Publications (6)
Combining Cost-Constrained Runtime Monitors for AI Safety
Tim Tian Hua, James Baskerville, Henri Lemoine +3
Monitoring AIs at runtime can help us detect and stop harmful actions. In this paper, we study how to efficiently combine multiple runtime monitors into a single monitoring protoco…
Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
Eric Gan, Aryan Bhatt, Buck Shlegeris +2
As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We in…
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
Jiaxin Wen, Vivek Hebbar, Caleb Larson +9
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previou…
LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
Tyler Tracy, Ram Potham, Nick Kuhn +31
We introduce LinuxArena, a control setting in which agents operate directly on live, multi-service production environments. LinuxArena contains 20 environments, 1,671 main tasks re…
BashArena: A Control Setting for Highly Privileged AI Agents
Adam Kaufman, James Lucassen, Tyler Tracy +2
Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The field of AI control…
Ctrl-Z: Controlling AI Agents via Resampling
Aryan Bhatt, Cody Rushing, Adam Kaufman +5
Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first contr…