Learning to Reason with LLMs(openai.com)

1573 points by fofoz 2 years ago | 1186 comments

OpenAI research post introducing o1, a large language model trained with reinforcement learning to reason using a long internal chain of thought before answering.

SimpleQA(openai.com)

216 points by surprisetalk 2 years ago | 76 comments

OpenAI Reinforcement Fine-Tuning Research Program(openai.com)

218 points by marban 1 year ago | 53 comments

OpenAI O3-Mini(openai.com)

915 points by johnneville 1 year ago | 861 comments

OpenAI's announcement of o3-mini, a cost-efficient reasoning model available in ChatGPT and the API, strong in science, math, and coding.

OpenAI Grove(openai.com)

152 points by manveerc 1 year ago | 141 comments

New models and developer products(openai.com)

1081 points by kevin_hu 3 years ago | 521 comments

OpenAI blog post announcing new models and developer products at DevDay, including GPT-4 Turbo and the Assistants API.