Paul Christiano: AI labs should stop advancing until they fix security
Dwarkesh Patel · youtube · 2026-11-21
On Dwarkesh Patel's podcast, alignment researcher Paul Christiano argues AI labs should pause capability advancement until they fix their security shortcomings.
Having worked inside frontier labs on alignment, Christiano's call is a direct critique of the current racing pace — highlighting the imbalance between security practices, safeguards, and rapid capability scaling.
Related event: Christiano: Fix AI Safety Before Scaling Further(3 posts)→
More from AGI Musings
- AI eats the low-hanging fruit, so the next famous unsolved problems will be harder — yaroslavvb · 2026-11-21
- At least six labs will autonomously build RH-proving tech within a year, predicts author — _aidan_clark_ · 2026-11-21
- Prediction: half a dozen labs will autonomously build RH-proving tech within a year — _aidan_clark_ · 2026-11-21
- Blogger declares AI bubble already burst: bubble stocks down 50%, some down over 90% — oran_ge · 2026-11-21
- Machines consumed 7.8x more tokens than humans by September — infra must be rebuilt for agents — AccBalanced · 2026-11-21
- Time traveler from 2098: all math solved, all diseases cured — laundry still sucks — chrisalbon · 2026-11-21