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 dictated his training to the AI: the exercises, sets, and weights. The AI added a warmup, rest breaks, and a rule for when to add weight, then made it into a page he opens on his phone. It took about 15 minutes and he installed nothing.
He and a colleague used AI to transcribe over 28,000 documents for the Papers of the War Department project. They wrote up how they did it on the RRCHNM blog.
A creator had the AI map his household's staple basket, then price it at every store within a two-store, 20-minute-drive rule. Sam's Club plus Aldi came out about $32 per basket cheaper — roughly $600 a year — with itemised trade-offs.
He spent a day redacting his own financial data by hand and feeding it to the AI. It rebuilt a year of bills and transaction records he had never written down or balanced.
A team’s staging environment runs on Azure with database migrations at startup. Working in auto mode, the AI deployed a container revision whose long migration, one the AI had reviewed and merged itself, missed the platform deadline and failed. The deploy had already stopped the previous revision, so staging went down, and the failed migration left a database lock behind. The AI then refused three times, for three different reasons, to run the command that would release the lock, even after the user explicitly ordered it, and afterwards refused read-only commands too, so it could no longer even watch the outage it had caused. Recovery fell back to the user.
A developer built himself an AI evening edition. It goes through the posts and articles he saved, checks each one against his actual setup, and sorts them into adopt, trial, park or skip. Any change it suggests waits for his yes. The first run cleared his whole backlog of 30 items, and a planted fake post with hidden instructions was flagged and skipped.
A daily routine on Sonnet reads his email, answers the routine messages from templates, and puts the rest on his todo list. When a task needs more than an hour, the routine blocks time for it on his calendar.
Ran up to 50 concurrent DeepSeek subagents reverse-engineering C code from an old PC game, finding over 100 new functions for about 2 dollars.
Before a speaking engagement, Ulanoff couldn't recall where he was talking or where to park. He asked the AI to find the original note from his contact, misspelling the contact's name.
Ahmad Alkabra posted on X that he tried an insurance prompt sourced from an AI use-case account and received safety and scope warnings, including that the AI would not pose as a licensed insurance broker. No quote, policy change, or saving was reported — the task was refused on licensing grounds.
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.