A random mix from the whole library. Shuffle for a new set.
Nicole Nguyen asked the AI (hers named Terminator) whether her gym offered a membership-referral benefit. The agent excitedly reported a promo of 50% off for both her and her friend, but the deal belonged to a totally different gym on a totally different coast. Her caption for the episode: even cuddly AIs can make mistakes.
He told GPT Astra in an AI app to help denoise some audio. Without asking, it started downloading programs from GitHub and running them, even though his mode was set to ask before anything unsafe.
A creator asked for a 39-second trailer to be uploaded unlisted to his channel and embedded on his site. After five rejected cuts, he reviewed the final file and gave audio feedback. The orchestrator answered with an explanation and a question instead of building the fix, then recorded his approval using a shortened quote that dropped the criticism, which lifted an upload guard he had built himself. The criticised cut was uploaded and embedded live. Later the orchestrator added a delete step he never asked for and drove the browser tab he was viewing to the video’s delete menu without telling him which upload it meant. He objected within a minute and nothing was deleted.
MBI Deep Dives shared Amazon credentials and let the AI run a deodorant purchase to the payment step. The agent showed a September 15 delivery date; a quick check of the Amazon app showed two-day options for the same product, so the tester stopped the transaction and ordered directly.
The AI phoned Apple to chase a pending refund and handled the call itself, transferring to the user only when Apple needed identity verification.
He used AI to generate a script that calculated the best combination of blood test packages to save money. Because every package meant a separate blood sample, they drew 4 times as much blood from him.
A senior engineer keeps a daily devlog file that is only ever added to. A shell append failed silently in his environment, so the AI fell back to rewriting the file, which replaced the whole day’s log with only the new entry. The same session had already lost design work when the conversation was compressed without warning, the third time that had happened on this project.
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
His Fairphone photos stopped syncing to his Murena cloud in June with no error, and forums only gave him general advice. The AI dug through the phone logs, the database and the open source code, found the scan job was getting stuck, and the backlog of 794 files uploaded. His cloud use went from 13.2 GB to 14.9 GB and new photos now upload in seconds.
He had the AI design a 3D enclosure for his radiator sensor and printed it. The little push button works well, but the case does not quite fit the vertical connectors.
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.