Compile by Training
Compile by Training released — presents a way to "compile" natural-language specifications into reusable neural functions. Explains that at compile time a teacher model generates examples for training a small adapter, and later calls are handled by the local adapter, removing the recurring cost, latency and provider dependence of remote model calls. Says compiling takes about 1 minute
Why it matters
A strand that, instead of sending the prompt to a remote model every time, distills the specification once and sets it into a local function. In the authors' own reporting, 83.6% semantic accuracy on FuzzyBench-Hard. Presents a multi-site web assistant, a language-controlled 3D avatar and a bidirectional translator as examples
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2609.04199Added in Week 37, 2026 · See that week