MIT 研究人员用 GPT-6 Astra 直接修改 Qwen3.5-0.8B 权重提升数学准确率

AI 导读

MIT 研究人员使用 GPT-6 Astra 直接修改 Qwen3.5-0.8B 的权重，在不训练的情况下将其 MATH-500 准确率从 7.9% 提升至 48.1%。

正文 · 原文

MASSIVE. MIT researchers showed that GPT-6 Astra can improve another AI model by changing its weights directly, without training.

Here, GPT-6 Astra raised Qwen3.5-0.8B from 7.9% to 48.1% on MATH-500 by editing 0.016% of its weights, without training.

Astra got Qwen’s weights in a Python notebook, plus a budget of 50 test runs on practice math problems. It saw the model kept repeating itself until it hit its length limit, traced that habit to a single internal signal written by 2 of its layers, and subtracted that signal out of the weights.

With the loop gone, the model could finish answers it was already capable of solving.

That single targeted edit changed 0.016% of the weights and lifted math accuracy from 7.9% to 48.1%.