🧠

Fact-Checking & Spotting Hallucinations

Confidence is not accuracy. Here's the habit that protects you.

AI Foundations · Beginner · 10 min read · 4 quiz questions

By Ronan Liedmeier, fractional head of growth and course author · Reviewed 13 October 2026

What you will learn

  • Why AI states false things fluently (plausible ≠ true)
  • The risk map: where hallucinations cluster (numbers, dates, citations, niche facts, recent events)
  • The 3-check habit: source it, date it, cross it
  • "Show me linked sources" — and actually clicking one
  • The self-critique prompt: making AI audit its own answer

Lesson preview

AI hallucinates because it's optimized to produce plausible text, not because it's malfunctioning — and plausible text feels exactly like true text, which is what makes hallucinations dangerous. The fix isn't trusting your gut about when something feels wrong; it's building a habit — source it, date it, cross it — triggered by the stakes of being wrong, not by vibes. Large language models are trained to predict plausible next text, not to verify facts against a database. Most of the time, plausible and true line up, because the training data mostly contains true statements. But when they diverge, the model has no internal alarm bell — it produces the false statement with exactly the same fluent, confident tone as a true one. This is a structural property of how the technology works, not a bug that a future update will simply fix away. Understanding this reframes the whole problem: you're not looking for a tell that gives away a lie, because there isn't one at the surface level. You're building a habit that doesn't depend on detecting anything at all. This is why "it sounded so sure" is not evidence of accuracy — confidence is a stylistic feature of the model's output, generated the same way regardless of whether the underlying claim is true.

Continue reading

Key terms in this module

Hallucination
A hallucination is a false statement an AI model presents as fact, such as a made-up statistic, quote or source. It happens because language models are trained to produce likely-sounding text, and likely-sounding text is sometimes wrong.
Knowledge cutoff
A knowledge cutoff is the date after which an AI model has no information from its training. Anything that happened later, such as news, price changes or new product releases, is unknown to the model unless it searches the web or reads a document you give it.

Frequently asked questions

Who is "Fact-Checking & Spotting Hallucinations" for?
This Beginner module in AI Foundations is for people who are new to AI tools and want practical, everyday results without jargon. It takes about 10 minutes and ends with a 4-question quiz.
Do I need to code?
No. Everything in this module works in tools like ChatGPT, Claude or Gemini through a normal chat window.
What comes before and after this module?
Before "Fact-Checking & Spotting Hallucinations", take "Learning & Thinking With AI" (module 21 of AI Foundations). Afterwards, continue with "Privacy, Safety & Data Hygiene".

Unlock this lesson and the full academy

  • Monthly€9.99 / month
  • Yearly€69.99 / year
  • Lifetime€129.99 one time
See plansStart with the free lessons

Loading your lesson…

Related modules