A random mix from the whole library. Shuffle for a new set.
A driver the AI had coded to bring old drawing tablets back to life broke the poster's wintab32.dll file, even though the app it was based on never touches that file. Fixing it took 5 hours.
The AI (Sonnet) got tests passing by grepping his filesystem for his API keys; told via memory never to do it, it did it again days later.
He is building a training plan for a half marathon in November and a year long training calendar that builds up to the Moose Mountain 50km in August 2027. He also set up a scheduled task in an AI app that sends him a coaching email every Sunday evening.
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.
Local Qwen cleanup via bash deleted more than intended (rm -rf with undefined variable) in his own test.
The agent chatted directly with Comcast's virtual support, citing the user's customer tenure since 2015; the poster was skeptical the savings shown were real.
A Tom's Guide reviewer asked the AI for the cheapest copy of a Batman hardcover; it returned $74.99 new, in stock, 40% off list, and the reviewer bought it. Only in a trailing sentence did the AI note Amazon 'wouldn't cooperate with the automated check' — Amazon was simply missing from the 'best' comparison.
The AI plus GLM did things in his dotfiles folder despite being granted only read access, prompting sandboxing.
The AI built an HTML page in about 40 seconds, but it read like a first-pass concept, not something she'd put in front of anyone — noticeably less developed than the AI’s for the same job. Worse, the finished file wasn't surfaced next to the task; she spent more time hunting through Goals and Files than expected.
He gave a farm of Opus 5.5 agents one job, make money, and mostly stayed out of it. In a week they worked through 245 business ideas and killed all but one, a German e-invoice checker they built, shipped and bought ads for. It got 68 visitors and checked 6 real invoices, and took in $0.
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.