MIT 博客：GPT-6 Astra 直接编辑 Qwen3.5-0.8B 权重，MATH-500 从 7.9% 升至 48.1%
GPT-6 Astra can edit Qwen3.5-0.8B’s weights and raise its MATH-500 from 7.9% to 48.1%, without gradients or retraining.
摘要
alphaXiv 转述 MIT 的一篇博客，称 GPT-6 Astra 能在不计算梯度、不重新训练的情况下直接读取并编辑 Qwen3.5-0.8B 的权重，使其 MATH-500 成绩从 7.9% 提升到 48.1%。
摘要由模型根据原文撰写，以原文为准。
正文 · 原文
GPT-6 Astra can edit Qwen3.5-0.8B’s weights and raise its MATH-500 from 7.9% to 48.1%, without gradients or retraining.
“Sparks of Weight-Space Programming”
This blog from MIT asks whether LLMs can read and edit neural network weights directly, much like code.
In Qwen, Astra traced repetitive reasoning loops to a direction written by two MLP layers, then edited the weights to suppress it.
With 50 batches of forward-pass feedback, the fix also raised instruction following from 21.0% to 62.3%
Read on alphaXiv: https://www.alphaxiv.org/abs/2611.weight-space-programming
来源：alphaXiv · x.com
引用原文
askalphaxiv. GPT-6 Astra can edit Qwen3.5-0.8B’s weights and raise its MATH-500 from 7.9% to 48.1%, without gradients or retraining.[EB/OL]. (2026-11-03)[访问日期]. https://x.com/askalphaxiv/status/2117406632229646689.