Cryptographer Condemns Frontier Labs for Ignoring Encrypted CoT Extraction Vulnerability
matthew_d_green · x · 2026-08-11
Prominent cryptographer Matthew Green commented on the recent Stolen Thoughts paper, noting that based on its responsible disclosure section, frontier model providers actually cared about the vulnerability but chose not to acknowledge it. He labeled this behavior from the labs as "pretty 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