Act 4 · Lesson 17 of 21≈8 minutes○ Saves on this device

Confidently Wrong: Hallucination and Uncertainty

By the end you'll be able to

  • Explain hallucination as the machine doing its normal job on questions where plausible and true diverge.
  • Predict high-risk conditions: thin coverage, specific checkable details, questions it "shouldn't" be able to answer.
  • Apply a verification habit proportionate to stakes.
⚡ 30-second warm-up — From Lesson 1: what's the difference between predictable and true?

Two separate properties. The most plausible-sounding continuation is not automatically the correct one — it's just the one the diet made most likely. Today that gap gets a name and a defence.

Revisit Lesson 1

Ask an AI for five real court cases supporting your argument. It may return five perfectly formatted citations — two of which don't exist. It didn't "lie".

Start with a real professional's mistake

Lawyers have been sanctioned — including in Australian matters — for filing briefs with AI-invented case citations: real-looking names, real-looking years, real-looking court reporter numbers. Nothing about the format looked wrong. Nothing was checked.

Commit to a prediction

Using what you already know from Act 1, what actually happened when it invented those citations?

This lesson changes one thing: you'll stop hunting for a "tell" in the tone that reveals a fabrication, and start predicting where fabrication is likely — because there is no tell, and there is a pattern.

Discover the mechanism

How it works The raffle always finishes

The raffle always draws a ticket (Lesson 4): when evidence is thick, the winning ticket is usually true; when evidence is thin, a ticket still wins — and the machine announces it in the same fluent, confident voice, because that voice was learned from confident, specific human writing (Lesson 2), not from a truth-detector. Hallucination is not a malfunction mode; it is the normal mode, operating outside its evidence.

Where it bites hardest: specific checkable facts (names, numbers, quotes, references), thin-coverage topics (your suburb, your niche, anything recent), and questions after training day without retrieval (Lesson 13). What helps: sources you can actually click through, instructions that make "I don't know" an acceptable answer (Lesson 11), and your own three-question test — is this checkable? would the training diet plausibly cover it? what happens if it's wrong? Match your verification effort to the third answer.

reported hallucination rates are falling and retrieval-grounding helps — but the tendency is structural to prediction machines, not a bug awaiting a patch; treat any specific rate figure as a snapshot. Lesson 18 asks what happens when the answer is accurate to the data, but the data carries the world's tilt.
Useful mental model An improv actor who is never allowed to break character

Ask them anything — their character answers, instantly, specifically, in a confident voice, because the show must go on. Marvellous for scenes; catastrophic if you mistake the performance for testimony.

  • Improv skill = fluent pattern continuation (Lesson 1). Never breaking character = the structural default to always produce output.
  • The confident, specific voice = tone learned from confident, specific training text (Lesson 2) — its style, not its evidence.
  • Where it breaks: a real improv actor knows they're inventing and could stop; the model has no such awareness — no inner distinction between its true and invented statements, which is precisely why it can't reliably flag its own fabrications.

Judge the gauntlet yourself

Conceptual illustration — six fixed, pre-verified answers, not a live model. Vote on each before revealing, and watch your own calibration build.

Your calibration: 0 of 6 judged

Where this bites at work

In the field · Kerry

Kerry asks for recommended screening intervals for a client cohort: general prevention patterns are thick territory, but the specific interval is exactly the checkable-detail category. She clicks through to the current Australian clinical guideline rather than trusting the number outright (retrieval-with-verification, Lesson 13's habit, applied here).

In health work, question three of the test almost always answers itself: verify fully.

Where the picture breaks

"Hallucinations are rare glitches that better models will eventually eliminate" is the misconception to retire. Rates are falling and grounding helps, but plausible-without-true is structural to how these systems work — the honest framing is managed, never cured. A citation or a confident tone never substitutes for checking when the stakes are real.

Now make the call

A client asks Kerry for the recommended interval between screenings for their specific risk profile. The assistant gives a confident, specific answer. What does she do?

Apply it to your work

This week, at your desk

Run the three-question test on the next specific, checkable AI-supplied fact you're about to use: is it checkable? would the diet plausibly cover it? what happens if it's wrong? Let the third answer set your verification effort.

Open the AI fact-check checklist

Prove it to yourself

Two quick questions — untimed, retryable, and they count toward ★ Mastered (completed + decision + self-check all correct). This is what defeats the feeling of "that made sense" evaporating by next week.

Explain it in your own words

Two or three sentences for a colleague. Then compare against the rubric — it checks ideas, not wording, and only you see your note.

  • Explains hallucination as normal prediction on thin evidence
  • States that confident tone is a learned style, not a truth signal
  • Names stakes-proportionate verification as the fix

Evidence & review — how we know what this lesson claims
Claim register for Lesson 17
ClaimTypeBasisReview risk
Hallucination is the normal plausible-continuation process operating on thin or absent evidenceHow it worksPrimary research literatureLow
Confident, fluent tone is a learned stylistic feature uncorrelated with factual correctnessHow it worksPrimary research literatureLow
Reported hallucination rates and the effectiveness of grounding/retrieval mitigationsProduct behaviourProvider / research benchmarksHigh — reviewed six-monthly
Real incidents of AI-fabricated legal citations submitted in court filings, including Australian mattersDocumented incidentExternal reportingMedium — reviewed six-monthly
The fact-or-fabrication gauntletTeaching deviceFixed, pre-verified illustrative itemsMedium
The improv-actor analogyUseful mental modelLimits stated in the lessonLow

Concept review due: January 2027. Product-behaviour and incident claims: six-monthly.

Where you are in the machine

You're now in the top layer — human judgement, applied to the machine's most convincing failure. Select any layer for its role, lessons and your live progress.

The machine, bottom to top: training data (2) → token pieces (3) → prediction engine (1, 4–9) → the desk (10–11) → senses (12) → live knowledge (13) → tools (14) → memory (15) → agent loops (16) → human judgement (17–21).

Next: the world's fingerprints

Invention is one failure family. The second is subtler: answers that are accurate to the data — and the data carries the world's fingerprints. Next: bias and blind spots.