Module 15 · Level III · Builder

How large language models work

Tokens, embeddings, attention, context windows, temperature and training: what is actually happening when a model answers you.

7 lessons · about 1 hour

The module in 48 secondsCaptions on · sound optional

What’s inside

  1. 01
    Tokens: how a model reads text

    Models never see your words, only numbered chunks called tokens, and that explains odd spelling mistakes, surprise costs and hard limits. · 10 min

  2. 02
    Embeddings: meaning as position

    Models turn each token into a long list of numbers that places it in a space where similar meanings sit close together. · 9 min

  3. 03
    The transformer and attention

    The 2017 architecture behind nearly every modern language model, and the attention mechanism that lets every token weigh every other. · 11 min

  4. 04
    Pre-training: learning by predicting the next token

    One simple objective, repeated across trillions of tokens, produces most of what a model knows and much of what it gets wrong. · 10 min

  5. 05
    Post-training: from text predictor to assistant

    Instruction tuning and preference learning turn a raw text predictor into a helpful assistant, and explain its habits, good and bad. · 10 min

  6. 06
    Context windows, sampling and temperature

    What a model can see at once, and how it chooses each word: two settings behind a surprising number of bugs. · 11 min

  7. 07
    Reasoning models, and why hallucination is built in

    How models that think before answering use extra computation, and why making things up follows directly from how language models are built. · 12 min

Where this sits on your path depends on your assessment. Some people skip this module outright; others start here. The free placement assessment decides, and the first lesson of every module is free to read. Find your level →