LLM原生读写权重：通过方向操作移除模型行为
LLMs can natively read & write neural network weights
LLMs can natively read & write neural network weights
LLM 可以原生地读取和写入神经网络权重
Astra traced the looping to one direction written by the MLPs of layers 15 and 19, and subtracted that direction from 64 output columns in each ... much like removing a behavior by deleting a single direction from a model’s weights.
Astra 将循环追踪到由第 15 层和第 19 层的 MLP 所写的一个方向，并从每个 ... 的 64 个输出列中减去该方向，这类似于通过从模型权重中删除单个方向来移除某种行为。
https://rikiyat.github.io/blog/weight-space-programming/
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