Weight Space Programming

Blogger claims local Qwen 3.8 27B model can read and edit neural network weights

A developer reports replicating findings from a paper titled 'Sparks of Weight-Space Programming,' which described GPT-6 Astra analyzing and editing raw neural network weights directly from text. The blogger says a locally run Qwen 3.8 27B model performed similar weight interpretation tasks on a laptop, following an example from the paper.

simonwillison.net · 2026-11-03

Astra AI system edits Qwen3.5-0.8B's raw weights, lifting MATH-500 score sixfold

A research team reports that its frontier model, called Astra, can directly read and edit neural network weights without any training loop or gradient updates. By identifying a reasoning-loop flaw in Qwen3.5-0.8B's weights, Astra edited roughly 0.016% of them and raised the model's MATH-500 score from 7.9% to 48.1%, with IFEval scores tripling. Astra also reportedly wrote small game-playing networks from scratch that beat networks trained with PPO over 100 million steps, and could identify a network's training task just by inspecting its weights.

rikiyat.github.io · 2026-11-02