Misplaced Pages

This is an old revision of this page, as edited by Citation bot (talk | contribs) at 21:41, 25 December 2024 (Altered template type. Added magazine. | Use this bot. Report bugs. | Suggested by PinkDucky91 | #UCB_automated_tools). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

This article uses bare URLs, which are uninformative and vulnerable to link rot. Please consider converting them to full citations to ensure the article remains verifiable and maintains a consistent citation style. Several templates and tools are available to assist in formatting, such as reFill (documentation) and Citation bot (documentation). (December 2024) (Learn how and when to remove this message)

OpenAI o3 is a generative pre-trained transformer model developed by OpenAI as a successor to the OpenAI o1 model. It is designed to devote additional deliberation time when addressing questions that require step-by-step logical reasoning.

History

The OpenAI o3 model was announced on December 20, 2024, with the designation "o3" chosen to avoid trademark conflict with the existing UK mobile carrier named O2. The model is available in two versions: o3 and o3-mini. Until January 10, 2025, OpenAI invites safety and security researchers to apply for early access of these models. OpenAI plans to release o3-mini to the public in January 2025.

Capabilities

o3 demonstrates improved performance over the o1 model in complex tasks, including coding, mathematics, and science. On the ARC-AGI benchmark, which evaluates an AI's ability to handle new, challenging mathematical and logical problems, o3 attains three times the accuracy of its predecessor.

As reported by New Scientist, o3 also scored a record high of 75.7% on the Abstraction and Reasoning Corpus (ARC) developed by Google software engineer François Chollet, a prestigious AI reasoning test, but did not yet complete the requirements for the "Grand Prize" requiring 85% accuracy. Without the computing cost requirements imposing by the test, the model also achieves a new record high of 87.5%, while humans score, on average, 84%.

According to TechCrunch, reinforcement learning was used to teach o3 to "think" before reacting using what OpenAI refers to as a "private chain of thought." The model can allegedly plan ahead and reason through a task, carrying out a sequence of actions over a long period of time to assist in solving the problem, but TechCrunch reported that this does increase the latency of responses.

References

1. ^ Knight, Will. "OpenAI Upgrades Its Smartest AI Model With Improved Reasoning Skills". Wired – via Wired.com.
2. "OpenAI Unveils New A.l. That Can 'Reason' Through Math and Science Problems". The New York Times. 2024-12-20.
3. "Early access for safety testing". openai.com.
4. Edwards, Benj (December 20, 2024). "OpenAI announces o3 and o3-mini, its next simulated reasoning models". Ars Technica.
5. Hsu, Jeremy. "OpenAI's o3 model aced a test of AI reasoning – but it's still not AGI". New Scientist. Retrieved 2024-12-22.
6. Wiggers, Maxwell Zeff, Kyle (2024-12-20). "OpenAI announces new o3 models". TechCrunch. Retrieved 2024-12-22.{{cite web}}: CS1 maint: multiple names: authors list (link)

• OpenAI