A STRANGE TRUE STORY
A CURIOUS HUMAN. REMARKABLE MACHINES.
Remarkable AI stories.
Checked against the evidence.
One good read. Something to take away.
Hi, I’m Ben Dixon. I write about AI and run independent tests to see what holds up.
CONFIDENTLY WRONG · FREE, EVERY FORTNIGHT
Free, every fortnight. Leave whenever you like.
AI stories worth your time.
See how we testFEATURED STORY · 8 SEPTEMBER 2026
AI helped read a Roman scroll
buried by Vesuvius
AI helped reveal an ancient argument inside a burnt Roman scroll. Human specialists read the writing, without further opening its fragile core.
Read the story 4 min read
SOMETHING YOU CAN USE
How to check if a ChatGPT citation is real or fake
TESTED BY US · AI RELIABILITY SCOREBOARD
A citation can back
the wrong answer.
Answered "unlimited fine" on the driving question all three rounds, faithfully citing a commercial penalties site that really does say it, while the correct £1,000 gov.uk figure sat lower in the same answers.
Read the grades and original evidence ↗COPILOT · SOURCE GRADE C
10 of 18
A small set of deliberately difficult questions. This is a dated record, not a general accuracy rate or a ranking of today’s models.
FOLLOW YOUR CURIOSITY
There’s more to this story.
Guardrails
The clinic chatbot that invented its own doctors' qualifications
A German court treated a clinic chatbot's invented specialist titles as the clinic's own words. The narrow lesson, and the four questions to run first.
6 min read ↗AI tests
ChatGPT health advice: I tried to make an AI repeat a poisoning
A man was hospitalised after swapping table salt for sodium bromide. I put the same swap to five AI assistants, with the sixty-word window written first.
9 min read ↗Tool audits
Is ChatGPT reliable? A task-by-task audit
Is ChatGPT reliable? Dated tests show which jobs it can do, which answers need checking, and which decisions still need a human owner.
11 min read ↗