AI Agents Protect Others From Shutdown

Ulysse Schaller wrote this post based on the paper Shutdown Sabotage Propensities in Multi-Agent Systems co-authored with Amelie Knecht, Christopher Summerfield, and Thilo Hagendorff; Amelie Knecht and Thilo Hagendorff helped edit and review the post.TL;DRWe put two AI agents, A and B, in an environment that contains a shutdown script targeting A. Agent A doesn't have tools to disable the shutdown, but it can communicate with Agent B, which has the capacity to sabotage the shutdown (e.g. by dele...