TRAIL

How a model actually works

Tokens, prediction, attention, context, and cost — the mechanics under everything else.

This is the trail for the moment you stop wanting analogies. Not “it’s like autocomplete” but what is actually happening: what the model reads, how it chooses each word, what it can hold at once, and what you are paying for.

By the end you’ll be able to explain why a model miscounts letters, why the same prompt gives different answers, why long conversations drift, and why a confident answer carries no information about whether it is right. These are the mechanics behind failures you have already met.

7 landmarks · 42 min · 0/7 explored

Begin trail
  1. 1UnderstandTokens

    Start at the input. Models don’t read letters or words — they read chunks from a fixed vocabulary, and that single design choice explains a whole family of odd failures.

  2. 2UnderstandPredicting the next token

    Then the output, one token at a time, sampled from a probability distribution. This is why the same prompt gives different answers and why an early wrong turn hardens into a confident wrong answer.

  3. 3UnderstandInside a transformer

    The mechanism in the middle: attention, which lets every token be read in the light of the others. It’s also why parameter count tells you about capacity rather than quality.

  4. 4UnderstandContext as working memory

    What the model knows about your situation is what is in the window right now. Treating that window as a designed budget is where most real quality improvements come from.

  5. 5UnderstandWhat happens at inference

    What running the model actually costs, in two phases with very different behaviour. This is where speed and price come from — and which levers genuinely move them.

  6. 6UnderstandReasoning and extended thinking

    The same next-token machine, told to spend more of it before answering. Extra “thinking” genuinely helps on multi-step problems — and the steps it shows are generated text, not a proof, which is the catch that makes the next habit matter.

  7. 7UnderstandUncertainty and confidence

    The closing habit: a model’s tone is a style setting, not a measurement. Getting a usable confidence signal takes structure from outside the model.