Generative AI — Understand it and use it well

Guide 01 / 2

Generative AI glossary

Make sense of the words of AI to understand what these tools do — and do not do.

Reading
0%

Generative AI glossary

Artificial intelligence

A set of techniques that let a computer system perform tasks associated with human intelligence: understanding text, recognising an image, making a decision.

A spam filter that learns to recognise unwanted emails.

Machine learning

An approach where the system learns from examples instead of being programmed rule by rule.

A model trained on thousands of listings to estimate a property’s price.

Large language model (LLM)

A model trained on very large volumes of text to predict the most likely continuation of a sentence. It generates text without “understanding” in the human sense.

Prompt

The written instruction given to a generative AI. The precision of the prompt shapes the quality of the answer.

“Summarise this meeting report in five points for a management audience.”

Token

A unit of text processed by the model, roughly a word or part of a word. Usage limits and costs are counted in tokens.

Context window

The amount of text the model can take into account at once, question and answer included.

Hallucination

A wrong answer delivered with confidence. The model produces what is plausible, not necessarily what is true.

An invented legal reference or quotation.

Bias

A systematic tendency of a model to favour certain outcomes, inherited from its training data.

AI agent

A system that chains several actions semi-autonomously (search, read, write, call a tool) to reach a given goal.