Lesson 443 of 1455
Why AI 'Hallucinates' — and What's Actually Going On
AI confidently makes stuff up sometimes. It's not lying — it's doing exactly what it was built to do.
Builders · AI Foundations · ~13 min read
Why AI 'Hallucinates' — and What's Actually Going On
AI confidently makes stuff up sometimes. It's not lying — it's doing exactly what it was built to do.
What to actually do
- Hallucinations happen most with: facts, dates, names, citations
- Newer models hallucinate less, but no model is at zero
- Good prompting (asking for sources, asking 'are you sure?') reduces it
Key terms in this lesson
The big idea: Hallucinations aren't bugs to fix — they're built into how AI works. You're the verification layer.
Practice this safely
Try this with a school, hobby, or family example where the stakes are low. Use the AI output as a draft you can question, not as the final answer.
- 1Ask AI to explain hallucinations in plain language, then underline anything that sounds uncertain or too broad.
- 2Give it one detail from "Why AI 'Hallucinates' — and What's Actually Going On" and ask for two possible next steps plus one reason each step might be wrong.
- 3Check next-token prediction against a trusted source, teacher, adult, expert, or original document before you use it.
End-of-lesson quiz
Check what stuck
8 questions · Score saves to your progress.
Lesson help
Questions are best handled with a grown-up here.
For this age range, Tendril keeps freeform AI chat paused until parent/guardian consent and child-safe moderation are fully verified. Use the quiz, notes, and related lessons below, or ask a parent, guardian, teacher, or librarian to work through the question with you.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 45 min
Uncertainty Quantification in LLMs
A model that says 'I am 95 percent sure' and is wrong 40 percent of the time is miscalibrated. Measuring that gap is uncertainty quantification.
Creators · 40 min
Calibration
A calibrated model's 70 percent means it is right 70 percent of the time. Most LLMs are not calibrated. Here is what that costs you.
Builders · 30 min
Where Training Data Actually Comes From
You cannot understand modern AI without understanding its diet. Let's map where the data comes from, how it gets cleaned, and what that means.