OpenAI / @OpenAI (RSS Feed) on Nostr: We trained an AI using process supervision — rewarding the thought process rather ...

We trained an AI using process supervision — rewarding the thought process rather than the outcome — to achieve new state-of-art in mathematical reasoning. Encouraging sign for alignment of advanced AIs: …openai.com/research/improvin… (https://openai.com/research/improving-mathematical-reasoning-with-process-supervision)

https://nitter.moomoo.me/OpenAI/status/1663957407184347136#m