Reinforcement Learning from Human Feedback

▲

95 points byonurkanbkrc9 hours ago |4 comments

▲dang4 hours ago

Related. Others?

▲verdverm7 hours ago

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

▲leggerss5 hours ago

You could say he's also learning from human feedback

▲klelatti8 hours ago

Web version with links, etc:

▲dang4 hours ago

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