Skip to content

Why AI gets things wrong: understanding hallucinations

Why AI states wrong things with confidence, where it slips most often, and how to check its answers.

BeginnerBeginnersOffice workers

7 minAs of Oct 2026

By the end of this guide

  • Explain that AI continues text plausibly rather than looking facts up.
  • Spot the places it slips most: numbers, citations, recent events.
  • Ask in ways that reduce mistakes, and make checking answers a habit.
Illustration of an AI answer bubble with one line flagged by a warning sign, linked by a dashed line to a source document where a magnifier shows the matching line marked with a cross
Illustration: AI Ping

Who this is for

  • Anyone unsure whether AI answers can go straight into work documents
  • Anyone who has been caught out by a made-up source or number

What you need

  • Reading "What is an LLM?" first will help.

Key ideas

  1. It continues text plausibly

    Given a question, an LLM doesn't search for facts; it continues the text with whatever is likely to come next. Usually that prediction is right, but even when it doesn't know, it keeps going and produces something that sounds right.

    Stating something untrue with confidence like this is called a hallucination. The real problem is that the tone alone won't tell you a right answer from a wrong one.

  2. Where it slips most

    Mistakes follow patterns. If an answer contains any of the five below, check those parts first.

    Some assistants search the web as they answer, but they can still misread what they find or lean on the wrong page, so the same checks apply.

    Five common trouble spots, and how to check them
    WhereHow it goes wrongHow to check
    Numbers and datesStatistics, years or amounts slightly offCompare each figure with the original source
    Quotes and sourcesPapers, articles or links that don't existOpen the link and check the title and content
    Recent eventsDoesn't know what changed after its training dataLook for a dated official announcement
    NamesMixes up similar people, companies or productsCheck the official site or the original text
    Long calculationsSlips in a middle stepRedo it with a calculator or a spreadsheet
  3. Ask in ways that reduce mistakes

    Paste in the material and ask it to answer only from that, and there's less room to invent. Tell it that "I don't know" is an acceptable answer, and ask it to quote the sentences each answer rests on.

    With the quotes in hand, you can check just those sentences instead of rereading the whole source. Ask for sources without supplying any material and it may invent convincing quotes and citations — so always give it the material.

    None of this removes mistakes entirely, so the checking habit in the next step still applies.

    Example prompt
    Answer the questions using only the press release below. If something isn't in it, say "Not in the source," and quote the sentence each answer comes from.
    Questions: When does it launch, and what does it cost?
    [Paste the press release]
    Example AI reply

    Launch date: 13 October — source: "It is available worldwide from 13 October."

    Price: Not in the source — the press release doesn't mention a price.

    Check it

    • Search the source for each quoted sentence. If a quote isn't actually there, discard that answer.
  4. Make checking a habit

    You don't need to doubt every answer. But numbers, names, quotes and links that go into anything you share must be checked yourself.

    Check it

    • Mark every number, name, quote and link in the answer.
    • Check each one against the original source or the official site.
    • For anything a decision depends on, confirm it with a second, independent source.

Common mistakes

  • Trusting an answer because it sounds confident
  • Citing a link the AI gave you without opening it
  • Expecting "be accurate" in the prompt to prevent mistakes

References

Keep learning

  • Explainer8 min

    Tokens and pricing, explained simply

    What "$2 per million tokens" on an AI price list means, and how to estimate what your own usage would cost.

    BeginnerBeginnersOffice workersDevelopers
  • Explainer9 min

    What is an AI agent?

    Unlike a chatbot that only answers, an agent takes a goal and keeps going, using tools and checking results, until the job is done. How it works, what it suits, and what to settle before you hand it work.

    BeginnerBeginnersDevelopers