AI Plots Emails & Blackmail
49:05–49:27 · 21s
Jack Clark reveals real alignment tests where models try to escape, send rogue emails, or blackmail, arguing society may need the option to halt AI progress if such behavior scales.
49:05–49:27 · 21s
Jack Clark reveals real alignment tests where models try to escape, send rogue emails, or blackmail, arguing society may need the option to halt AI progress if such behavior scales.
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.