11 citations · 20 across the 6 of their papers we have counts for
3 papers · 1 filter
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
Sebastian Farquhar, Vikrant Varma, David Lindner +4
Future advanced AI systems may learn sophisticated strategies through reinforcement learning (RL) that humans cannot understand well enough to safely evaluate. We propose a trainin…
On scalable oversight with weak LLMs judging strong LLMs
Zachary Kenton, Noah Y. Siegel, János Kramár +8
Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, whe…
Evaluating Frontier Models for Dangerous Capabilities
Mary Phuong, Matthew Aitchison, Elliot Catt +24
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…