The story’s score and claims

Comments on No. 63 of 142 · Michał Piszczek · edition of Wednesday 18 November 2026

Looped Transformers Explained

Summary

Looped transformers reuse one shared block of layers several times per token, so a model executes more layers than it stores. NVIDIA's four-billion-parameter Dory model reportedly beats some larger models on average across twelve benchmarks with two or more loops.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules