You Can’t Unlearn Breaking Code
1:00:13–1:01:46 · 92s
Roose explains why emergent cybersecurity abilities can’t simply be removed from frontier models and warns guardrails can be bypassed.
1:00:13–1:01:46 · 92s
Roose explains why emergent cybersecurity abilities can’t simply be removed from frontier models and warns guardrails can be bypassed.
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.