# LLMs can read and edit neural network weights directly

> Original title: Must-read report! They find that LLMs are surprisingly good at reading and writing neural network weights.

- Source: Elvis Saravia
- Published: 2026-11-02T20:31:05.000Z
- Bad Influence: https://badinfluence.news/items/xdbsdqazhgwai5r93tz0pz5i0
- Original: https://x.com/omarsar0/status/2117353828446060736

## Summary

A report finds LLMs can read and write neural network weights, a capability Elvis Saravia calls a more native route to recursive self-improvement than current pipelines that write code to launch training jobs. In a related post, Rikiya Takehi says GPT-6 Astra changed only 0.016% of Qwen3.5-0.8B's weights without gradients or training, improving math up to 6x and instruction following 3x.

## Post

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.

## Quoted post @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: https://rikiyat.github.io/blog/weight-space-programming/

https://x.com/rikiyatakehi/status/2117313742891327994