Monday, November 16, 2026
About  ·  Contact  ·  RSS
Artificial Intelligence

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

Sentiment: Bullish 🚀
By Funded4Trading  ·  November 16, 2026  ·  1 min read  ·  6 views
Advertisement
Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy

Cmpnd has released dspy-wsp, a prototype optimizer that brings weight-space programming to DSPy.

Weight-space programming is a technique in which a frontier LLM reads another model’s weights and edits them directly.

There are no gradients, no training loop and no fine-tuning dataset.

dspy-wsp packages this as WeightSpace, an optimizer that plugs into any DSPy program and metric.

In Cmpnd’s tests, about $5 to $10 of GPT-6-Astra calls improved every decision model they tried.

You can check the deployment options and specs here through our GPULeaderboard.com chrome extension.

TL;DR What it is: A DSPy optimizer (WeightSpace) where a writer LLM edits a student model’s weights.

MIT license, pip install dspy-wsp, needs DSPy 3.5.

Size: Tested on open decision models from 0.6B to 9B parameters.

One 25-pass run edited a single layer or head.

Runs on: One Mac for all experiments.

2B models used about 6 GB of memory.

d1-omni-600M needs 4 GB or more (Mac or GPU).

Performance: WeightSpace alone added 1.9 to 16.1 points on Typed Decisions.

With ReAnchor, gains were 6.5 to 20.0 points.

Best: d1-omni-600M rose from 50.9% to 69.1% (+18.3) with WeightSpace + ReAnchor.

Worst: Clef-Flash (9B) gained only +1.9 from WeightSpace alone.

▸ Read Next

Silicon Valley claims to know the future. So why did it get the midterms so wrong?

Artificial Intelligence · November 15, 2026
Advertisement