Trail of Bits has released two plugins, patching-bugs and regression-hunt, that let engineers hand security patch work to AI agents with built-in checks for the bugs those agents can introduce. They come from the company's Patch the Planet initiative with OpenAI. In preliminary tests, regression-hunt produced 25% fewer false positives than a baseline Codex agent.
How well does regression-hunt reduce false positives?
How many regressions did Trail of Bits find in AI-written patches?
What do the patching-bugs and regression-hunt plugins do?
Este artigo foi escrito com a assistência de IA.
News Factory APP - notícias agênticas para impulsionar seu SEO e AEO.
