Handwired: write JavaScript logic as a neural net, zero training
Why it matters
Handwired, a new MIT-licensed open-source project from Cheng Lou (released Oct 15), lets you write JavaScript logic as an exact neural net: if-else, loops and state become matrix multiplications and ReLU gates over floats, with weights written by hand rather than learned. Nothing is trained, the output is exact, and the whole program stays fully differentiable, runnable in a browser without a GPU. The flagship Mini OS demo is a small desktop with windows, dragging, scrolling and animation in 9,909 weights and 130 layers with zero training; a JSON search demo searches 100,000 documents at every keystroke with the JavaScript turned into WebGPU kernels; and a learned gallery unfreezes a program's weights and trains them in real time. The pitch: attach an exact, frozen program to a regular neural net and train end to end. Caveat: there is no automatic converter; you write the network in builder code by hand, and only the search demo runs on WebGPU.
Read the source: GitHub (chenglou/handwired) (opens in a new tab)
All hits from 17 Oct 2026More CodingGet the daily hits by email