I wanted to see exactly how the X "For You" algorithm decides whether to recommend your tweet or not, so I built this 'playable' CRT-styled simulator that runs a simpler version of X's recommendation pipeline right in your browser.
It's a "playable documentary" that allows you to type raw text and watch it physically travel through tokenization, embedding, safety filtering, and final ranking, all based on the X-AI reference docs.
Under the hood it's running real local ML inference (a tiny embedding model using Transformers.js) to generate embeddings and score content on the fly - all locally on your machine.
Would love some feedback!