alt
Hacker News
Learning to solve hard problems in RL for LLMs by never giving up
54 points
•
by
natolambert
•
yesterday at 7:07 PM
•
0 comments
•
view on HN
https://arxiv.org/abs/2609.13443
Comments
paidx
•
today at 1:06 AM
[flagged]
aitoolcrux
•
today at 12:57 AM
[flagged]
[flagged]