DeepLoop paper makes looped transformers scalable; rumor claims frontier models are 48 layers looped twice
StartupYou · x · 2026-09-03
yifanzhang claims 'some frontier models are basically a 48-layer transformer looped twice (48L x 2)'—unverified—and introduces DeepLoop: Depth Scaling for Looped Transformers, a paper making looped transformer training stable and scalable. If true, frontier labs may be reusing layers rather than merely stacking depth, but the rumor remains unconfirmed.
Related event: DeepLoop: looping Transformers scale stably in depth(2 posts)→
More from Models
- Polish dev defends open model: built on Gemma with more than a simple LoRA fine-tune — ColinWPLewis · 2026-10-21
- X trends: SophontAI's Holon-S1 predicts gene activity from cancer slides; decision models rise — iScienceLuvr · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- 704-vote robotics Elo ranks Claude Opus 5.5 first at 1379; no model completes the task — qinzytech · 2026-10-21
- DeepSeek V4 called 'god-tier infra, 4th-tier ML': 7 tricks stacked, 20 patches to fix them — teortaxesTex · 2026-10-21
- GPT-6 Astra and Claude Fable 5.1 write $10,000 research papers — experts reject all — sayashk · 2026-10-21