Book a call

Daniel & Friends / Glossary / Large language model (LLM)

AI and automation

Large language model (LLM)

A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer. ChatGPT, Claude and Gemini are built on such models.

Daniel Votruba ·


In practice

Always check the output of a model for numbers, names and quotes. It handles language very well, and facts sometimes slip.

Read more: The most popular AI tools of 2026, by category

Related terms

  • Prompt: A prompt is the instruction a model receives.
  • Hallucination: A hallucination is a case where a model states plausible-sounding but false information.
  • Context window: The context window is the amount of text a model can process at once, including the instruction and the answer.
  • RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.

More terms in the group AI and automation

Machine learning (ML) · Jailbreak (AI) · MCP (Model Context Protocol) · Inference and latency · Model bias (AI bias) · Human in the loop · Model evaluation (evals) · Multi-agent system · Guardrails · Multimodal model · Grounding · Neural network · Generative AI · NLP (natural language processing) · Function calling (tool use) · No-code and low-code · Foundation model · Open-weight model · Fine-tuning · Predictive analytics · Few-shot and zero-shot prompting · Explainable AI (XAI) · Prompt engineering · EU AI Act

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.