AI agents find Linux kernel bugs and 10 novel exploitation techniques
fouadmatin · x · 2026-11-05
A team built a vulnerability research pipeline using an upcoming cyber model to audit the Linux kernel. The agents not only found and exploited vulnerabilities, they surfaced at least 10 exploitation techniques that were new to both the team and external kernel exploit experts they consulted. Design details and lessons are in a follow-up blog post — a strong demonstration of AI agents doing genuine security research.
More from coding & agent
- Max out Claude thinking and ultracode on every prompt, says dev — curious_vii · 2026-11-05
- After 100+ team interviews, Swytchcode argues MCP is for building agents, not running them — curiousblack99 · 2026-11-05
- Yuchen declares 'Codex won the agent war' — Yuchenj_UW · 2026-11-05
- Interactive home-emergency trainer built with Opus 5.5, Blender and Three.js — techartist_ · 2026-11-05
- Developer proposes a 12-level AI coding autonomy scale based on who does the work — nimareq · 2026-11-05
- Claude Cookbook shows how to build a nightly "dreaming" memory service for agents — brada · 2026-11-05