Skip to content
Newsletter →
// AI reliability, tested

Five AIs, one real question. I show you which answers hold up.

I put ChatGPT, Claude, Gemini, Perplexity and Grok through the same checkable questions and grade every answer against the source. Receipts, not vibes. One email a fortnight.

// The Lessons30 documented failures // Latest test:
  1. 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…

  2. 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…

  3. 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…

All evidence
Ben Dixon
// The author

I test how far you can trust the main AI assistants, and I publish exactly where they get things wrong. Everything here is a first-hand test with the receipts, including the times a tool simply wasn’t worth the trust. More about me →

// Which AI can you trust?
1 Claude 6/6 right · Strong
2 Gemini 5/6 right · Strong
3 Grok 5/6 right · Strong
4 ChatGPT 5/6 right · Strong
5 Perplexity 4/6 right · Mixed
objective core, 6 questions, N=3, 2026-06-25 See the full board →
// free tool Make your AI admit when it’s guessing. The problem isn’t that it’s wrong sometimes. It’s that it sounds just as sure when it’s guessing, with no tell. The fix is four lines you paste into any AI you use, ChatGPT, Claude, Gemini or Grok. Same model. It just flags its guesses instead of slipping them past you. Get the Bluff Filter, free →
// The State of AI Reliability

Every AI was right on the facts you can look up. Every mistake was on the data that moves.

Live, moving data a closing price, a live quote

3 of 10 a confident error

Fixed public-record facts a filing, a base rate, an index yield

0 of 20 — every one clean

5 assistants, 6 checkable questions, N=3, 25–26 June 2026. A documented index, not a benchmark. Read the full report →

Worth a look

// a curated few
AI Tests Most read

ChatGPT vs Claude vs Perplexity vs Gemini for stock research: Gemini faked the options chain

23 min read
AI Tests ★ Just for fun

Which AI picks the World Cup winner? I asked five

5 min read
Prompt Stack

AI quality of earnings review: 4 prompts to find the real profit

10 min read
Tool Audit

Is Grok good for stock research? I ran the same test on the fifth tool

14 min read
// New here? Start here
4 parts · ~14 min · no jargon

Four short reads, and you’ll have a check you can run on any AI answer.

The kind you’d want on a contract, a letter from a doctor, or an email you’re not sure about.

Start with part 1 →
  1. 01 How to tell if an AI answer is true in 30 seconds
  2. 02 The whole method, in four questions
  3. 03 Make it show its working
  4. 04 Where I actually use this
// See all four parts →
// Latest · 4 new this week
AI Tests

I opened a private AI chat. It still knew my name and my rough location.

I asked three AI tools a generic question in their private modes. Perplexity greeted me by my first name and placed me near a city 30 miles away. Here's what private really means.

New · · 11 min read
AI Tests

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

I asked five AI assistants six everyday UK questions, made each one cite a source, then opened every link. Three cited a real page that didn't back the claim.

New · · 13 min read
AI Tests

Which AI picks the World Cup winner? I asked five

Which AI predicts the World Cup winner? I asked five assistants on the same day: four said France, one said Spain, and none of them hedged.

New · · 5 min read
// Archive
AI Tests Does AI change its answer when you push back? I told five AIs they were wrong New · 9 min AI Tests How often is ChatGPT wrong? I kept a running tally across 20 real AI tests · 11 min AI Tests I let three rival AIs audit my own AI method. They agreed on the weak step. · 4 min Tool Audit Is Grok good for stock research? I ran the same test on the fifth tool · 14 min AI Tests I run an AI to catch AI mistakes. It fell for a fake. · 6 min AI Tests Real AI hallucination examples, caught and dated · 14 min
Browse all →
// By topic Prompt StackTool AuditGuardrailsAI Tests

// The Method Four prompts that stop AI inventing the answer.

Read →