Glossary

Quick, plain-language definitions of common AI terminology.

Hallucination Large Language Models

A hallucination occurs when an AI generates information that is incorrect or fabricated.

Language models sometimes produce responses that sound convincing but are factually wrong. This behavior is commonly called hallucination. Users should verify important information and avoid assuming AI-generated content is always accurate.

Prompt Prompting

A prompt is the instruction or input given to an AI system.

Prompts are how users communicate with AI tools such as ChatGPT, Claude, Gemini, and Copilot. A prompt may be a question, request, task, or conversation. The quality and specificity of a prompt often influences the quality of the AI's response.

Token Large Language Models

A token is a small unit of text used by a language model.

Large Language Models do not process text one word at a time. Instead, text is broken into smaller pieces called tokens. A token may be a word, part of a word, punctuation, or another text fragment. Token limits affect how much information a model can process at one time.