把模糊需求编译成AI小程序，本地跑还省内存
你让AI做一件事——比如“把乱掉的JSON修好”——每次都要调大模型API，慢、贵、还依赖网络。这篇把过程反过来：先让一个4B参数的“编译器”把你的自然语言需求转成一个极小的AI程序（参数适配器），然后交给一个0.6B的“解释器”在本地执行。结果：效果跟直接调用32B的大模型一样好，但推理内存只用五十分之一，在MacBook M3上每秒能跑30次。它不是你明天就能用的工具，但思路很颠覆：大模型不再是每次帮你解题的“家教”，而是帮你造一个“计算器”——造一次，以后随便用。
📄 原文摘要(英文)
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.