Researchers affiliated with MIT’s Computer Science and Artificial Intelligence Laboratory used OpenAI’s GPT-6 Astra to edit Alibaba’s Qwen3.5-0.8B model, raising its MATH-500 score to 48.1% from 7.9% in an experiment with 50 forward passes. The method, called “Weight-Space Programming,” lets a language model inspect and change another model’s weights directly, without training or gradient updates. The edit touched 131,072 weight values, equal to 0.016% of Qwen’s weights, and targeted repeated reasoning loops that caused answers to run into a 32,768-token limit. The edit reduced those cutoffs but did not eliminate them; on MATH-500, the share of answers reaching the token limit fell to 33.1% from 93%. In an initial set of 96 practice answers, 85 had hit the limit before the edit. The score depended on the execution budget: separate tests with 10 and 25 forward passes produced MATH-500 scores of 12.3% and 14.1%, respectively, compared with 48.1% at 50 passes. A separate paired evaluation on 1,152 held-out practice problems recorded 579 rescued answers and five regressions; of the rescued answers, 576 had been truncated before the edit. The approach showed little effect on Google’s Gemma 3 270M, whose MATH