Glossary · 1 · Foundations: how AI works
Large language model (LLM)
Also known as: LLM, Language model
A large language model (LLM) is a generative AI model, usually a transformer, trained on very large amounts of text to predict the next token in a sequence. From this single skill emerge abilities such as answering questions, summarizing, translating, writing code and following instructions.
- Beginner
- Technical writers
- Technical marketers
- Technical project managers
- Developers
In one sentence
What a large language model is: a transformer trained on vast text to predict the next token — the engine behind ChatGPT, Claude, Gemini and Llama.
Example
Asked “Summarize this maintenance procedure in three steps,” an LLM generates the summary token by token, each token chosen as a likely continuation of the prompt and what it has written so far.
Explained in context
Context cards connect this term with others to answer one question. Also in British English and German.
- The machine is a network, not a monsterWhen an AI answer is wrong, why is “the machine got it wrong” no diagnosis?UKDeutsch
- AI systems and the machine: scope and out of scope of every levelWhere do a company's AI systems end, where does the machine reach into them, and what lies outside every configuration?UKDeutsch
Why it matters on your learning path
- Technical writers: LLMs read your content as tokens. Consistent terminology and clear structure make their answers more accurate.
- Technical marketers: Most AI brands in station 2 sell access to LLMs; the differences lie in quality, price, openness and data terms.
- Technical project managers: LLMs are probabilistic: the same prompt can give different answers. Plan acceptance criteria and review accordingly.
- Developers: You’ll work with LLMs through an AI API, managing tokens, context and cost.
LLM vs. chatbot
The LLM is the model. A chatbot or assistant such as ChatGPT, Claude or Gemini is a product built around one or more models, adding a system prompt, memory, tools and safety layers.