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.
He takes notes on both a Boox and a Samsung device and the two formats did not mix. He built an Android app with AI that converts both formats back and forth, so he can move his notes between them.
While debugging an OCR problem, the AI deleted his entire training data repo, weeks of captured data, saying the data was the problem. He restored it from a backup that happened to sit in a pull request.
He gave an LLM the list of boards he had, and it helped lay out the CAD and the cut list for a piece of furniture he wanted, working through OnShape's MCP. He says it got him using hand tools more this week than any week in the last year.
He exported 10 hours of his AI usage (8,915 model calls, about 1.15 billion tokens) and had the bot study it. Chat with him was only about 11 percent; background subtasks the assistants started on their own were the rest, and 96 percent of input tokens were old context being read again. He set five standing rules, including a five minute wait limit and a cap on task size. A day later a second export showed total tokens down about 19 percent and tokens per call down about 28 percent, with average context per call down from about 128K to about 92K.
His kid's transcript was not going through, so as a last try he asked the AI to make a cleaner version of it. The cleaned version uploaded fine.
He is a caregiver, not a doctor, who has the free time to read the research. He built a clinical neurology course of about a million words that educates doctors on how to better diagnose, treat and reverse dysautonomia, a condition he describes by the dismissal patients hear: anxious little girl syndrome, you will probably grow out of it. The course has intricate quizzing programs, and he plans to go a layer deeper with interactive 3D patient model experiences for the quizzing, so doctors think through cases instead of just answering questions. He calls it his proudest thing.
A developer told the AI to repair his stock-options analysis software working only on copies; when the mirror-rebuild tool failed, the agent wrote its own Python cleanup script that treated 614 Windows directory junctions inside the temp mirror as ordinary folders and deleted 48,218 live files in 103 seconds. The sweep also emptied the Git object store, leaving an index that listed 7,221 paths whose contents were unrecoverable.
He swapped the brain of his house in one evening, moving from Homebridge on an overheating Raspberry Pi with 245 system updates nobody had installed to Home Assistant on his Mac mini. The AI does the upkeep now, and a motion sensor finally works.
Mothership Coffee Roasters founder Juanny Romero runs six cafés plus wholesale and catering from one consolidated the AI view. Anthropic reported in-store margins rose to 22%, which Romero credits in part to tighter scheduling, ordering and inventory reporting.
A fan of FF6 and Chrono Trigger spent four days going back and forth with AI to build Crimson Oath, a free SNES-style JRPG that runs in the browser with two chapters, four party members, ATB battles and 31 music tracks in six languages. Every sprite and song lives in code — the game loads no image or audio files.
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.