Menu

MIT Researchers Used GPT-6 Astra To Edit Qwen's Open Weights Directly, Boosting Math Scores - Slashdot

science.slashdot.org·12 days ago
#2wcmWJX1
#model#astra#directly#weights#networks
Reading 0:00
15s threshold

An anonymous reader quotes a report from VentureBeat: Researchers from the Massachusetts Institute of Technology (MIT) Computer Science & Artificial Intelligence Laboratory (CSAIL) reported today that they used OpenAI's GPT-6 Astra language model to raise a small, open source Qwen model's math score roughly sixfold by directly editing its weights -- the numerical parameters that govern its behavior. Rikiya Takehi, Jayden Teoh, Alex Zhang and Omar Khattab described their work in a research blog post published November 2. They call the approach "weight-space programming" and tested Astra's ability to interpret and alter networks without using conventional training procedures to generate the edits.

In the strongest language-model example, Astra's intervention raised Qwen3.5-0.8B's MATH-500 score from 7.9% to 48.1% while touching approximately 0.016% of its weights.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.