PAW让模糊函数（如日志告警、修复JSON）不再依赖大模型API。用4B编译器一次编译，0.6B小模型就能跑出32B的效果，还省内存和算力。
PAW（Program-as-Weights）提出一种模糊函数编程范式，将自然语言规范编译为紧凑的本地可执行神经构件。一个4B编译器在FuzzyBench（1000万示例）上训练，为冻结的0.6B Qwen3解释器生成参数高效适配器。该解释器执行PAW程序，性能匹配直接提示Qwen3-32B，但推理内存仅为其1/50，在MacBook M3上达30 tokens/s。PAW将基础模型从逐输入求解器转变为可复用小工具构建器。
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference memory and running at 30 tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.