# Post questions whether weight-editing fix for Qwen3.5-0.8B loops has side effects

> Original title: 非常有启发！但... 难道不像 LLM 的贺建奎么？

- Source: Dongxi NLP
- Published: 2026-11-02T19:28:34.000Z
- Bad Influence: https://badinfluence.news/items/v7j8ndg76tsvi477bybo39wq8
- Original: https://x.com/dongxi_nlp/status/2117338092768047481

## Summary

Dongxi NLP compares the method to activation steering and argues that the reported gains on MMLU-Pro, GPQA, and IFEval may come from fixing reasoning loops that affected those benchmarks. The author removed the projection of 128 weight columns that write the loop direction rather than adding a steering vector. The post asks what side effects the edit causes.

## Post

非常有启发！但... 难道不像 LLM 的贺建奎么？

方法中看到了 activation steering 的影子：先找到模型某种倾向对应的激活方向，比如文中让模型算题停不下来的 loop 问题。

作者没有往模型里加一个 steering vector，而把写入这个方向最多的 128 列权重里的对应分量投影掉了。

评估使用的 MMLU-Pro、GPQA、IFEval 等确实都有提升，但这些 benchmark 原本都受 loop 影响，loop 修好了，分数当然全面提升。

问题是，副作用呢？

## 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