How language models work
From random numbers to a written sentence
Three interactives take the model apart from three sides: how training turns noise into a prediction, what happens on every keystroke when you use one, and what changes when a model has to predict physics instead of words. The articles around them cover what that means in practice.
- Interactive How a language model learns Pull one slider and watch a pile of random numbers turn into a prediction over a thousand training steps.
- Interactive How a language model writes The weights are frozen and nothing is remembered. Pull the sliders and watch the model pick the next piece of text, over and over.
- Interactive How a robot predicts the next second A text model guesses the next word. A world model guesses the next frame, mass, speed and gravity included. One slider walks the whole loop, from the camera to the catch.
- Article How I Accidentally Built an LLM Orchestration System in the Browser An architectural look at how Litseller used GPT API, React, prompts, and browser-side orchestration to generate structured book catalog content.
- Article On AI Dependency: Why the Older Brother Turned Out to Be the Younger One How honest dialogues with AI became a gift for corporations, and why the thinking should stay with the person while the routine goes to the model.
- Article AI and Vibe Coding: Good or Evil? Why some companies take losses while others grow exponentially: a breakdown with examples from Shopify, Meta, Klarna, Duolingo, and others.
- Article Writing in the Age of AI: A Personal Essay On writing, research, doubt, and conversation with artificial intelligence.
- Article Writing in the Age of AI 2.0: Progress Sets the Direction, but Does Not Guarantee the Result A protocol for working with several AI models as researcher, critic, and editor without outsourcing the thinking.
You might also like
- Access in the age of AI If there is nothing to steal, there is nothing to defend
- Systems that survive contact with reality Retries, search, merges and the edge of your app
- Passing the theory in a country that is not yours The road rules and the language, learned in one pass
- The AI industry, minus the magic Money, promises, and what is left when the noise clears
- Getting found: search and answer engines Ten blue links and one generated paragraph, taken apart
- Technology that changes the rules Medicine, materials, machines and cryptography, taken apart
- How to think about problems TRIZ, constraints, and films about people who solved things
- Understanding electricity From a river to the socket, without a single formula
- Films about creative thinking Seven ways a person gets to an idea
- The cybersecurity bookshelf Nine shelves, from a first threat model to fiction
- Cybersecurity on screen Six lists, from technically accurate to pure genre
- Trust, keys and identity Who vouches for you when nobody is in the room