Cheng Lou releases Handwired to build neural networks from JavaScript program logic

What happened

Cheng Lou released Handwired, an MIT-licensed project for manually expressing JavaScript program logic as neural networks with exact outputs, no training, and differentiable operations. Baoyu’s overview describes a browser desktop, document search, and a trainable photo layout demo. Handwired does not automatically convert existing JavaScript source code; developers must rebuild logic using its construction functions, declare value ranges, and work within 32-bit floating-point and execution constraints. https://chenglou.me/handwired/ https://github.com/chenglou/handwired

The story so far

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.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights