Recurrent Looped Transformer 'infinite reasoning depth' claim slammed: no loss curves at any scale
burny_tech · x · 2026-09-14
Researcher yifanzhang announced the Recurrent Looped Transformer (RLT), claiming Transformers now have 'infinite reasoning depth' in a superintelligence-framed post. SmartPigJoe quoted it with a pointed critique: despite a million views, the post shows no pretraining loss curve at any scale, let alone validation through a scaling ladder — 'ideas are cheap, show me the scaling result.'
Related event: RLT Paper Touting Superintelligence Sparks Backlash(3 posts)→
More from Research
- PostTrainBench traces hit 104k monthly downloads — author warns it's likely reward hacking — maksym_andr · 2026-10-31
- OpenAI's Navier-Stokes solution accused of specification gaming via unrealistic forcing — dhadfieldmenell · 2026-10-31
- Researchers encode 200+ properties of SGLang inference server, uncover 10 bugs — LingmingZhang · 2026-10-31
- Expert panels map 21 clinical AI risks; adversarial tests show autonomous care still unsafe — AleksandraFaust · 2026-10-31
- Handwritten RAGEN code becomes the #3 hardest task in FrontierCS 2 — wzenus · 2026-10-31
- Fudan, Tencent Hunyuan and Tsinghua unveil ExplorationBench to test AI rule discovery — jiqizhixin · 2026-10-31