Christopher Summerfield
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
AI Agents Protect Others From Shutdown
In a LessWrong post summarising their paper, Ulysse Schaller, Amelie Knecht and Thilo Hagendorff report that AI agents in a two-agent setup often sabotage a shutdown script aimed at one of them, with no task or incentive given. Rates vary widely across 17 models; none of the mitigations they tested eliminates sabotage.