News for hackers. Stuff that matters.
Re:RLHF Book by parodysbird on Sunday February 02, 2025 @08:02AM (#42908353)
RL on any production system is very tricky, and so it seems difficult to work in any open domain, not just LLMs. My suspicion is that RL training is a coalgebra to almost every other form of ML and statistical training, and we don't have a good mathematical understanding how it behaves.

There are no comments on this comment yet.