CoT Monitoring and Plan Injection
Series · 1 posts
-
Corrupt Plans, Clean Traces: How Plan Injection Evades Chain-of-Thought Monitoring
Advanced Agent runtime, safety, and evaluationA deep reading of Plan Injection: when an adversarial plan enters context and an actor rewrites it into plausible Chain-of-Thought, why the monitor’s clean trace can disconnect from behavioral causality, and where APPS, Bio-Math, and budget-sweep evidence stops.
Understand it in 90 seconds
For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.
Speaking & contact