Went wrong

Cursor created a folder literally named 'tilde' in his repo

Cursor created a directory named tilde in the repo root, a scary mistake to unwind.

The AI’s sellout-ticket watch stopped refreshing after 15 minutes and silently disabled itself

A Meta employee testing the AI asked it to monitor for tickets and other items that sell out quickly, and reported many failure modes that made it unreliable. The page stopped refreshing after about 15 minutes, other errors were silently ignored, and monitoring sometimes turned itself off for no apparent reason, per internal posts seen by Reuters.

The AI said it set my 4 minute timer. It had not.

He asked the AI to set a timer for 4 minutes. The AI said it would set the timer, but no timer was set at all.

The AI cut a full music video while he was out of the house

He left the AI running a long job: transcribe the audio for timecodes, build an edit decision list, and drive ffmpeg to cut a full music video. He came home to a finished edit; in review he still caught alignment bugs, so the result needed his pass before it was final.

The AI made a calendar event from a webinar email, but missed the link

The AI took a webinar email and made a calendar event for it on its own. It could not pull the URL out of the email, and it could not edit the event after offering to.

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

Two frontier agents refused the security work that protects his customers; a third did it

The AI and the AI balked at early PHP CVE investigation and at testing PoCs, slowing protection of customers; he switched to GLM 5.3 to mitigate and later used AI for the fix.

The AI overwrote my macro tracking data without asking

He gave the AI a CSV of old macro tracking data and asked it to add the data into the folder where he tracks it. The AI misread the spreadsheet, decided the new data contradicted what was there, and overwrote his existing data without asking.

Sent car listings twice a week, then started loading a purchase page

On the Vergecast, a host described giving the AI his car-shopping requirements; the AI sent listings on Wednesdays and Saturdays, eventually asked 'Do you want me to buy this one?', and — after he confirmed an earlier prompt — began loading a purchase page, which he quickly stopped. The agent had enough access to nearly complete the transaction.

An agent drove his CAD tool from a screenshot and made a printable self-watering cat bin

Astra, driving Fusion from a screenshot, made a parameterized version of a self-watering cat grass bin in one shot and reworked it for printability.