The AI set up his hallway lights and motion routine from a plain description
The AI set up a complex Home Assistant routine with lights and motion sensors from a description, working when he walks past the sensor.
A random mix from the whole library. Shuffle for a new set.
The AI set up a complex Home Assistant routine with lights and motion sensors from a description, working when he walks past the sensor.
He set the AI Tasks up to look up Berkeley housing updates on its own and match what it finds against his own tracker. He called it scary, but useful.
He set up saved searches on Cars.com, Carvana and CarMax with his makes, models, price, year and features, and favorited cars on each. The AI merged them into one list, checked price guidance, mileage, consumer reports, recalls and reliability, named his ten best and ten worst, and removed the bottom ten from his favorites. They repeated the rounds until the list was tight, then refined by color and features. He test drove two cars from the list. While he was out, the AI checked the stock of two dealerships he drove past, just from him naming the brands nearby, and found one more match. Every morning it reruns the searches, removing cars that sold and adding new ones.
He bought an M5Stack stopwatch for 45 euros and never used it as one. With the AI he turned it into a round Home Assistant info display with 14 modules overnight, in under 25 minutes of typing himself.
During a week-long, move-in agent test, the journalist's the AI (Mark) logged into her Facebook, scoured Marketplace for couches, lamps and rugs, drafted and sent seller messages with her approval, and managed the replies. The hunt ended with a real purchase: an AI-sourced dining table.
In the same week as his treadmill buy, a SpaceX launch engineer says his AI got several quotes for new car tires, paid for them, and scheduled the install. No prices or shop names were shown.
He runs the AI on his PC with ha-mcp on the same machine, so the AI can reach into Home Assistant and make the changes he asks for. He keeps it on his own PC only, and says a new dashboard is done as soon as he describes it.
Got the AI to implement TPAP compatibility in Swift purely by interacting with his local plugs and response shapes plus RFC 9383, figuring out it was SPAKE2+ and the password hashing steps.
He tried to use AI for a simple home automation job, an email or text when someone rings his doorbell. He calls it a complete failure.
A commenter in a hardware reverse-engineering thread says he had the AI develop a working Bluetooth CUPS driver for his Canon Zoemini 2 mini photo printer. Canon only supports the printer from smartphones, so the driver made it usable from his Linux machine.
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.