply to you, because you are a human? Or are you just posting the output of an LLM without bothering to read anything yourself? DS (talk) 06:08, 7 January 2025 (UTC)
Most likely you would reply because someone posted a valid comment and you are assuming they are acting in good faith and taking responsibility for what they post. To assume otherwise is kind of weird and not inline with general Misplaced Pages values. PackMecEng (talk) 15:19, 8 January 2025 (UTC)
No The OP seems to misunderstand WP:DGF which is not aimed at weak editors but instead exhorts stronger editors to lead by example. That section already seems to overload the primary point of WP:AGF and adding mention of AI would be quite inappropriate per WP:CREEP. Andrew🐉(talk) 23:11, 5 January 2025 (UTC)
Yes. AI use is not a demonstration of bad faith (in any case not every new good-faith editor is familiar with our AI policies), but it is equally not a "demonstration of good faith", which is what the WP:DGF section is about.
It seems some editors are missing the point and !voting as if every edit is either a demonstration of good faith or bad faith. Most interactions are neutral and so is most AI use, but I find it hard to imagine a situation where AI use would point away from unfamiliarity and incompetence (in the CIR sense), and it often (unintentionally) leads to a presumption of laziness and open disinterest. It makes perfect sense to recommend against it. DaßWölf22:56, 9 January 2025 (UTC)
Yes. Per Dass Wolf, though I would say passing off a completely AI-generated comment as your own anywhere is inherently bad-faith and one doesn't need to know Wiki policies to understand that. JoelleJay (talk) 23:30, 9 January 2025 (UTC)
Yes. Sure, LLMs may have utility somewhere, and it might be a crutch for people unfamiliar with English, but as I've said above in the other AI RfC, that's a competence issue. This is about comments eating up editor time, energy, about LLMs easily being used to ram through changes and poke at editors in good standing. I don't see a case wherein a prospective editor's command of policy and language is good enough to discuss with other editors while being bad enough to require LLM use. Iseulttalk to me01:26, 10 January 2025 (UTC)
No - anyone using a washing machine to wash their clothes must be evil and inherently lazy. They cannot be trusted. ... Oh, sorry, wrong century. Regards, --Goldsztajn (talk) 01:31, 10 January 2025 (UTC)
Edit quality in Android application
Several contributors, including myself, don't understand the point of the ‘edit quality’ mention in the Android application.
The mw:Wikimedia Apps/Android FAQ states that edit quality is ‘based on how many of your edits were reverted’. Is this the only criterion used? If so, calling it ‘edit quality’ is presumptuous, not to say irresponsible, given that there should be so many criteria. What are the different levels of judgement: excellent, good, bad, horrible, etc. ? What does this mean for developers, bots, patrollers and administrators? Whatever the case, the consequences of such a statement could be quite serious.
It's clear that the choice to keep this mention in the application doesn't just concern the application developers or even a small team, but all Misplaced Pages contributors, whatever their language. So we think it's important that you answer our questions. (As my English isn't very good, could you answer me in basic English, or at least without figures of speech? Thank you in advance.) Abalg (talk) 13:12, 7 January 2025 (UTC)
Hi Albag. I agree with the core of your message. But I don't get why you have been redirected to English Village Pump. This should be discussed somewhere on Meta or Mediawiki wiki, as it's relevant for all Misplaced Pages communities, not only the English one. (You and I are from fr-wp.) Best, — Jules*13:28, 7 January 2025 (UTC)
While I have no issue with the direction the linked discussion has taken, I agree with almost every contributor there: As a practice I have zero interest in generally allowing random editors closing outside their permissions. It might make DRV a more chatty board, granted. BusterD (talk) 15:02, 7 January 2025 (UTC)
Tamzin makes a reasonable case in their comment below. When we have already chosen to trust certain editors with advanced permissions, we might allow those folks to utilize them as fully as accepted practice allows. Those humans already have skin in the game. They are unlikely to act rashly. BusterD (talk) 19:32, 7 January 2025 (UTC)
To me, non-admin delete closes at any XfD have always seemed inconsistent with what we say about how adminship and discussion closing work. I would be in violation of admin policy if I deleted based on someone else's close without conducting a full review myself, in which case, what was the point of their close? It's entirely redundant to my own work. That said, I can't really articulate a reason that this should be allowed at some XfDs but not others, and it seems to have gone fine at CfD and TfD. I guess call me neutral. What I'd be more open to is allowing page movers to do this. Page movers do have the tools to turn a bluelink red, so it doesn't create the same admin accountability issue if I'm just cleaning up the stray page left over from a page mover's use of a tool that they were duly granted and subject to their own accountability rules for. We could let them move a redirect to some other plausible title (this would violate WP:MOVEREDIRECT as currently written but I think I'd be okay with making this a canonical exception), and/or allow moving to some draftspace or userspace page and tagging for G6, as we do with {{db-moved}}. I'll note that when I was a non-admin pagemover, I did close a few things as delete where some edge case applied that let me effect the deletion using only suppressredirect, and no one ever objected. -- Tamzin (they|xe|🤷) 19:07, 7 January 2025 (UTC)
I see that I was sort of vague, which is consistent with the statement that I hinted at allowing non-admin delete closures. My main concern is that I would like to see our guidelines and our practice made consistent, either by changing the guidelines or changing the practice. It appears that there is a rough consensus emerging that non-admin delete closures should continue to be disallowed in RFD, but that CFD may be a special case. So what I am saying is that if, in practice, we allow non-admin Delete closures at CFD, the guideline should say something vague to that effect.
I also see that there is a consensus that DRV can endorse irregular non-admin closures, including irregular non-admin Delete closures. Specifically, it isn't necessary for DRV to vacate the closure for an uninvolved admin to close. A consensus at DRV, some of whose editors will be uninvolved admins, is at least as good a close as a normal close by an uninvolved admin.
Also, maybe we need clearer guidance about non-admin Keep closures of AFDs. I think that if an editor is not sure whether they have sufficient experience to be closing AFDs as Keep, they don't have enough experience. I think that the guidance is clear enough in saying that administrator accountability applies to non-admin closes, but maybe it needs to be further strengthened, because at DRV we sometimes deal with non-admin closes where the closer doesn't respond to inquiries, or is rude in response to them.
Also, maybe we need clearer guidance about non-admin No Consensus closures of AFDs. In particular, a close of No Consensus is a contentious closure, and should either be left to an admin, or should be Relisted.
As for I can't really articulate a reason that this should be allowed at some XfDs, the argument is that more work is needed to enact closures at TfD and CfD (namely orphaning templates and emptying/moving/merging categories). Those extra steps aren't present at RfD. At most, there are times when it's appropriate to unlink the redirect or add WP:RCATs but those are automated steps that WP:XFDC handles. From my limited experience at TfD and CfD though, it does seem that the extra work needed at closure does not compensate for the extra work from needing two people reviewing the closure (especially at CfD because a bot that handles the clean-up). Consistency has come up and I would much rather consistently disallow non-admin delete closures at all XfD venues. I know it's tempting for non-admins to think they're helping by enacting these closures but it's not fair for them to be spinning their wheels. As for moving redirects, that's even messier than deleting them. There's a reason that WP:MOVEREDIRECT advises not to move redirects except for limited cases when preserving history is important. --Tavix20:16, 7 January 2025 (UTC)
@Tamzin: I do have one objection to this point of redundancy, which you are quite familiar with. Here, an AfD was closed as "transwiki and delete", however, the admin who did the closure does not have the technical ability to transwiki pages to the English Wikibooks, meaning that I, who does, had to determine that the outcome was actually to transwiki rather than blindly accepting a request at b:WB:RFI. Then, I had to mark the pages for G6 deletion, that way an admin, in this case you, could determine that the page was ready to be deleted. Does this mean that that admin who closed the discussion shouldn't have closed it, since they only have the technical ability to delete, not transwiki? Could I have closed it, having the technical ability to transwiki, but not delete? Either way, someone else would have had to review it. Or, should only people who have importing rights on the target wiki and admin rights on the English Misplaced Pages be allowed to close discussions as "transwiki and delete"? JJPMaster (she/they) 12:04, 8 January 2025 (UTC)
I do support being explicit when a non-administrator can close a discussion as "delete" and I think that explicitly extending to RfD and CfD is appropriate. First, there can be a backlog in both of these areas and there are often few comments in each discussion (and there is usually not the same passion as in an AfD). Second, the delete close of a non-administrator is reviewed by an administrator before action is taken to delete the link, or category (a delete close is a two-step process, the writeup and the delete action, so in theory the administrators workload is reduced). Third, non-admins do face administrator accountability for their actions, and can be subject to sanction. Fourth, the community has a role in reviewing closing decisions at DRV, so there is already a process in place to check a unexperienced editor or poor close. Finally, with many, if not most discussions for deletion the outcome is largely straight forward. --Enos733 (talk) 20:01, 7 January 2025 (UTC)
There is currently no rule against non-admin delete closures as far as I know; the issue is the practical one that you don't have the ability to delete. However, I have made non-admin delete closures at AfD. This occurred when an admin deleted the article under consideration (usually for COPYVIO) without closing the related AfD. The closures were not controversial and there was no DRV. Hawkeye7(discuss)20:31, 7 January 2025 (UTC)
The situation you're referring to is an exception allowed per WP:NACD: If an administrator has deleted a page (including by speedy deletion) but neglected to close the discussion, anyone with a registered account may close the discussion provided that the administrator's name and deletion summary are included in the closing rationale. --Tavix20:37, 7 January 2025 (UTC)
Bad idea to allow, this sort of closure is just busy work, that imposes more work on the admin that then has to review the arguments, close and then delete. Graeme Bartlett (talk) 22:05, 7 January 2025 (UTC)
(1) As I've also noted in the other discussion, the deletion process guidelines at WP:NACD do say non-admins shouldn't do "delete" closures and do recognize exceptions for CfD and TfD. There isn't a current inconsistency there between guidelines and practice. (2) In circumstances where we do allow for non-admin "delete" closures, I would hope that the implementing admin isn't fully reviewing the discussion de novo before implementing, but rather giving deference to any reasonable closure. That's how it goes with requested move closers asking for technical help implementing a "moved" closure at WP:RM/TR (as noted at WP:RMNAC, the closure will "generally be respected by the administrator (or page mover)" but can be reverted by an admin if "clearly improper"). SilverLocust💬08:41, 9 January 2025 (UTC)
Comment - A couple things to note about the CFD process: It very much requires work by admins. The non-admin notes info about the close at WT:CFD/Working, and then an admin enters the info on the CFD/Working page (which is protected) so that the bot can perform the various actions. Remember that altering a category is potentially more labour intensive than merely editing or deleting a single page - every page in that category must be edited, and then the category deleted. (There are other technical things involved, like the mess that template transclusion can cause, but let's keep it simple.) So I wouldn't suggest that that process is very useful as a precedent for anything here. It was done at a time when there was a bit of a backlog at CfD, and this was a solution some found to address that. Also - since then, I think at least one of the regular non-admin closers there is now an admin. So there is that as well. - jc3709:14, 9 January 2025 (UTC)
If the expectation is that an admin needs to review the deletion discussion to ensure they agree with that outcome before deleting via G6, as multiple people here are suggesting, then I'm not sure this is worthwhile. However, I have had many admins delete pages I've tagged with G6, and I have been assuming that they only check that the discussion was indeed closed as delete, and trust the closer to be responsible for the correctness of it. This approach makes sense to me, because if a non-admin is competent to close and be responsible for any other outcome of a discussion, I don't see any compelling reason they can't be responsible for a delete outcome and close accordingly. —Compassionate72719:51, 9 January 2025 (UTC)
Placement of dynamic list template
Where does the template {{dynamic list}} actually go? It superficially looks like it should be a hatnote at the top of the article, but there are a great number (perhaps a majority) of dynamic list articles where the template is placed under the infobox and lead. I can't find anything in the MOS specifically addressing this. Anonymous21:44, 7 January 2025 (UTC)
In many cases, the template is neither at the very top nor within a section. Just to be clear, this placement is not correct? Anonymous22:25, 7 January 2025 (UTC)
That talk page has been checked by at least 100 registered editors during the last month, which makes it one of our better watched pages. WhatamIdoing (talk) 18:22, 9 January 2025 (UTC)
Apparently. :) Getting no response in 36 hours was surprising. The silence could mean "no objection" (since I'm not proposing a change, just a clarification that already used to be there), but since it's a policy page, it would be good to have something more tangible. Gamapamani (talk) 08:20, 10 January 2025 (UTC)
Does my name technically violate the promotional username policy?
Comment: It would appear Jimbo responded indirectly in a interview: 
Sm8900 (talk) 17:46, 24 December 2024 (UTC)
Facepalm). Not gonna link what I can't (quickly) verify!)) (As an aside, I think "afflicted with" can come across as a bit... charged? Just something to note.)
Done 
Pope Francis and Brigette Lundy-Paine
.jpg)
