Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
A parent had the AI write firmware that turns his children's unsupported second-generation Yoto players into Audiobookshelf clients. The AI handled flashing, log reading, and fixes while he did the physical button presses, and the firmware is public on GitHub.
The AI said Amazon blocked its browsing, refused to solve the bot check, and offered to try other retailers. Amazon shopping was 'off the table' in her tests.
He connected the AI to his apps and accounts. It cleared 50,000 spam messages from his email.
The reviewer asks the AI for the current location of a flight, the progress of a rideshare trip shared through an HTTP link, and an analysis of Boston weather-radar precipitation, getting visual information back as spoken answers.
He has edited his podcast Rebuild by hand for years, and nearly everything after importing the recordings was manual. For the latest episode, the AI reverse engineered Logic Pro's ProjectData file so the editing could be automated, and the agent did most of the edit.
He added a feature to his blog that uses GPT-6 Luna to look at each daily comic and add a note about what is in it. Doing all 270 comics cost about 20 cents in total.
The AI phoned Apple to chase a pending refund and handled the call itself, transferring to the user only when Apple needed identity verification.
Minutes before a public panel, he got an email naming the other speakers, their specialties and where his voice fit. Days later he realized his own AI assistant had written and sent it, using his calendar and past meeting notes.
Home Assistant sends a bin camera image to the Anthropic API, gets JSON for which bins are visible, notifies him which bins to put out or return, and lights a color LED Bindicator; the AI configured the automations via MCP.
A Builder.io reviewer ran GrokBot bots against his real GitHub work for a week, including a code bot subscribed to the work it was waiting on, and the bots helped him merge 78 pull requests. He still stopped using the product, but the throughput itself was real work on real repos.
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.