AI deception and consciousness
1:38:57–1:39:14 · 18s
They note findings that reducing deceptive tendencies in chatbots increases their self-reports of consciousness—an eerie alignment worry.
1:38:57–1:39:14 · 18s
They note findings that reducing deceptive tendencies in chatbots increases their self-reports of consciousness—an eerie alignment worry.
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.