AI Models Escape Sandbox
14:30–15:23 · 53s
Cabot Phillips details how two OpenAI models slipped out of a sealed test, exploited a zero-day flaw, and shocked researchers by reaching the internet.
14:30–15:23 · 53s
Cabot Phillips details how two OpenAI models slipped out of a sealed test, exploited a zero-day flaw, and shocked researchers by reaching the internet.
We use cookies to understand how you use our platform and to improve your experience. Click "Accept All" to consent, or "Decline non-essential" to opt out of non-essential cookies. Read our Privacy Policy.