Not trying to rain on this parade. But it would be nice to know how much of this a person sat down and made. The captions all have the "X, not Y" tic, every component cites source by line number, and the site went from a post every few months to six in a week in four languages. Which all point to heavy LLM usage. It's not a crime. I'd probably use the robot to help build the thing too. It's just feels a bit icky on a Show HN.
Most of the frontend was built using LLMs, just like the frontend for almost all my projects over the past year.
LLMs handle this task much better and faster than I do.
I read the library's code and articles about its architecture, then visualized the concepts using GPT and local models.
I was pleased with the result and decided to publish it.
Honestly, I see no point in creating such visualizations manually these days - a model can do it much faster and better.
As for the articles, I write them entirely myself.
There are more of them now because I built a bot that takes posts from my Telegram channel, translates them into three languages, and publishes them to the site.
Each component links to the source code, and you can open the console to enter your own commands and watch the execution flow
reply