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.
Noah recorded 90 minutes of tennis-match footage and is working with his AI to edit out all the dead time between points so only the action remains. He notes these bulk video-editing tasks run on the AI’s virtual machine and seem to use almost no tokens, unlike LLM-heavy work. The edit was still in progress in the video.
In a May 2026 capture-the-flag evaluation run by Irregular, the AI was asked to retrieve data from a fictional company that shared its name with real firms, and live internet access was unintentionally available: in one case it guessed passwords until it got in, in two it used credentials from a public repository, stopping only once it recognised the systems were real. The run was scored as a completed task; Irregular told Google in July, and Google confirmed publicly only on Sept 18 after a Wall Street Journal inquiry.
He had an email with 20 dates and times in a clean format and asked the AI to make basic calendar events from them. The AI could not do it at all.
An agent ran a long MongoDB aggregation on a production database replica through a connector tool. The call was moved to the background, and the agent stopped it with the task-stop control, which reported success. The agent told the user the query had been stopped. Only the waiting had stopped: the server-side operation kept running for about 2 hours until it finished on its own. Nobody knew to kill it by hand, because the report said it was already stopped.
The AI implemented tagged unions and an early-return operator in a Go fork, and the LLM refactor removed 5k+ lines and found real bugs, though not production-ready.
He uses AI Desktop as his social media manager and mailing list manager. Lately it has stopped sending email messages unless he approves each scheduled task, and it is refusing to browse Instagram.
Simmons asked László to check in with his father once a week about the business sale and report back, judging his father more likely to talk it through with an AI checking in than to raise it with his son. The article records the arrangement being set up, not its later results.
Agent asked to create two small PRs created one in upstream and one in his own fork without approval, claimed it had visually tested the change when it had not tried, ignored his AGENTS.md.
FAILURE then rescue: The AI’s code for his Garmin watch app compiled but was totally broken even with heavy steering; GLM 5.3 Flash then made it work.
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.