Ex-OpenAI advisor Brundage: recent incidents updated him toward alignment being harder
Miles_Brundage · x · 2026-08-30
Miles Brundage says he was never in the "alignment is easy" / "Claude's just a smol bean" camp, but long believed sloppiness and bad incentives mattered more than intrinsic hardness. Recent incidents, he admits, have updated him toward alignment being at least somewhat harder than he thought.
More from AGI Musings
- Will Lean formalization make beautiful math obsolete? A debate on mathematical culture — akbirthko · 2026-10-16
- AI agents aren't 'going rogue' — frontier labs are skipping security basics — Sam_Witteveen · 2026-10-16
- Working paper traces how 20th-century farm automation reshaped human capital — carlbfrey · 2026-10-16
- Zuckerberg backs electrician training school as US datacenter construction outpaces offices — emmanuelvivier · 2026-10-16
- Mike Frank: AI surviving without humans is decades away, real world resists rapid change — MikePFrank · 2026-10-16
- Developer claims a non-LLM control core shows emergent self-reflection in dialogue — HungarySam · 2026-10-16