Language Models Can Rewrite Their Own Weights: no gradients, no training
jiqizhixin · x · 2026-11-18
A share of the paper "Language Models Can Rewrite Their Own Weights" (arXiv:2611.21885), which shows a model can edit its own weights through pure reasoning — no gradients, no training — to make itself more accurate.
Related event: Language Models Can Rewrite Their Own Weights Without Training(3 posts)→
More from Research
- Field experiment: Google AI Overviews cut publisher clicks 39.8% with no UX gain — paulnovosad · 2026-11-18
- RoboDojo sim "not even wrong": blog exposes physics flaws in popular robot benchmark — ZeYanjie · 2026-11-18
- CoTAM: Machine-Oriented Image Compression That Preserves Multimodal AI Reasoning Performance — burkov · 2026-11-18
- Formal verification meets agentic AI: neurosymbolic approach pitched as a path to trustworthy agents — luislamb · 2026-11-18
- Claude correctly folds ubiquitin from a plain prompt, no specialized tools needed — iScienceLuvr · 2026-11-18
- Peking University Open-Sources PanDWM, a 360° 4D Driving World Model Beating DiST-4D — PekingUniversity · 2026-11-18