What is an AI hallucination?
Published . Updated .
Hallucination: A response from an AI model that presents false or misleading information as if it were fact.
Hallucinations happen because a language model produces likely text, and likely is not the same as true. Retrieval and grounding reduce them by giving the model real sources to work from, though they do not remove them.
For a site owner, a hallucination about your product is a reason to publish the plain facts on a page an assistant can find and cite.
Read next
- What is grounding in AI?
- What is a large language model (LLM)?
- How do AI citations work in ChatGPT, Claude and Grok?
Sources
See the fan-out for your own prompts
Only Fan Out is a free Chrome side panel that lists the queries, fetched pages and cited pages behind each ChatGPT, Claude or Grok answer. Nothing leaves your browser.
Add to Chrome, it's free