dspy-wsp releases WeightSpace optimizer that edits model weights via a writer LLM

dspy-wsp is a prototype DSPy optimizer that brings Weight-Space Programming to existing programs, letting a writer LLM such as GPT-6-Astra edit another model's weights without gradients or training. Tested on five open decision models from 0.6B to 9B parameters with the Typed Decisions benchmark, WeightSpace alone added 1.9 to 16.1 points of accuracy on 400 held-out cases, and 6.5 to 20.0 points when combined with the ReAnchor optimizer. Each run used 25 forward passes at maximum reasoning effort for roughly $5-10, and the edited models run locally through MLX on Apple silicon or PyTorch on NVIDIA GPUs.