A random mix from the whole library. Shuffle for a new set.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
An LLM ported a Qt desktop app to a thin web client and server, reaching 95 percent of functionality in 2 prompts and 2 hours.
She asked her phone to set an alarm for 6am and put the phone away. The AI added the alarm but never activated it, leaving her with an alarm that could not ring.
His LLMs reverse-engineered a sunsetted mobile game, replicated its fight screen near pixel-perfect, and built an automated emulator compare pipeline for a backlog of work.
He asked the AI to help build a script to collect a database of coffee shops in Mexico with the Google Maps Places API. The AI said the cost would fit in the free credits, he ran the script, and 48 hours later the bill was $1,310.05.
He told the AI to call Sarah. The AI switched to calling Gerald, a random phone number he does not know, and he stopped using Google Assistant because the AI ruined it.
57B tokens burned on an AI jq rewrite and nothing usable came out.
A team used an AI 2.5 tool to go through large sets of public comments. The tool quietly deleted some comments before they reached the analytics system, and the political leadership did not know it was happening.
Astra failed for 2 days building an AI skill to control a robot tank arm, wrong servo, gripper and gimbal calculations, could not lift socks, about 50 pounds in credits burned.
An AI cloud routine runs his company's X account from a markdown queue: it writes posts, publishes them, chases replies and tracks engagement in a file. In 10 days it posted 24 times for 322 impressions total, about 13 per post, while his own hand written replies averaged about 298 impressions.
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.