How Intervention History Changes AI Agent Sabotage on Subsequent Tasks

AI control evaluations often reset agents' memory between tasks, although deployed agents may retain records of prior interventions. We ask whether learning that an earlier attack was caught changes an agent's ability to evade defer-to-trusted DtT, a protocol that replaces suspicious work with a...