Yudkowsky Rips Apart Claims That Interpretability Could Make ASI Alignment 'Normal Science'
inductionheads · x · 2026-10-16
After Nick Cammarata, co-author of early OpenAI mechanistic interpretability work, hinted at interpretability breakthroughs that could turn "aligning ASI" into normal science, Eliezer Yudkowsky fired back in a profanity-laced thread: no level of interpretability makes alignment normal science, and findings like polysemanticity and single-neuron activations are still at the absolute beginning of understanding how a mind thinks. Roon even claimed the work would force Yud to lower his p(doom).
Related event: Yudkowsky Disputes Claims of Interpretability Breakthrough in AI Alignment(2 posts)→
More from AGI Musings
- Yudkowsky slams mech interp progress as critique sparks AI safety drama — inductionheads · 2026-10-16
- Rethinking disability in an enhanced future: James Hughes' democratic transhumanism — Chris_Armstrong · 2026-10-16
- Chess legend Judit Polgar: AI's ready-made answers can crush playful curiosity — Chris_Armstrong · 2026-10-16
- Mark Cuban's "AI is book smart, not street smart" dubbed the best pitch for RL environment startups — joecole · 2026-10-16
- Big consulting's business model faces a reset as AI ends learning-on-the-client's-dime — DavidLinthicum · 2026-10-16
- Optimists build planes, pessimists build parachutes: an analogy for AI factions — prasanna_says · 2026-10-16