LLMs · hallucination
Why AI makes things up
🎓 School maths · Years 7–8Probability — Reason about uncertainty and unseen (zero-frequency) cases.Maths by year →
The Case. Chatbots sometimes answer confidently — and are totally wrong. That's called a hallucination. Why does it happen?
Your tools. Our tiny model only learned about the sky, grass and sun. We'll ask it about the moon — which it never saw.
Investigate. Press Run. It has no real answer, so it guesses anyway and sounds sure of itself.
- A language model always produces something — even when it doesn't actually know.
- That's why we double-check AI: confident is not the same as correct.
your_code.py
Starting Python…
The Reveal
Starting Python… (first time only — a few seconds)
🗒️ Detective's notes
Bundles your findings, chart and code into one PDF you can keep, print or hand in.
🧩 How this code works
The tools it uses
- random — makes lucky, unpredictable choices — like rolling a dice.
What this one does
- • It uses chance and randomness.
How to read it, top to bottom
- 1. Import — bring in the tools (listed above).
- 2. The data — the lists and numbers near the top. These are the bits you change.
- 3. The work — a little maths, or a loop that repeats a step.
- 4. Show it —
print(...)writes words;plt.show()draws the picture.
Use it for your own problems
- Change the numbers at the top and press Run — nothing breaks, so experiment!
- Ask your own version of the question — swap in your family, your scores, your week.
- The same tools work on any numbers — that's the superpower you're learning.
Need a hint?
Because 'moon' isn't in what it learned, it falls back to a random known word — and states it confidently.