Skip to content

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 / Contact

A project behind this word?

Thirty minutes, by video call or at the agency, to go from the definition to your own case. We tell you frankly what we would do, at what price and with what funding.

Radu Ulea, founder of AR Digital

Radu Ulea

Founder, AR Digital

“We tell you what works, what doesn’t, and what it costs. Then we do it.”

hello@ardigital.eu