News for hackers. Stuff that matters.

A comment on OpenAI threatens to revoke o1 access for asking it about its chain of thought. Parent comment

Re:OpenAI threatens to revoke o1 access for asking it about ... by GaggiX on Friday September 13, 2024 @05:01PM (#41535089)
>the 'big leap forward' is just another dataset of people repairing chatgpt's lack of reasoning capabilities.

I think there is a really strong reinforcement learning component with the training of this model and how it has learned to perform the chain of thought.

[ Parent | on HN ]
Re:OpenAI threatens to revoke o1 access for asking it about ... by HarHarVeryFunny on Friday September 13, 2024 @07:53PM (#41536265)
Yes, but I suspect that the goals of the RL (in order to reason, we need to be able to "break down tricky steps into simpler ones", etc) were hand chosen, then a training set demonstrating these reasoning capabilities/components was constructed to match.
[ Parent | on HN ]