HN2
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Reinforcement Learning from Human Feedback
(
rlhfbook.com
)
133 points
by
onurkanbkrc
28 days ago
|
hide
|
past
|
favorite
|
5 comments
https://arxiv.org/abs/2504.12501
verdverm
28 days ago
|
next
[–]
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
27 days ago
|
parent
|
next
[–]
You could say he's also learning from human feedback
dang
27 days ago
|
prev
|
next
[–]
Related. Others?
RLHF Book
-
https://hackertimes.com/item?id=42902936
- Feb 2025 (37 comments)
klelatti
28 days ago
|
prev
|
next
[–]
Web version with links, etc:
https://rlhfbook.com/
dang
27 days ago
|
parent
|
next
[–]
Thanks! We've switched to that above from
https://arxiv.org/abs/2504.12501
, and put the latter in the toptext.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: