研究称 LLM 可直接改写神经网络权重，GPT-6 Astra 微调 Qwen3.5-0.8B 数学能力提升至 6 倍
有人让 GPT-6 Astra 直接改 Qwen3.5-0.8B 的权重，不动一行训练代码，数学就快了 6 倍，这思路挺新鲜。
研究团队让 GPT-6 Astra 直接编辑 Qwen3.5-0.8B 的权重来改进数学能力，全程不使用梯度或训练。模型只修改了 0.016% 的权重，就把 0.8B 模型的数学能力提升最高 6 倍，指令遵循提升 3 倍，并修复了推理循环问题。团队将这种方法称为 Weight-Space Programming，即前沿 LLM 可以原生读写神经网络权重。作者认为相比现有通过写代码启动训练任务的 RSI 流程，这提供了经由权重直接递归自我改进的更原生路径。
Must-read report! They find that LLMs are surprisingly good at reading and writing neural network weights. Huge for RSI when you think about it! Current RSI pipelines focus on writing code to launch training jobs. This capability could offer a more native path to recursively self-improve models via weights. 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 💬 13 🔄 6 ❤️ 40 👀 8098 📊 17 ⚡
