Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

hallucination

A model stating a plausible-sounding but false claim with the same fluent confidence as a true one.

Hallucination is a language model generating text that is fluent and plausible but factually incorrect or unsupported -- a fabricated citation, a wrong date, a function that doesn't exist -- stated with the same confident tone as accurate output, since nothing in ordinary generation distinguishes "confident and right" from "confident and wrong."

Examples

  • Asked for a legal citation, a model might confidently produce "Smith v. Jones, 2019, 4th Circuit" -- a case that never existed, stated with the same fluency as a real one.

See also

knowledge cutoff retrieval-augmented generation (RAG)
Read the full section →
Graph settings

Calculator