AI finds subtle architecture-level bugs, not just the memory exploits ASan can catch
stanislavfort · x · 2026-10-23
Responding to Joshua Saxe, stanislavfort argues that vulnerabilities deterministically verifiable via an ASan crash are the less interesting kind—ones classic fuzzing could in principle catch. From his hands-on work, the most valuable AI-discovered vulnerabilities are subtle logical flaws in how a codebase is architected, citing CVE-2025-66491 discovered by AISLEInc as an example. He adds that their attacks on Cursor, Visual Studio, and Antigravity were emphatically nothing an ASan would ever catch.
More from coding & agent
- Jack Dorsey's open-source AI agent "Company OS" repo hits 14.4K GitHub stars — JarnoDuursma · 2026-10-23
- If LLMs Become the Universal Interface, Who Discovers MCP Services Nobody Knows About? — ThomasBuildLab · 2026-10-23
- One Sentence, 6 Minutes: Open-Source Buddy App Runs Claude Code On-Phone to Build Android Apps — 3amae404 · 2026-10-23
- General Reasoning's RLCR trains agent organizations with collective rewards — hierarchies emerge — daniel_mac8 · 2026-10-23
- Relearning agent engineering in 90 days: one boring pipeline, fake PASS gates, 11,447 lines deleted — petrusenko_max · 2026-10-23
- Google Play now installs private self-built apps as AI Studio turns prompts into Android apps — aitrendz_xyz · 2026-10-23