Introducing Handwired: JavaScript as Neural Networks (1 minute read)
Summary
Handwired 是一个趣味项目，可将普通 JavaScript 代码转换为神经网络，无需训练即可获得与原程序完全一致的输出，并且完全可微，全部在浏览器中运行，无需 GPU。
View Cached Full Text
Cached at: 10/16/26, 06:36 PM
My dear friends, I’d like to show you my latest toy project
Introducing Handwired: turn your regular JavaScript code into a neural net!
- no training
- exact outputs vs the JS program
- fully differentiable
All runnable in a browser, without GPU
Similar Articles
Show HN: Turn regular JavaScript into a neural net
Handwired 是一个可以把普通 JavaScript 代码（如 DOM 渲染的迷你桌面应用）直接转化为神经网络的工具，可对界面交互进行训练和优化。
@knowledgefxg: Fun Site Recommendation: Wokwi – An Electronic Circuit Simulator That Runs in Your Browser, Makes Embedded or IoT Development Easy. You Can Drag and Drop to Build Circuits, Write Code (Even Supports MicroPython), and Run Simulations with a Click – Even Simulate Wi-Fi Network Behavior. No Need to Spend a Penny on Hardware, Just…
Wokwi is an electronic circuit simulator that runs in the browser, supporting embedded system development like ESP32. You can drag and drop to build circuits, write code (including MicroPython), and simulate Wi-Fi behavior, allowing you to validate projects without hardware.
@ekzhang1: Homage to karpathy joining anthropic: made an in-browser (webgpu) version of the famous char-rnn "Unreasonable effectiv…
Created an in-browser WebGPU version of the classic char-rnn demo training on Shakespeare, paying homage to Karpathy joining Anthropic.
@ctatedev: Tiny models are becoming software primitives This 27.5KB model runs locally in your browser, syntax-highlighting code w…
A tiny 27.5KB AI model called gpu-lexer from Vercel Labs runs locally in the browser using WebGPU to syntax-highlight code in any programming language without prior knowledge.
@realfxw: Getting started with hardware has always been considered a steep barrier: countless components, wiring that easily shorts out, the difficulty of debugging hardware and software together... But what if complex circuits were broken down into interactive "building blocks"? Developer Dilum Sanjaya built an incredibly impressive...
Developer Dilum Sanjaya built Learn Arduino, an interactive hardware learning app powered by Claude Opus. With high-quality 3D circuit visualization and instant code-hardware linkage, it breaks Arduino fundamentals into step-by-step building-block lessons, lowering the barrier to learning hardware.