Cheng Lou Releases Handwired for Manually Building Neural Networks From JavaScript Logic

Cheng Lou released Handwired, an MIT-licensed project for manually expressing JavaScript program logic as neural networks without training; Bao Yu has since shared a tutorial and reported trying it with countdown and Snake examples. Bao Yu’s overview describes Handwired as producing exact outputs through differentiable operations, with demos including a browser desktop, document search, and a trainable photo layout. It does not automatically convert existing JavaScript source code into a network: developers must rebuild the logic using Handwired’s construction functions, declare value ranges, and work within 32-bit floating-point and execution constraints. Bao Yu’s tutorial, available in English and Chinese, explains the approach and claims that every number matches without training.

Generated by AI from reports · Updated 14 hours ago

1. 10/16 22:10 (UTC+8) · 1 reports
   Bao Yu Shares a Handwired Tutorial Video
   宝玉 · X：Bao Yu Shows How Handwired Turns Code Into an Exact Neural Network
2. 10/16 02:04 (UTC+8) · 1 reports
   Dotey Explains How Handwired Turns JavaScript Logic into Handwritten Neural Network Weights
   宝玉 · X：Cheng Lou releases Handwired to build neural networks from JavaScript program logic