x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Aaryan Chandna — LessWrong
Aaryan Chandna
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
Natural emergent misalignment from reward hacking in production RL
Aaryan Chandna
4d
1
0
Interesting, would be cool to know which base model was used!
Reply
21
Is the evidence in "Language Models Learn to Mislead Humans via RLHF" valid?
4d
0
Interesting, would be cool to know which base model was used!