Grade 7 · AI Literacy
Describe a large language model as a neural network trained on vast text that works by predicting the next token.
A large language model (LLM) is the kind of AI behind the chatbots you may have used. It is a very large neural network trained on an enormous amount of text — books, articles and web pages. From all that text it learns how words and ideas usually fit together.
An LLM works by breaking text into small pieces called tokens and repeatedly predicting the next token. Doing this billions of times lets it write fluent answers, summarise and translate. But it has no true database of facts and no understanding — it predicts likely text, which is exactly why it can sound right while being wrong.
Have a go right here. Nothing is saved and you can retry as much as you like. Create a free account when you want to save your progress and get Archie, your tutor.
Create a free account to save your progress, track mastery and ask Archie, your tutor, for a hand.
Already with us? Open this lesson in learncoach.ch for mastery tracking and Archie, your tutor.