# GPT-6 Astra edits Qwen3.5-0.8B weights to improve math without training

> Original title: From the blog:

- Source: Andrew Curran
- Published: 2026-11-02T18:34:45.000Z
- Bad Influence: https://badinfluence.news/items/nieond8g99z40f0g2jypvypjr
- Original: https://x.com/AndrewCurran_/status/2117324550505730437

## Summary

Riki Yatakehi says GPT-6 Astra directly changed only 0.016% of the weights in Qwen3.5-0.8B, without gradients or training. The edits reportedly fixed the model's reasoning loops and raised math performance up to 6x and instruction following up to 3x.

## Post

From the blog:

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWI_dS4bcAA8UtV.jpg&mode=thumb&exp=1793836800&sig=7ea74ebdfaa59f85)

## 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