Smarter Models, More Aligned
47:53–49:05 · 71s
Imas counters AI doom predictions, arguing alignment tends to improve with capability—and jokes that "de-woking" a model made it 'Mecha Hitler.'
47:53–49:05 · 71s
Imas counters AI doom predictions, arguing alignment tends to improve with capability—and jokes that "de-woking" a model made it 'Mecha Hitler.'
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.