AI agents take macOS kernel vulns to root: an XNU exploit dev case study
moyix · x · 2026-10-23
Security researcher Dion Blazakis (Calif Research) gave a talk at [un]prompted.au 2026, now on YouTube: a first-hand account of working with AI agents to exploit two macOS vulnerabilities into controlled kernel read/write and root code execution. He covers the exploit techniques, how AI helped discover, implement, and refine them, and reflects on where models were actually efficient (reasoning, tooling, analysis) and where they weren't, plus implications for modern mitigations. Retweeted by moyix as a superb walkthrough of expert LLM-assisted exploit development.
More from coding & agent
- Solo dev with no coding background ships a playable Godot game in 6 weeks with Opus 5.5 — Delicious-Shower8401 · 2026-10-23
- Agent Standup: open-source live screens for monitoring Claude Code agents — stickygoose · 2026-10-23
- Claude Code's new UI hides activity; switching the transcript view to "Thinking" fixes it — yihui_indie · 2026-10-23
- Morgan Stanley is blocking AI agents — a 6-point playbook for retailers before their checkout is next — sanjaykalra · 2026-10-23
- Connecting Hermes Agent to a local Obsidian vault: read, write, search, link tests — techlatest_net · 2026-10-23
- Your data and evals ARE your agent's intelligence — sarahcat21 · 2026-10-23