Jerry Liu· @jerryjliu0 · X·· 2 小时前AI 评分54
AI 导读
Jerry Liu 转发 Rikiya Takehi 等人（MIT CSAIL）的 Weight-Space Programming 研究：让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 权重以提升数学能力，仅改动 0.016% 的权重，无梯度无训练，修复了推理循环问题，MATH-500 从 7.9% 提到 48.1%，instruction following 提升约 3 倍。研究还称前沿 LLM 可从原始权重判断网络训练目标，并能从零写出胜过 PPO 训练 1 亿步的小型游戏网络。博客：https://rikiyat.github.io/blog/weight-space-programming/
正文 · 原文
wtf
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：Jerry Liu · x.com