developer tools
The Prompt Became a Small Program You Could Keep
A teacher generates examples once, trains an adapter in about a minute, and leaves behind a reusable local neural function.
Summary
A teacher generates examples once, trains an adapter in about a minute, and leaves behind a reusable local neural function.
Compile by training treats a natural-language specification as build input rather than a request to send repeatedly to a remote model. Teacher models create task-specific examples, a compact interpreter learns a small adapter, and the resulting function can be stored, versioned and composed without the teachers at runtime. On the difficult FuzzyBench-Hard subset where the compared fast Program-as-Weights compiler produced no exact matches, the authors report 83.6% semantic accuracy. The tradeoff is a roughly one-minute compile instead of seconds; demonstrations include a multi-site helper, a language-controlled 3D avatar and an English-Claudish translator. The figures and deployment examples are author-reported preprint results.
Why it matters
A teacher generates examples once, trains an adapter in about a minute, and leaves behind a reusable local neural function.
Limits and context
No additional limitation was separately recorded.
Key claims
A teacher generates examples once, trains an adapter in about a minute, and leaves behind a reusable local neural function.
Evidence: source-2026-09-04-002
Sources
- arXiv preprint 2609.04199arXiv · primary research
Corrections
No corrections have been recorded for this story.