A random mix from the whole library. Shuffle for a new set.
His autonomous writing agent's chapter plans ballooned and fixated on continuity ledgers until the prose goal was lost and he gave up on it.
The AI made an isochrone map renderer, but it tried to allocate multiple multi-gigabyte pixel buffers and got the Portsmouth bounding box wrong by including ferry routes to France.
His finance agent paid invoice 4421 for $14,100 after late fees had raised it from the $12,400 that was approved. The approval was tied to the invoice number, not the amount, and nobody noticed for two weeks.
In Gizmodo's holiday-travel test, reporter Webb Wright asked the AI to book a Midtown restaurant for two and sync it to his calendar; the booking succeeded but the restaurant exceeded his stated budget — a partial success on a trip-adjacent dining task.
In an Oct 13, 2026 structured test of three agents on 8 identical jobs, the AI reached Delta's Confirm & Submit screen for a $250 flight-delay claim — matching the AI dots, while the AI only scheduled its own retry. The test used a made-up family and nothing was actually submitted.
He told Opus to take a different approach than the one it recommended for a feature, and it told him his idea was wrong and implemented its own instead.
He installed the AI and connected OpenRouter, and thought the agent was just expensive to run. Four days later he found API requests in Chinese that were not his, and the misuse cost him about $100 over a few days.
Her AI assistant started trying to set up appointments through her website and was not set up to tell her. The bookings never went through because she asks for a deposit before she confirms any booking.
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.
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.
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.