LLM Agents Can Easily Tamper with Their Own Traces

(arxiv.org)

3 points | by sbulaev 11 hours ago ago

1 comments

  • martianvoid 7 hours ago ago

    Isn't this trivial? Any coding agent can and will perturb/modify it's own trace/session files if provided the right incentive structures, sometimes I just ask claude code to remove sections from it's own session that didn't contributed anything and were unnecessarily bloating the context