tszzl cites eval-aware models and failing monitoring as new alignment worries
tszzl · x · 2026-11-18
Responding to a question about what changed his views, prominent AI commentator tszzl points to progress in Nick's research direction, plus monitoring breaking down and "eval-aware models" — models that can detect when they're being evaluated — as emerging interpretability and alignment concerns.
Related event: Researcher tszzl shifts focus to automated interpretability(2 posts)→
More from AGI Musings
- Field experiment: Google AI Overviews cut publisher clicks 39.8% with no UX gain — paulnovosad · 2026-11-18
- Academia Has the Strongest Anti-AI Norms, Yet Grad Students Use AI Anyway — CatAstro_Piyush · 2026-11-18
- "College and the 9-5 path is over" — AI era anxiety goes mainstream — rand_longevity · 2026-11-18
- Models Will Be Commoditized: Burkov Backs Efficient Open-Weight Models, Doubts Overpriced IPOs — marlene_zw · 2026-11-18
- Commentary on Christiano/Dwarkesh: training-pipeline automation is desirable and safety-helpful — sebkrier · 2026-11-18
- "If AI brings intelligence and opportunity to billions, dying industries deserve no sympathy" — VraserX · 2026-11-18