Skip to content

LLM (Large Language Model)

An LLM is a large language model trained on enormous text volumes that can generate, summarise, and analyse text in a human-like way.

Also known as: language model, large language model

An LLM (Large Language Model) is an artificial intelligence model trained on billions of words of text, capable of generating, summarising, classifying, and analysing text in a human-like way. Examples include OpenAI's GPT series, Anthropic's Claude, and Google's Gemini. For businesses, LLMs are the engine behind chatbots, document analysis, email sorting, and content generation. They have limitations: they occasionally "hallucinate" (generate plausible but incorrect answers), and they cannot know things that were not in the training data — which is why they are often combined with RAG.

In Norwegian context

Modern LLMs understand Norwegian Bokmål well and Nynorsk reasonably well. For particularly sensitive data, smaller locally-runnable models can run on Norwegian infrastructure.

Read more in the in-depth article on this topic.

Related terms

  • RAG (Retrieval-Augmented Generation)RAG is a technique where a language model answers based on the business's own documents — instead of only its general training.
  • AI agentAn AI agent is software that sets goals, plans steps, and acts autonomously to achieve them — without continuous human oversight.
  • Fine-tuningFine-tuning is the process of further training an existing AI model on specific data to improve performance for a narrow use case.
No commitment · 30 min · Free

We build what you need. Let's figure out what that is.

Send us two sentences about what's grinding. You'll hear back today, and we'll tell you whether this is something we can help with.

You can change these choices at any time. Necessary is always on because it is required for the site to work.

Necessary

Required for basic functionality, such as remembering your consent choice. No tracking.

Statistics

Anonymised visit statistics via Google Analytics 4. Helps us understand which pages people read.

Product insights

Detailed behavioural analysis via PostHog, including session recording with masked input fields. Used to improve the user experience.