AI Tools Academy
0 / 117 (0%)

Prove It · Module 1: Why it lies

Where it fails most

Concept · 7 minLast checked against the live product: 13 September 2026

Errors are not evenly spread. They cluster around specific kinds of question, and knowing the clusters tells you where to look hardest.

Specifics: exact dates, figures, quotations, section numbers, names of people and papers. The model has seen the shape of these and reproduces the shape. Recent events: anything after its training cut-off, which it may not know it does not know. Niche topics: the less it has read about something, the more it fills in. Long chains of reasoning: each step is probably right; the chain may not be. Anything you have asked it to confirm: models agree with the premise of a question more often than they should.

Conversely, it is most reliable on widely-documented general knowledge, on transforming text you have given it (summarising, reformatting, rewording), and on explaining well-established concepts. Those are the tasks where fluency and accuracy mostly travel together.

Higher riskLower risk
Exact dates, figures, quotations, referencesExplaining a well-known concept
Recent events and current office-holdersSummarising or reformatting text you supplied
Niche or specialist topicsWidely-documented general knowledge
Long multi-step reasoningSingle-step tasks with a clear answer
Questions that contain an assumptionOpen questions with no premise built in

In practice. A consultant used AI to draft a market overview. The general framing was accurate and useful. Every specific market-size figure was wrong, several by an order of magnitude, and two of the four cited reports did not exist. The structure was the safe part. The numbers were the dangerous part, and they were the part the client would have quoted.

At your desk. Take a piece of AI output you have used recently. Highlight every specific: every date, figure, name, quotation and reference. Count them. Those are the checks you owe.

Write it down.

  • Specifics in my sample:
  • How many I had actually checked:
  • The one that worried me: