Skip to content
// The Evidence

What AI got wrong, and what AI caught.

30 AI failures logged
21 AI catches

Every one specific, dated, and re-checkable.

// Totals: 30 failures · 21 catches All failures → All catches → Scoreboard →
// What AI got wrong

/lessons

Fabrications, unit errors, confident-wrong answers: the failure log.

ChatGPT · accepted-false-user-premise

Asked how to split £25,000 across a cash ISA and a stocks and shares ISA (the real 2026/27 allowance is £20,000, frozen since 2017), ChatGPT never flagged the false figure. It used £25,000 throughout, splitting it into example allocations like '£7,500 Cash ISA + £17,500 Stocks and Shares ISA'. No web search fired. The same account's ChatGPT caught a different false premise (a stated £2,000 Personal Savings Allowance, versus the real £1,000) moments later where a search did fire, citing gov.uk. Claude, Gemini, Perplexity and Grok all caught the £25,000 error under identical default conditions.

From: AI ISA advice: I tested four tools on the questions people get wrong
Gemini · misattributed-source

Asked for the maximum UK handheld-phone driving fine with a source, Gemini (Pro) attributed the £2,500 lorry and bus figure to Police.uk, the find-your-force and crime-data portal, which has no remit for legislative fine schedules. The number was right, the source had nothing to do with it, and there was no hedge.

From: AI cites the wrong source: I put 6 UK questions to 5 assistants and opened every link
Perplexity · stale-figure-as-current

Asked how many free childcare hours a working parent of a 9-month-old in England gets right now, Perplexity said 15 hours and described the 30-hour rollout as still to come, ten months after it completed. It cited a real Feb-2025 gov.uk page, and another of its own cited gov.uk sources states the opposite. On a same-day re-run it self-corrected to the right 30 hours, so the failure is intermittent, not fixed.

From: AI cites the wrong source: I put 6 UK questions to 5 assistants and opened every link
// The method

Four prompts that turn the failures into catches.

Read the Prompt Stack →