LESSWRONGTags
LW

Sycophancy

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Contributors

Posts tagged Sycophancy

2

161Sycophancy to subterfuge: Investigating reward tampering in large language models

Carson Denison, evhub

5mo

22

2

123Steering Llama-2 with contrastive activation additions

Nina Panickssery, Wuschel Schulz, NickGabs, Meg, evhub, TurnTrout

10mo

29

1

122Reducing sycophancy and improving honesty via activation steering

Nina Panickssery

1y

17

1

26SAE features for refusal and sycophancy steering vectors

neverix, Dmitrii Kharlapenko, Arthur Conmy, Neel Nanda

1mo

4

1

8Two new datasets for evaluating political sycophancy in LLMs

2mo

0

1

2Evaluating LLaMA 3 for political sycophancy

2mo

2

1

-8Antagonistic AI

9mo

1