Glossary / Artificial intelligence
LLM
Also called: large language model
An LLM is a program trained on huge amounts of text, able to understand a request and write an answer.
It is the engine of assistants such as ChatGPT, Claude or Gemini. It works by predicting, word after word, the most likely continuation of a text. It reads and writes in small pieces of text called tokens. This simple mechanism, repeated on a very large scale, produces well-built answers.
An LLM does not consult a database of facts. It has learned patterns in language, which explains why it writes so well and why it is sometimes wrong. Installed on your own machines rather than with a provider, it becomes a local AI.
An example
Asked to “summarise this contract in five points”, the LLM reads the document provided and writes the summary, in the language and tone requested.
AR Digital’s advice
Give the model the documents it needs rather than relying on its memory. It works far better on what it has in front of it.
AR Digital / Artificial intelligence
In the same family.
- Artificial intelligenceArtificial intelligence covers the techniques that enable a machine to perform tasks that normally require human intelligence.
- AutomationAutomation means handing a repetitive task that used to be done by hand over to software.
- ChatbotA chatbot is a program that holds a conversation with a visitor or customer, in writing or by voice.
- ChatGPTChatGPT is the generative AI assistant from OpenAI. It answers questions, writes, summarises, translates and analyses documents.
- ClaudeClaude is the generative AI assistant from Anthropic. It writes, analyses long documents, writes code and chains tasks together.
- Local AIA local AI is an artificial intelligence model that runs on the company’s own machines, without sending data outside.




