Sebastian Raschka· @rasbt · X·· 2 小时前同事件AI 评分65
AI 导读
Sebastian Raschka 转发了一项称 GPT-6 Astra 直接修改 Qwen3.5-0.8B 权重以提升数学能力的工作，该工作称仅改动 0.016% 的权重，无需梯度或训练，数学能力最高提升 6 倍、指令遵循提升 3 倍，并将其称为 Weight-Space Programming。Raschka 本人只配了一句 What could possibly go wrong? 和一张漫画，漫画把 Transformer 第 13 层前馈模块中单个已训练权重画成支撑全部现代数字基础设施的支柱。
同一件事，精选收录的是《MIT CSAIL 提出权重空间编程：GPT-6 Astra 直接修改 Qwen3.5-0.8B 权重》
正文 · 原文
What could possibly go wrong?
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: https://rikiyat.github.io/blog/weight-space-programming/在 X 查看被引用的帖子
来源：Sebastian Raschka · x.com