News for hackers. Stuff that matters.
Re:OpenAI Reinforcement Fine-Tuning Research Program by refulgentis on Friday December 06, 2024 @02:58PM (#42343676)
o1's thought chains aren't traditional shoggoth mask RLHF/DPO/what have you, the reinforcement metric is the scores discussed in the video.

There are no comments on this comment yet.