elvis· @omarsar0 · X·· 2 小时前AI 评分66
AI 导读
一项研究让 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，无需梯度或训练，数学表现最高提升 6 倍、指令遵循提升 3 倍。作者将这一做法称为 Weight-Space Programming，认为前沿 LLM 已能原生读写神经网络权重。Elvis Saravia 转发时指出，现有 RSI 流程主要靠写代码启动训练任务，而这一能力可能提供经由权重递归自我改进模型的更原生路径。
正文
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.
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：elvis · x.com