LessWrong: looping boosts no-CoT reasoning far more than general skills in NVIDIA's Dory 4B

CFGeek · x · 2026-11-22

A LessWrong study tests the worry that looped transformers are harder to monitor, using NVIDIA's public looped transformer Dory 4B.

The finding is in tension with claims that looped-transformer interpretability is no harder than very deep models.

Original post →

More from AGI Musings

AGI Musings channel →