AI Safety Researchers Rethink Control Narrative and Automated Alignment

Cambridge's David Krueger argued that deliberate scheming is only a small slice of AI existential risk, while a PIBBSS Symposium talk cautioned that automated alignment research cannot rely on simply halting AI when misbehavior is caught.

2026-11-06 ~ 2026-11-06 · 2 related posts

• David Krueger: intentional scheming is a small slice of AI x-risk, control research overfocused — JacquesThibs · 2026-11-06
• Automated alignment research needs a better plan than 'stop if we catch them' — JacquesThibs · 2026-11-06