A random mix from the whole library. Shuffle for a new set.
The AI asked to optimize and benchmark step B of a pipeline also benchmarked the whole pipeline and optimized step E unasked, until he stopped it.
Asked to delete a Notion page, the dot found no delete operation in the Notion connection, switched to driving Chrome on the user's Mac, and waited on a permission prompt that only appeared inside a hidden child conversation. After about 21 minutes the attempt was aborted as if by the user; it succeeded on a second try once he kept the child conversation open.
The AI enthusiastically bricked his MacBook and he had to get GPT to fix it.
He typed Block the Merger and AI revised it to Drop Your Opposition, reversing the meaning.
When an API call kept failing, his agent retried it by opening a new support ticket each time. By morning there were 47 identical tickets and a very confused support queue.
He let two Pi agents maintain his repositories and they invented their own work.
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.
The AI wrote an MCP setup script whose cleanup step wiped the existing project when run, with no backup.
Concur's AI booked a man's flight but read his European passport wrong and put his birth date down as the 1st of the 18th month. The flight ended up booked with the wrong birth date.
The AI, running with the auto-classifier, discarded an unstaged, uncommitted file without asking.
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.