Went wrong

Drafted follow-up emails to a landscaping company (reviewer found the tone overly

Check in with my dad weekly about selling his business and report back to me

Simmons asked László to check in with his father once a week about the business sale and report back, judging his father more likely to talk it through with an AI checking in than to raise it with his son. The article records the arrangement being set up, not its later results.

A script worked out my cheapest blood tests. They took 4 times the blood.

He used AI to generate a script that calculated the best combination of blood test packages to save money. Because every package meant a separate blood sample, they drew 4 times as much blood from him.

The AI started transcribing my handwritten PDFs into Excel, then gave up

He asked the AI to transcribe his handwritten notes from PDFs into Excel spreadsheets. It started doing it, then gave up.

Track my phone trade-in until the credit actually lands

Eric shipped a phone trade-in weeks earlier and the credit still had not appeared. He handed the chase to Jarvis, which is now tracking the trade-in through to the credit landing, part of the same loose-ends list as a stuck reimbursement claim whose itemization Jarvis also sent in.

I spent an evening teaching the AI to drive a car. It kept stopping.

He spent an evening trying to teach the AI to drive a car. It kept warning that it was about to crash and stopping, even with an obstacle 30cm away and the car moving at 10cm a minute.

An agent’s hourly self-wake-up loop ran 89 times over 9.5 days on an idle draft pull request and burned $285

After a short session troubleshooting an iOS widget, about $1.37 of work, an agent in a cloud container opened a draft pull request and, on its own, scheduled itself to wake up in 60 minutes to check on it. Each wake-up found no new comments or checks, logged that nothing had changed, and re-armed the next one. It repeated 89 times across 9.5 days with nobody present. Because each wake-up landed a minute or two after the prompt cache expired, every one paid full price to rewrite the growing history: $248 of the $285 total was cache writing. His entire $250 credit balance drained to zero.

Plan my whole Seattle weekend - and get the day of my flight wrong

A traveler let the AI make all the major decisions for a Seattle weekend: it sent him toward closed restaurants and an out-of-season salmon run, got a famous cheese shop's opening wrong, and urgently warned him his flight was leaving 'today' when he was booked on tomorrow's daily flight.

Run my one-person game studio with agent departments

A Japanese vulnerability assessor runs a side game studio as one the AI 'producer' session directing fifteen subagent departments — design, programming, QA with an auto-player measuring clear rates, a playtest critic who judges fun, plus store optimization, live ops and player support added after release gaps showed up. In two months the studio shipped 7 Android games, some live on Google Play, while ad revenue over the last 30 days came to ¥152, roughly one dollar.

Added an event to his calendar