Development

Research suggests some frontier models are a small transformer looped twice

development2026-07-19

Claim

Princeton's DeepLoop showed looped Transformers scale depth stably once residual rules account for revisited parameters, with its author passing along the rumor that some frontier models are basically a 48-layer transformer looped twice.

Reported metric: 48 layers, looped

Reporting date: (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Knowledge graphopen in browser →

Reported in
Actor
Evidence for
Supersedes
Referenced by

Cite or correct this record

Suggest a correction — opens a GitHub draft for you to review and submit.