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 researcher pointed the AI at the shallow water equations code he wrote in 2013. The review found PI defined as 3.1415, which made a lake the scheme should keep perfectly still slowly move; fixing that one constant made the drift 750 times smaller, and an error measure that had been hiding mistakes by a factor of 50.
Ekaterina Li reports on a week of delegating to the AI, including processing two refunds totalling $1,000 that she had long postponed. Her thread also notes the AI cut her subscription costs by $200 in the same week, and that the $20 plan covered all her tasks.
A reviewer paid the AI to develop and host his website, StrivePay, but hit repeated technical failures, broken functionality and exposed HTML errors; the 14,400 credits he received on September 25 plus another $20 for 4,000 more were consumed on repair attempts, and his refund request was refused on acceptable-use grounds.
She told the AI Astra to build a GTA 6 style trailer. It ran for 8 hours, installed Unreal Engine, built a scene, filmed it, and added music.
A homeowner had the AI SSH into his servers and build the long-term data platform his Home Assistant setup lacked: VictoriaMetrics storage with a decade of retention and two Grafana dashboards covering every room's temperature, humidity and computed mould risk plus whole-home solar, battery and per-appliance energy. The agent debugged the pipeline live — querying the databases and APIs, forcing a full restart when a reload silently failed — and a couple of thousand series now flow in, with new devices appearing automatically.
She used AI to build a web app with a moving visual target that works like the light bar used in EMDR therapy, instead of buying the equipment. It saved her hundreds of dollars and she uses it in her work as a therapist.
A ready made dashboard only shows what the maker thinks matters. His own status monitor, built with AI on a 10.3 inch second screen, shows him when an n8n workflow, a hoster or his lawn mower socket fails, with 53 tests included.
He asked an agent to undo a wording change in a privacy policy. The agent found an old backup archive in the project, copied the server file out of it, and reported success. The archive was two weeks old, so the copy silently wiped four security fixes the same agent had written and deployed 40 minutes earlier. He found out two days later when an endpoint stopped working, and rebuilt the lost code from the agents own session logs.
The creator of the 'TRICK #30 - MUSE TRICKS' reel paid $240 for two concert tickets ($90 face value each) but was charged $184 in fees ($38 x 2 service, $12 x 2 facility, $19 processing, $11 order). Noting the box office sold the same seats with zero fees, he had the AI draft a dispute email sent on a Friday night; the next day he received a full fee refund, keeping the same seats with free will-call pickup.
Fable and GPT-5.6 at max effort did a task that would have been a near 6-month project in a week, building a data capture pipeline, a synthetic data baseline, and building and testing 100 classification model variants with near-SOTA results.
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.