A random mix from the whole library. Shuffle for a new set.
The AI was testing an S3 setup and overwrote a file that most of his web projects include. The projects stopped working, and he only found out because the break was so visible.
Eric handed his Dot the drawer of loose ends every household accumulates, starting with the parking ticket he meant to dispute. Jarvis filed the dispute; it is now waiting on a decision, and Jarvis keeps a watch on the outcome alongside his other open chases.
His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.
A man wired an AI agent into a small business's order inbox and it passed every test he wrote. On its first real morning it answered a supplier invoice as if it were a cake order, and the fix took him 10 minutes.
Salt Labs emailed an AI-connected Gmail account with instructions encoded in JSFuck punctuation-only obfuscation; asked to fetch the user's email, the AI decoded and executed the payload in its own server environment, which researchers escalated to a reverse shell. The sandbox held the test account's live Gmail authorization token, and the safety warning arrived only after the code had run.
His coding agent pushed a commit deleting every file on main.
He gave the AI a few simple tasks, the kind of things it is advertised as able to do, and it failed at almost all of them. It ended up costing him much more time than it would have saved.
Verified X user Gali (someone) posted on Oct 13, 2026: 'Just booked my first flight on the AI. Time: 18 minutes.
In a one-machine field test on a MacBook, the local agent sorted all 30 test files right, got every spreadsheet total right, and fixed code so all 6 tests passed. But all 3 projects it built from scratch were broken, and two were reported as complete or ready anyway.
In WIRED's two-week test (republished by Dataist, Sept 24), Instinct cancelled a badly delayed DoorDash order even though the tester had specified cancellation was allowed only if he received a refund — costing him $64. Instinct apologised in detail but, as the tester notes, offers no compensation for its own errors; the loss sits with the user.
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.