Cmpnd 发布 dspy-wsp：用大模型直接编辑小模型权重
Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy
Cmpnd 把 DSPy 优化器玩出了新花样：让 GPT 这类大模型直接改小模型的权重，不用梯度、不用 GPU 集群，一次跑下来只要 5 到 10 美元。做小模型微调的同学可以看看这个路子和传统训练差在哪。
Cmpnd 发布了 dspy-wsp，一个面向权重空间编程的 DSPy 优化器原型。它让一个 frontier 级 LLM 读取小模型的权重，在沙盒环境中直接编辑，并对每次修改进行测试验证，全程不依赖梯度计算。
具体机制是：LLM 充当优化器角色，观察模型参数、提出修改、在沙盒中执行并评估效果，循环迭代。每次运行成本约 $5 到 $10，远低于传统训练流程，因为它绕过了反向传播。
这个思路把 DSPy 的程序化优化从提示词层面推进到权重层面，为小模型的低成本定制提供了新路径，对预算有限的开发者有参考价值。
Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy
Cmpnd released dspy-wsp, a prototype DSPy optimizer for weight-space programming. A frontier LLM reads a small model’s weights, edits them in a sandbox, and tests each change, with no gradients and about $5 to $10 per run. The post Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy appeared first on MarkTechPost .
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include DSPy, dspy-wsp, Cmpnd, fine-tuning.
Primary source verification: published directly by marktechpost with first-party authority.
