AI safety researcher invokes 1946 Slotin criticality accident as cautionary tale
JeffLadish · x · 2026-11-08
AI safety researcher Jeff Ladish quotes the Wikipedia account of Louis Slotin's 1946 Los Alamos criticality accident, where a physicist manually lowered beryllium reflector halves over a plutonium core with only a thumb-hole gap — a demonstration that ended in a fatal radiation accident. The "demon core" anecdote is a common analogy in AI safety circles for manually approaching dangerous thresholds without safety margins.
Related event: AI Safety Researcher Warns of Impending RSI With Demon Core Meme(2 posts)→
More from AGI Musings
- JEV Gets Its First Paper as Researchers Split on Research Merit vs Closed Business Model — teortaxesTex · 2026-11-08
- "Humans overfit to confirmation too" — a witty mode collapse analogy for AI slop debate — flowersslop · 2026-11-08
- bayeslord: Stop treating AI as a monolith — four distinct goals demand precise language — sebkrier · 2026-11-08
- AI doesn't change how unique your niche interests are, argues dev pixlpa — pixlpa · 2026-11-08
- Albert Gu: Bitter Lesson isn't 'just scale Transformers' — algorithmic innovation matters — sewon__min · 2026-11-08
- The 'evolutionary mismatch' chart explaining why humanity will ignore AI warnings — sebpaquet · 2026-11-08