MIT Proposes Weight-Space Programming: GPT-6 Astra Enhances Models Without Training
MIT researchers demonstrated 'Weight-Space Programming,' a new paradigm where frontier LLMs like GPT-6 Astra directly edit the weights of other AI models without training or gradients. By modifying just 0.016% of Qwen3.5-0.8B's weights to fix reasoning loops, the method boosted math accuracy from 7.9% to 48.1%, achieving nearly 6x performance improvement.
Full Report
Rohan Paul (@rohanpaul_ai) · 2026-11-02 20
MASSIVE. MIT researchers showed that GPT-6 Astra can improve another AI model by changing its weights directly, without training.
Here, GPT-6 Astra raised Qwen3.5-0.8B from 7.9% to 48.1% on MATH-500 by editing 0.016% of its weights, without training.
Astra got Qwen’s weights in a Python notebook, plus a budget of 50 test runs on practice math problems. It saw the model kept repeating itself until it hit its length limit, traced that habit to a single internal signal written by 2 of its layers, and subtracted that signal out of the weights.
With the loop gone, the model could finish answers it was already capable of solving.
That single targeted edit changed 0.016% of the weights and lifted math accuracy from 7.9% to 48.1%.
↳ 引用 @rikiyatakehi (Rikiya Takehi): We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog:
