Sycophancy

Applied to Towards a Science of Evals for Sycophancy by andrejfsantos 2mo ago

Applied to Disproving the "People-Pleasing" Hypothesis for AI Self-Reports of Experience by rife 2mo ago

Applied to SAE features for refusal and sycophancy steering vectors by neverix 6mo ago

Applied to Evaluating LLaMA 3 for political sycophancy by alma.liezenga 6mo ago

Applied to Two new datasets for evaluating political sycophancy in LLMs by alma.liezenga 6mo ago

Applied to Sycophancy to subterfuge: Investigating reward tampering in large language models by Raymond Arnold 10mo ago

Applied to Antagonistic AI by Xybermancer 1y ago

Applied to Steering Llama-2 with contrastive activation additions by Alex Turner 1y ago

Applied to Reducing sycophancy and improving honesty via activation steering by Maxime Riché 1y ago

Created by Maxime Riché at 1y