PapersMulti-source
GPT-6 Astra 直接改写 Qwen3.5-0.8B 权重，数学能力提升最高 6 倍
Why we picked it
有人让 GPT-6 Astra 手改 Qwen3.5-0.8B 的权重，不动训练流程，数学就快了 6 倍，思路很新奇。
研究者 Rikiya Takehi 让 GPT-6 Astra 编辑 Qwen3.5-0.8B 的权重来改进数学表现。模型只改动了 0.016% 的权重，无需梯度或训练，就修复了 0.8B 模型的推理死循环，数学成绩提升最高 6 倍，指令遵循提升 3 倍。作者将这一方法命名为 Weight-Space Programming，即前沿大模型直接读写神经网络权重。
Original · Thomas Wolf
what? Rikiya Takehi @rikiyatakehi 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: rikiyat.github.io/blog/weight-sp… q 🔗 View Quoted Tweet 💬 17 🔄 13 ❤️ 222 👀 24605 📊 38 ⚡
