activity
20122024
most citedRaiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces

53 citations · 170 across the 8 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024★ 9 cited

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Carson Denison, Monte MacDiarmid, Fazl Barez +11

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming c…