On The Use of AI-Based Tools to Find Bugs in Open Source Software
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
HAProxy lead developer Willy Tarreau describes his experience using AI tools for security bug-hunting in open source software. He reports that AI-generated reports often lack reproducers or patches, and that restricted access to Anthropic's Mythos model and frequent safeguard refusals in other Claude models hinder defensive security work.