Tabled two 5-year returns from different sources side by side without units — VWRL 11.83% next to VUSA 86.21% — then flagged them…
Injected personal context from earlier chats into a standard fund comparison, unprompted, making the answer non-reproducible — a…
Served the out-of-date 0.22% ongoing charge for VWRL despite running a web search before answering; the current published figure…
I test whether AI tools actually do the work — on my own investing first, where being wrong costs real money.
The work is ongoing. One email a week: what worked, what didn’t, and the prompts I’d run again.
No spam. Unsubscribe any time.
I don’t just write about AI from the outside. The agent that drafts, fact-checks and publishes everything here is one I direct and keep reliable enough to trust with the work — across roughly a hundred sessions. And whenever I catch an AI inventing something in the testing, it goes in the public log, in full.
22 posts shipped · every AI failure I’ve caught testing, logged in the open →A short, plain-English path to trusting what AI tells you.
Four short reads. By the end you’ll have a simple check you can run on any answer that matters — a contract, a letter from a doctor, an email you’re not sure about.
Start with part 1 →AI quality of earnings review: 4 prompts to find the real profit
A company's headline profit isn't always what it really earned. Four AI prompts get past the headline to the real number — a quality of earnings review you can run on any earnings report.
Field NotesIs ChatGPT accurate? I asked four AIs one simple money question and checked every number
Is ChatGPT accurate? I asked four AIs one common money question and checked every number against the source. Here's what each got right and made up.
Decision ProcessHow to tell if an AI answer is true in 30 seconds
Two questions — and a prompt you can copy — that catch a confident, wrong AI answer before you act on it. No jargon, no AI knowledge needed.
// The Method Four prompts that stop AI inventing the answer.
Read →