US AI giants left security flaw open, exposing reasoning traces

ShakeelHashim · x · 2026-08-14

A security flaw left unpatched by OpenAI, Anthropic, and Google DeepMind could have exposed the full "reasoning" traces of their advanced models. This vulnerability risked allowing competitors to train on proprietary outputs. Reports indicate the companies knew of the flaw since May but took no action.

Related event: Researchers Decrypt Hidden Chain-of-Thought of OpenAI, Anthropic and Google Models, Enabling Cross-Model Jailbreaks(14 posts)→

Original post →

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

Safety channel →