GPT-6 Astra edited Qwen’s weights and raised MATH-500 from 7.9% to 48.1% in author-run tests. How weight-space programming works—and its limits.
Space Programming".1. Weight-Space ProgrammingOn November 2, 2026, a research team at MIT CSAIL announced a new method called "Weight-Space Programming", in which an LLM directly reads and writes the ...
MIT CSAIL researchers say GPT-6 Astra edited 0.016% of Qwen3.5-0.8B weights to fix reasoning loops, lifting MATH-500 from 7.9% to 48.1% without training.
Simon Willison ran the 17-gigabyte open-weight model locally and fed it floating-point arrays from four reinforcement-learning policies. Without calculators or code execution, Qwen identified Breakout ...
"Please improve an AI that is bad at math without additional training."When asked this, we usually think of adding training ...
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights' - ...
The MIT CSAIL team has proposed a "weight-space programming" method that enables GPT-6 Astra to directly read and modify ...
MIT CSAIL's "weight-space programming" has a frontier LLM read and edit neural network weights directly, with no gradient descent. Surgical edits ended Qwen's reasoning loops, but the results come ...
A new MIT CSAIL blog post is making the rounds in AI circles this week, and it describes something that sounds almost ...
Article by Shenchao TechFlowNo training required, no data needed, no gradient descent.Researchers at MIT fed the weights of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results