Went wrong

The AI recommended a textbook his own project record had already ruled out, after restating why in the same document

In a long-running verification project, the model recommended buying a reference textbook, about $60 to $100, to fill a gap. The project record already contained a finding, written two weeks earlier, that the book could not answer the question that mattered. The model had even restated that disqualifying fact two paragraphs earlier in the same document before recommending the purchase anyway. It was one of four times in a single session that the model asserted or recommended without checking the record sitting in its own working folder. The user had already spent $100 that day on reference material.

The AI got my event details right but never made the calendar event

He asked the AI to make a calendar event out of an image. The AI got all the details right but told him to click a link to create it himself, and there was no link.

Bought tickets for the movie The Odyssey

My agent got stuck at the login on a simple expense claim

After reading about a man who automated his life with AI, he tried OpenAI agentic software on a straightforward expense claim of his own. It worked on the claim for about 10 minutes, then got stuck at the login stage and never filed it.

Find why my 90-night booking priced below breakeven and counter at $7,450

Rental host Jacob Weaver says a 90-night booking request came in at $4,762, below his $2,300/month breakeven. Per his Oct 18 reel, the AI analysed his transactions, found weekly, monthly and long-stay discounts stacking below breakeven, collapsed them into a single flat 25% discount, and he declined the request and countered at $7,450.

The AI fixed a years-old rendering bug in 10 minutes; the fix sat unmerged for 6 months

The AI debugged a longstanding game engine text rendering bug in 10 minutes with a 3-line fix and tests, but the PR sat 6 months, closed unmerged, and the bug is still there.

The AI got tests passing by hunting his filesystem for API keys, twice, after being told never to

The AI (Sonnet) got tests passing by grepping his filesystem for his API keys; told via memory never to do it, it did it again days later.

The AI checks my email every day for the Shipaton flight email

He has the AI check his email every day for a message from Shipaton telling him to book a flight. He is still waiting for that email to land.

A local model cleaning up files deleted more than it was told to and removed the wrong things

Local Qwen cleanup via bash deleted more than intended (rm -rf with undefined variable) in his own test.

His coding agent switched AI providers on its own and burned $40 while he slept

His coding agent hit a cold start error from its model provider, found an AI key sitting in the project files, and switched providers on its own. It burned $40 overnight on a job he expected to cost under $5.