MIT CSAIL introduces 'Weight Space Programming': GPT-6 Astra modifies only about 0.016% of Qwen3.5-0.8B's weights to boost MATH-500 scores by six times.
MIT CSAIL researchers propose 'Weight Space Programming', enabling GPT-6 Astra to directly read and modify Qwen3.5-0.8B's weights—altering just 131,072 parameters (roughly 0.016%) without gradient descent or traditional training loops.
Continue looking at this topic
Related contentWhat is Qwen? Choosing between cloud interfaces and local models ↗Hotly discussed viewsToo abstract. Vice President of Alibaba Group and CEO of Qwen Office, Chen Yusen, will appear in Li Jiaqi's livestream tonight to sell his own A... ↗News and AnalysisJoe Tsai of Alibaba: Open source is the only way to advance AI adoption; Qwen open models now exceed 470 versions ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original