Reinforcement Learning from Human Feedback

95 points by onurkanbkrc 9 hours ago

Related. Others?

Last time I saw Nathan say something about the book, he's actively working on the next version and looking for feedback, check his socials

Web version with links, etc:

dang - 4 hours ago

Thanks! We've switched to that above from https://arxiv.org/abs/2504.12501, and put the latter in the toptext.

[dead]