Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy

Cmpnd released dspy-wsp, a prototype DSPy optimizer for weight-space programming in which a frontier LLM reads a small model's weights, edits them in a sandbox, and tests each change without gradients, at roughly $5 to $10 per run. The release gives DSPy developers a prototype tool for modifying model weights directly rather than through gradient-based training.