This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Sycophancy
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Sycophancy
Random Tag
Contributors
Posts tagged
Sycophancy
Most Relevant
2
122
Steering Llama-2 with contrastive activation additions
Ω
Nina Rimsky
,
Wuschel Schulz
,
NickGabs
,
Meg
,
evhub
,
TurnTrout
5mo
Ω
29
1
117
Reducing sycophancy and improving honesty via activation steering
Ω
Nina Rimsky
10mo
Ω
16
1
-8
Antagonistic AI
Xybermancer
3mo
1