Plain-language explainer
How LLMs work, without the math
How does a large language model actually work?
A large language model is a next-word predictor. It turns your text into numbers, runs them through billions of learned weights, and produces a probability for every possible next token. It picks one, adds it to the text, and repeats. There is no database of facts and no lookup step. The intelligence is a very good statistical guess about what comes next, learned from a huge amount of text. Everything else, chat, code, agents, is built on that one loop.
Do not just read it. Operate the mechanism yourself in a short interactive lesson.
See it work: How does an AI think? →Free, no code, no signup.
What people get wrong
- It looks answers up in a stored database. It does not. It predicts likely text, which is exactly why it can be confidently wrong.
- It understands the way a person does. It models patterns in language, not lived experience or meaning.
- Bigger is always smarter. Scale helps, but training data quality and how you use the model matter just as much.
Where you see it in real products
- Chat assistants generate each reply one token at a time.
- Writing and autocomplete tools rank the next word the same way.
- Coding agents wrap the same predictor in a loop that can run tools.
Related explainers
Part of See How AI Works, a free interactive course, where you learn how modern AI works by operating it, not watching videos.