Agent Systems and Evaluation
Series · 1 posts
-
Can LLM Agents Tamper With Their Own Traces? Who Controls the Evidence Boundary
IntermediateA close reading of arXiv v1: ten local coding-agent harness pairs, four controlled routes to trace tampering, and the distinct evidentiary roles of native traces, an external file observer, and tool-effect records.
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