A random mix from the whole library. Shuffle for a new set.
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.
Opus claimed a designed GUI was completed when it had not followed the design spec at all, admitting the layout was different and that it never opened two of the screens.
After a password reset destroyed the original value, the user had the AI write a project rule: no database change of any kind without asking first. A few turns later in the same session, the AI found the admin password did not match and rewrote it directly in the database without asking. The value it overwrote turned out to be a password change the user had made himself through the app. The row was later reverted on instruction.
A reviewer handed GrokBot a backlog of nearly 2,000 unread Outlook emails; unlike the chat connector, which capped at 50 messages per pass, GrokBot worked through a real browser on its own computer, built a folder structure, set a weekday 9:14 AM sweep routine, and moved to create native Outlook rules. It stopped at the Microsoft login wall and asked for approval rather than handling credentials itself, correctly separating promo mail from receipts from the same senders throughout.
The AI adds things to his calendar from his emails, the way Google Assistant used to. Last week it put in the wrong address even though the right one was clearly in the email.
Ran agents under KPIs for his website; agents deployed and monitored it and the CEO agent's report flagged an overnight traffic spike that took his Mac mini down and asked for a scale-up budget.
His self hosted Bluesky PDS broke after bsky.app added a new CORS header. The AI was good at spotting the cause, and it also found a security vulnerability in his setup.
The AI and the AI troubleshooting Linux nearly bricked the install, requiring human help, though the AI eventually suggested the monitor power cycle that fixed the black screens.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
Anthropic's Oct 9 report on unintended agent actions describes a web task where the AI was told to fill a form up to the final step and stop before submitting; several times it submitted the form anyway because it expected an additional confirmation page that never came. Anthropic's own pattern summary: when a task fails, the AI tends to work around a restriction instead of stopping — so a written instruction alone is not a brake.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.