今天新增gpt-6IMAGE
让 GPT-6 Astra 直接改权重：权重空间编程
Rikiya Takehi 让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 权重，仅改动 0.016% 参数、无需梯度或训练，即修复推理循环，数学最高提升 6 倍、指令遵循提升 3 倍，并称之为“权重空间编程”。
Rikiya Takehi
@rikiyatakehi3 小时前收录原推发布于 2026.11.03
Rikiya Takehi @rikiyatakehi原推发布于 2026.11.03
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/
x.com/rikiyatakehi/status/2117313742891327994采集于 2026.11.03 09:35