AnalysisAI ModelsNovember 2, 2026

MIT CSAIL: GPT-6 Astra edits Qwen3.5-0.8B weights, MATH-500 7.9% to 48.1%

Read original source →venturebeat.com

Four MIT CSAIL researchers report GPT-6 Astra read and wrote Qwen3.5-0.8B's weights directly, changing just 0.016% of them to lift MATH-500 from 7.9% to 48.1% with no gradients or training loop. The authors say the edit mostly removed a failure mode, and all experiments but the Qwen one were small.

4 sources

More stories today

Open the live feed