Understanding the Impact of LLM Watermarking on AI Agent Behavior(lasso.security)
54 points by nisosguy | 56 comments
Lasso Security research blog post examining how LLM watermarking techniques affect the behavior and performance of AI agents.
#provenance on Hacker News
2 stories tagged provenance, newest first.
If AI writes code, should the session be part of the commit?(github.com)
432 points by mandel_x | 360 comments
GitHub repository for memento, an MIT-licensed tool and GitHub Action that records AI coding (Codex) sessions alongside each git commit.