Looped Transformers, or Recurrent Depth Models
2026-10-17
7 min read1,387 wordsai safetyartificial intelligencecomputer sciencellmsmachine learningpersonalscalingwritingHow looped transformers reuse their layers to reason in latent space, why recurrent depth is suddenly showing up at the frontier, and what it could cost us in chain-of-thought monitorability.