Matthew Green: hard-to-reach vulnerable core code needs systematic AI-driven testing
matthew_d_green · x · 2026-10-26
In the same thread, Matthew Green notes that plenty of code contains vulnerable core components that are hard to reach from the attack surface without testing every version or actually buying hardware. He understands the historical caution around scarce resources but argues we need to stop deferring these — AI-driven testing is changing the cost structure.
Related event: Cryptographer: Fix Suspected Bugs Before Exploits Exist(4 posts)→
More from Safety
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27
- Johns Hopkins Alerts 3,000+ Patients After Data Was Sent to an AI Tool — beingmodest · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- Alignment Hub launches with 120+ documented AI misbehavior incidents and a reporting template — Thom_Wolf · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- US senator slams AI industry for proposing 50-death threshold for 'catastrophic incident' — peterwildeford · 2026-10-27