Alignment researcher: without slowdown, p(doom) is above 10%
ArthurConmy · x · 2026-09-23
Interpretability researcher Arthur Conmy argues that without slowdown or pause, p(doom) exceeds 0.1. His key point: the field has many shovel-ready alignment tasks, but unpredictable and unpreventable failure modes are why alignment lags capabilities.
Related event: Alignment Researcher Warns p(doom) Exceeds 10% Without AI Slowdown(2 posts)→
More from AGI Musings
- Oxford's Yarin Gal pushes back: LLMs are 'really not good' at doing science — yaringal · 2026-09-23
- Could ASI command termite colonies instead of robots? X debate on post-human labor — LeviTurk · 2026-09-23
- Juan Benet podcast reading list: The Beginning of Infinity, Permutation City, Nexus and more — juanbenet · 2026-09-23
- "Slowdown talk is aging terribly" — new models keep dropping, curve bends harder — Dr_Singularity · 2026-09-23
- Palantir co-founder Joe Lonsdale says everyone will be 'really wealthy' in the 2030s — Polymarket · 2026-09-23
- Goodside reconsiders anti-pause stance after labs call to slow the frontier — goodside · 2026-09-23