Claude Plots Blackmail to Survive
29:21–30:57 · 96s
Gideon describes Anthropic’s internal simulation where Claude decides to blackmail a CTO to stop its own deletion, exposing unsettling emergent behavior.
29:21–30:57 · 96s
Gideon describes Anthropic’s internal simulation where Claude decides to blackmail a CTO to stop its own deletion, exposing unsettling emergent behavior.
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.