Hallucination
Category: Fundamentals“huh-LOO-sih-NAY-shun”
When an AI confidently gives an answer that is simply made up.
Lesson #2: Working With AI: Prompts, Data & Guardrails →A confident coworker who'd rather guess than admit they don't know.
An AI inventing a book title that was never written.
An AI citing a building code section number that doesn't exist.
An AI quoting a refund policy your company never had.
AI can be wrong while sounding certain — always verify facts that carry money or legal risk.
A hallucination is a confident AI answer that isn't true.
Ask an AI a very specific factual question about your industry, then check the answer against a real source.
Hover or focus a choice to preview the new review date.
Exercises by category
- Agents0/21 · 0%
- Models0/10 · 0%
- Data0/11 · 0%
- Infrastructure0/22 · 0%
- Fundamentals0/15 · 0%
- NobleHub0/20 · 0%
Next badge: First Nail — 1 more exercise
Related terms
Picked automatically from the same category and the ideas this term shares.
Hand-picked pair
A method where the AI looks up your real documents before answering, instead of guessing.
Hand-picked pair
Adjusting an AI system so its answers become more accurate and reliable.
Hand-picked pair
The rules and limits you set so an AI stays safe and on task.
Same category: Fundamentals
The skill of writing instructions that get better answers from AI.
Same category: Fundamentals
The instructions or question you give an AI so it knows what you want.
Same category: Fundamentals
Testing an AI against known-good examples to measure how often it gets things right before you trust it.