前沿LLM原生读写神经网络权重能力研究
Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights [R]
Link: https://rikiyat.github.io/blog/weight-space-programming/
链接：https://rikiyat.github.io/blog/weight-space-programming/
Snippet: “We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or conventional algorithms. This might be a big deal for both optimization and interpretability.
摘要：“我们发现，前沿大语言模型（LLMs）在原生读取和写入神经网络权重方面表现出色，远超我们对人类或传统算法的预期。这对优化和可解释性来说可能意义重大。”
Just by looking at the raw weights, GPT-6 Astra can tell what a network was trained to do. And without any environment feedback, it has no trouble writing, from scratch, small game-playing networks that outplay networks trained with PPO for 100 million steps.”
仅通过观察原始权重，GPT-6 Astra 就能判断一个网络被训练用于执行什么任务。而且，在没有环境反馈的情况下，它也能毫不费力地从零开始编写小型博弈网络，这些网络的表现优于经过 1 亿步 PPO 训练的网络。
Very surprising result, I didn’t expect frontier models to have this capability that has not been optimized for, and it’s something humans cannot do either.
这是一个非常令人惊讶的结果，我没想到前沿模型会具备这种未被专门优化的能力，而这也是人类无法做到的。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力