Ethan Mollick· @emollick · X·· 3 小时前AI 评分65
AI 导读
有研究者称让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 的权重以提升数学能力，仅改动 0.016% 的权重，就在不借助梯度或训练的情况下修复了该模型的推理循环，数学能力最高提升 6 倍、指令遵循提升 3 倍，并将该方法称为 Weight-Space Programming。Ethan Mollick 转发该结论并表示仍在等待复现，但认为这是件大事。
正文
Waiting for replication but this is a pretty big deal.
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：Ethan Mollick · x.com