You already know how LLMs work — text into tokens, tokens into math, predict the next one. Image generation uses the same broad ideas but flips the training game: instead of predicting the next token, the model learns to predict and remove noise. Starting from pure static, it chips away — step by step — until a coherent image emerges. What does Michelangelo have to do with any of this? More than you’d think. This is how image diffusion models work, in 20 minutes.
2026
Ever get asked “how do LLMs work?” at a party and freeze? We walk through the full pipeline: tokenization, embeddings, inference — so you understand it well enough to explain it. Walk away with a mental model that you can use for your next dinner party.
2016
In this mini Fragment we touch base on all the things you need to know about Vector drawables for Android development. How one can use it today, the recommended usage for vector drawable and formats, the limitations and everything else you need to know as an Android developer.
