You are viewing archived messages.
Go here to search the history.

Konrad Hinsen 🕰️ 2025-11-03 13:22:46

Micrograd: a pedagogical implementation of neural networks using a reverse-mode automatic differentiation engine.

hyperdoc.khinsen.net/94FE4-micrograd

I have written this as a real-life example of explorable explanations in HyperDoc, my framework for explainable software systems which I demoed at a meetup earlier this year. The main new features in the platform that are showcased are interactive tools and much-improved playgrounds for free exploration.

Feedback welcome at codeberg.org/khinsen/micrograd (the source code repository), or right here of course.

📝 micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it

Konrad Hinsen 2025-11-13 06:20:26

Here's a blog post placing my HyperDoc project in the context of Bret Victor's "explorable explanations", with Micrograd supplying the illustrations: blog.khinsen.net/posts/2025/11/12/explorable-explorable-explanations.html

Mariano Guerra 2025-11-14 14:28:21

Performant Syntax Highligthing with CSS.highlights API and OhmJs

Quick overview showing how to generate small and performant syntax highlighting for your own programming languages using OhmJs and the new CSS.highlights API

🎥 Performant Syntax Highligting with CSS.highlights API and OhmJs

Performant Syntax Highligting with CSS.highlights API and OhmJs

Ivan Reese 2025-11-14 15:51:31

This is really cool. I'm excited to play with this.