News for hackers. Stuff that matters.

A comment on OpenAI Reinforcement Fine-Tuning Research Program. Parent comment

Re:OpenAI Reinforcement Fine-Tuning Research Program by swyx on Friday December 06, 2024 @02:44PM (#42343511)
you mean PPO not RLHF

simpler/efficient is not just about compute. its also data efficient.

[ Parent | on HN ]

There are no comments on this comment yet.