An AI hallucination is output from a generative model that is fluent and plausible but factually incorrect, fabricated, or unsupported by any real source. It arises because language models predict likely text rather than retrieve verified facts.
Why it matters
Hallucinations are the central reliability problem for using AI in knowledge work: a confidently wrong citation, statistic, or quote can be worse than no answer at all, especially for consultants and researchers whose output is trusted. Because hallucinated text often reads as authoritative, it is hard to catch without checking against real sources. Reducing hallucination is the main reason grounding and retrieval techniques exist.
How Pith relates
Pith is built around source grounding: its wiki and briefings are assembled from material you actually bookmarked, and claims carry citations back to the original source so they can be verified. By keeping the source attached to every answer it serves, including over its MCP server, Pith makes unsupported claims easy to spot rather than letting them blend in. It reduces hallucination risk but does not eliminate it, so verification against the cited source still matters.
See also
Last reviewed: 7 June 2026 · Licensed CC BY 4.0 · cite freely with attribution to Pith.