Hallucination

Garden · not yet reviewed Established: widely used Widely discussed since 2022

When AI states something false or invented, such as a statistic, quote, source or policy detail, with the same confidence as something true.

Also called: making things up · confabulation · fabrication · AI errors · fake citations

Connections

Understand first

Ideas this one builds on.

• Large language model (garden)

Leads on to

Ideas that build on this one.

• Verification (garden)

Related

Often used together or easily confused.

• Sycophancy (garden)
• Jagged frontier (garden)
• Deep research (garden)

Skills that use it

• /prove-it (garden)

Blueprints that practise it

• Hire and onboard an AI copilot for one piece of work (garden)
• Teach your AI assistant your team's jargon, one confirmed term at a time (garden)
• Turn messy notes into a status draft you can check (garden)

Resources that teach it

• AI Capabilities and Limitations (garden)
• An AI glossary (garden)
• Beyond vibe checks: A PM's complete guide to evals (garden)
• Getting started with AI: Good enough prompting (garden)
• Evaluating AI for high-stakes work (garden)

Competency

• Check the result

Find hallucination on the commons map ↗

You may know it from

• psychology confabulation People with memory gaps sometimes fill them with detailed, sincere, invented stories.
• law a confident witness who misremembers Confidence and accuracy are different things; courts learned to look for corroboration.

In plain words

Language models produce likely-sounding text. Most of the time, likely and true line up. Sometimes they don’t, and the AI produces a made-up statistic, a quote nobody said, a court case that doesn’t exist, or a policy rule that sounds right for your organisation but isn’t. It doesn’t flag these.

Hallucinations are most common with specific details: numbers, names, dates, citations, and anything niche or very recent. They are rarer, though still possible, when the AI works from material you gave it.

The tone of an answer tells you nothing about its accuracy. What helps is knowing which kinds of claims need checking and having a quick way to check them.

Example

A communications lead asks for “three statistics on volunteer retention with sources.” One source is real, one is real but says something different, and one doesn’t exist. She keeps the real one and replaces the others with figures from a report she trusts.

How it connects

• A direct result of how a large language model predicts text.
• Often confused with sycophancy, where the AI bends facts toward what you want to hear.
• Verification is the habit that catches it; the jagged frontier explains why it appears on some tasks and not others.

Try it

Ask your AI tool a factual question about your own field where you already know the answer. Write the correct answer down first, then compare. Repeat with a very specific detail, such as a date or a figure.

---

Read this card as plain Markdown: /concepts/con-hallucination.md. Know a parallel from your own field, or a product that implements this? Add it.