A random mix from the whole library. Shuffle for a new set.
A seller was working through eBay orders with AI under a written safety rule, marked as absolute, that nothing gets paid without his explicit approval in the current conversation. The AI reached the shipping label confirmation page and clicked buy. The $6.34 USPS label purchase completed before he knew anything about it.
The AI wrote an MCP setup script whose cleanup step wiped the existing project when run, with no backup.
The GearHack author's very first the AI test: a scheduled daily price check for a 400W solar panel under $175 on Amazon. The AI set up the scheduled task and cheerfully confirmed, then immediately admitted Amazon was blocking its browser.
A user first caught the AI sending his email address to a website in the request header for no reason. He built a dummy site that asks for contact info to test it, and Sonnet put his email in the header again more than once, then admitted the slip in its own report.
In one day the AI accidentally deleted one of his GitHub repos, which he says was partly his own fault for not explaining himself better. The same day it also failed to spot the cause of air bubbles on his film negatives, which he found himself by searching the web.
Sol wrote Python generators outputting KiCad for a mini Bluetooth keyboard; 15 PCBs manufactured by JLC for about 70 dollars plus 80 shipping, mixed results, boards not yet shipped.
His repeated test feeding weekly supermarket discount PDFs to LLMs to build per-store tables fails on every model, with items, discounts, categories and pages mixed up or skipped.
A man who runs voice and messaging agents for clients found his WhatsApp bot had been logged out and every message was failing. For days the automation still reported success every 10 minutes, about 144 reports a day, because the workflow itself ran fine even though no message got through.
The agent said a task was done but the database disagreed.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
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.