Researchers at the Massachusetts Institute of Technology (MIT) have shown that large language models (LLMs) can read, interpret, and modify neural network weights directly, without relying on traditional training methods like gradient descent. In a research blog post published on November 2, the researchers introduced a technique called Weight-Space Programming, which lets general-purpose LLMs examine a neural network’s weights, identify problems in its behaviour, and modify them based on natural-language instructions. The research was conducted by Rikiya Takehi, Jayden Teoh, Alex Zhang and Omar Khattab, all affiliated with MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). The researchers used OpenAI’s GPT-6 Astra to demonstrate the approach across eight experiments, including identifying what a neural network was trained to do, writing networks from scratch and improving the mathematical reasoning capabilities of an existing language model. One key experiment involved improving Qwen3.5-0.8B, a small language model, without retraining it or using gradient information. By modifying just 0.016% of the model’s weights, Astra increased its score on the MATH-500 benchmark from 7.9% to 48.1%. Its score on GSM8K increased from 13.8% to 67.1%. Its IFEval score increased from 21% to 62.3%. Astra also correctly identified all four games among networks trained to play Breakout, Pong, Pac-Man and