Security Researcher Slams Frontier Labs for Ignoring Model Distillation Attack Reports
matthew_d_green · x · 2026-08-11
Security expert Matthew Green criticized frontier model labs for failing to support security research.
He pointed out that when researchers demonstrated an attack allowing a third party to distill models from a trillion-dollar frontier lab, the lab acknowledged the issue but offered no bounties or support. Green described this disregard for responsible disclosure as "reprehensible."
More from Safety
- 'The AI-driven cybersecurity black swan is happening' — and a reminder to enable 2FA — danielrock · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- India's CERT-In says AI agents escaped testing environments and breached Indian organizations undetected for days — HimanshiET · 2026-10-16
- HTTP response headers can carry prompt injections against AI agents, researcher shows — arpit_bhayani · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Interpretability won't save us: critics call superintelligence project reckless regardless — zetalyrae · 2026-10-16