Venturebeat10 min read
'Like gene editing for neural networks': MIT researchers used GPT-6 Astra to edit Qwen's open weights directly, boosting math performance
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…
By Carl FranzenVentureBeat AI

Read the full story
Originally published by VentureBeat AI on Nov 2, 2026.
Comments
Sign in to join the discussion.