Lesson 1 of 6
What Is a Large Language Model?
Every AI assistant runs on an LLM — a model trained to predict the next token. This lesson demystifies what that means and what it doesn't.
Learning objectives
- ▸Define a large language model in plain terms.
- ▸Explain next-token prediction at a high level.
- ▸Separate the model from the product built around it.
The lesson
Read the full lesson →What Is a Large Language Model (LLM)?A large language model (LLM) is an AI system trained on vast amounts of text to predict the next token, which lets it generate fluent language, answer questions, and power tools like ChatGPT, Claude, and Gemini.3 min readKey takeaways
- ▸An LLM predicts the next token, scaled to billions of parameters and trillions of words.
- ▸The model (e.g. GPT-5.5) is distinct from the product (e.g. ChatGPT) around it.
- ▸LLMs model patterns in language — they don't 'understand,' which is why they can be confidently wrong.
Knowledge check
Knowledge check
0 / 3
1. What does an LLM fundamentally do?
2. Is ChatGPT the same as the LLM?
3. Do LLMs 'understand' language like people?