Hallucination

A hallucination is when an AI model states something false or made up as if it were fact.

In practice: Language models generate plausible text, not verified facts, so they can invent quotes, sources, statistics or features that do not exist. It happens most with specific details, recent events and niche topics, and it reads just as confidently as a correct answer.

Why it matters when picking a tool

Tools that show sources, answer from your own documents or search the web before answering reduce the risk but do not remove it. For anything that goes to a client, a court or a publication, pick tools that cite where each claim came from, and check the citations.