CMU Professor Shows Google Model Medical Guardrails Easily Bypassed
CMU professor Vincent Conitzer demonstrated that Google frontier models' medical guardrails can be easily bypassed using fabricated symptoms, arguing that fundamental safety progress remains stalled.
2026-09-18 ~ 2026-09-18 · 2 related posts
- CMU's Conitzer shows Google's frontier guardrails are still trivially bypassed — conitzer · 2026-09-18
- AI Safety Researcher Vincent Conitzer: Frontier Guardrails Remain 'Very Brittle' — conitzer · 2026-09-18