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)→

Original post →

More from AGI Musings

AGI Musings channel →