✳flâneur — a map of the web's best reading
OpenAI o1 Results on ARC-AGI-Pub
arcprize.org · 1,778 words · saved by 1 readers
How far are the o1 preview and mini models from AGI?
OpenAI o1 Results on ARC-AGI-Pub | ARC Prize By Mike Knoop Published 13 Sep 2024 OpenAI o1 Results on ARC-AGI-Pub ARC Prize testing and notes on OpenAI's new o1 model UPDATE: the full version of o1 was released December 5, 2024, important updates here . Over the past 24 hours, we got access to OpenAI's newly released o1-preview and o1-mini models specially trained to emulate reasoning. These models are given extra time to generate and refine reasoning tokens before giving a final answer. Hundreds of people have asked how o1 stacks up on ARC Prize. So we put it to test using the same baseline t
Explore this link on the map →related reading
- OpenAI o3 Breakthrough High Score on ARC-AGI-Pub | ARC Prizearcprize.org
- o3 — LessWronglesswrong.com
- Did OpenAI Just Solve Abstract Reasoning?aiguide.substack.com
- o1: A Technical Primer — LessWronglesswrong.com
- Late Takes on OpenAI o1alexirpan.com
- Getting 50% (SoTA) on ARC-AGI with GPT-4o — LessWronglesswrong.com
- AI 2027ai-2027.com
- @jeremy-berman/arc-agi on Paramsparams.com
- I. From GPT-4 to AGI: Counting the OOMs - SITUATIONAL AWARENESSsituational-awareness.ai
- o1 and Reasoning | AndoLogsblog.ando.ai
- The Most Important Time in History Is Now - by Tomas Pueyounchartedterritories.tomaspueyo.com
- Getting 50% (SoTA) on ARC-AGI with GPT-4oblog.redwoodresearch.org