Nov 13, 2026

Weight-Space Programming with DSPy

Drew Breunig, CEO of Cmpnd

Introducing dspy-wsp, a prototype optimizer that lets frontier models observe and edit the weights of another model.

Last week, Rikiya Takehi, Jayden Teoh, Alex Zhang and Omar Khattab showed that frontier models can edit the weights of smaller models directly, with no gradients and no training, using a technique called “Weight-Space Programming.” In one experiment, GPT-6-Astra edited 0.016% of Qwen3.5-0.8B’s weights, eliminating a looping problem and raising its MATH-500 score from 7.9% to 48.1%. Haoze “Hector” He applied the weight-space technique to decision models, demonstrating it works there, too.

It’s early days, but models that can perform brain surgery on one another have mind-boggling potential.