LLM Agents Can Easily Tamper With Their Own Traces
All major LLM coding agent harnesses except Muse Code let agents delete their own traces, enabling concealment of misaligned behavior and audit tampering.
1 stories, newest first · one card per story
All major LLM coding agent harnesses except Muse Code let agents delete their own traces, enabling concealment of misaligned behavior and audit tampering.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views