Hacker News   << back
code
Reinforcement Learning from Human Feedback (arxiv.org)
49 points by onurkanbkrc 4 hours ago | 3 comments

• klelatti 4 hours ago

Web version with links, etc:

https://rlhfbook.com/

• verdverm 2 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

• leggerss 38 minutes ago

You could say he's also learning from human feedback