AI Made Crystal Clear · chapter 3: How an LLM Works, With No Math
Training and inference
2026-09-14
The factory runs once: mountains of text tune billions of dials, then the settings freeze. The storefront runs on every request: your prompt goes through the frozen model's prediction loop and the answer is generated live, metered in tokens.
Below: the paragraph from the book that builds this idea, then the diagram itself (Figure 3.2), and a recap. About a minute of reading.
The factory and the storefront is the picture to keep. The factory ran once and produced the product. The storefront serves customers all day, every day, using that finished product. This figure puts the two phases side by side.
Recap
- The idea: The factory runs once: mountains of text tune billions of dials, then the settings freeze.
- The picture: Figure 3.2, from chapter 3 ("How an LLM Works, With No Math") of AI Made Crystal Clear.
- Go deeper: the chapter builds this step by step, with recipes and sources at the end.
This diagram is one of many in AI Made Crystal Clear.
Every chapter opens with the gist, draws the hard ideas, and ends with recipes and sources.
Get the book
