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

> Original title: GPT-6 Astra:

- Source: Vaibhav Srivastav
- Published: 2026-11-02T20:33:14.000Z
- Bad Influence: https://badinfluence.news/items/m3bizobiyc0gdl4x1zfu5bb6f
- Original: https://x.com/reach_vb/status/2117354368420786603

## Summary

OpenAI's GPT-6 Astra directly edited 0.016% of Qwen3.5-0.8B's weights, without gradients or training, to fix reasoning loops. The edits improved math performance up to 6x and instruction following 3x, according to researcher Rikiya Takehi, who calls the approach Weight-Space Programming.

## Post

GPT-6 Astra:

## 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