In their own words.
Our plain version above is ours. This is the official or expert wording we based it on.
“The production of plausible-seeming but factually incorrect output by a generative AI model”
Related words.
Context window
How much text (counted in tokens) a model can take in at once, including your question, any documents you give it and the conversation so far. Anything beyond it is not seen.
Prompt
The text (or image, or file) you give an AI model to tell it what you want.
Chain of thought
Step-by-step working that a model writes out before giving its answer. Reasoning models do this by default.
AI agent
An AI system that does not just answer but takes actions for you, such as browsing websites, running code or filling in forms, over several steps.
Token
The small chunk of text (often part of a word) that a model reads and writes. Prices, limits and context windows are counted in tokens.
Inference
Running a trained model to get answers, as happens every time someone uses a chatbot. Contrasts with training, which builds the model.