FuzzyBench

Program-as-Weights: compiling natural-language specs into compact neural adapters for local execution

Researchers introduce 'fuzzy-function programming' and its instantiation Program-as-Weights (PAW), a paradigm where a 4B compiler model converts natural-language function specifications into parameter-efficient adapters for a frozen lightweight interpreter. A 0.6B Qwen3 interpreter running PAW programs matches the performance of direct prompting with Qwen3-32B while using ~1/50th the inference memory and running at 30 tokens/s on a MacBook M3. The approach reframes large foundation models as one-time 'tool builders' rather than per-input solvers, targeting tasks like log triage, JSON repair, and intent-based ranking that resist rule-based implementation. The authors also release FuzzyBench, a 10M-example training dataset.