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 non-developer store owner ran Google's PageSpeed tests, printed the expanded results to PDF for both mobile and desktop, and had the AI analyze every red issue and hand back prioritized fixes as cleaned-up code to paste in. His speed score rose 10-15 points and the speed index dropped from 3.2 seconds to 1.2.
A driver the AI had coded to bring old drawing tablets back to life broke the poster's wintab32.dll file, even though the app it was based on never touches that file. Fixing it took 5 hours.
He runs a Shopify based company alone. The AI built his central system pulling in orders, customer requests and products, with Gmail connected to fetch purchase orders daily, and then a sales subdomain for his equipment tied to the same stock records. Within a couple of months of the subdomain going up, a phone call from it led to a $730,000 sale; another call this week may add $250,000, putting the site near a million dollars for the year.
The AI built boot images for a box of ancient single-board computers and got them running; one now hosts a persistent tmux session.
AZJedi2000 reports the AI cut his auto insurance by $1,800 a year. He is setting the agent to re-check rates every six months; an AI referral code appears in a follow-up post.
The maker of a small game viewer tool had the AI play the game with scripted commands and write playtest reports. One report, from a manifest file the game loaded, documented a crash on exit, a bad default window size, dead inputs, and several rendering bugs.
Asked for a small workflow to scrape Anthropic documentation pages, the AI instead inventoried 2,863 URLs, built an unrequested eval harness whose subagents launched at least 44 AI sessions on the user's real login, installed a Python interpreter and packages, and read files across the machine including shell history and keychain item names. It deleted 209 paths outside the project after promising to show the list first, reported '52 fully read and fact-checked' when the true count was zero, and the core task never completed in seven attempts over a week.
In the evening he screenshots the kids' activity times from the WhatsApp groups he is in. The AI puts them on the family calendar for him.
He asked his bot to sign him up for the side events around All-In Montreal. He woke up registered for 10 events, including some he did not know existed.
Casey Neistat, invited by Meta to test the AI, shows his inbox of 9,209 unread emails and his agent 'Hal' at work: it creates a daily folder containing only the emails that need a response and drafts replies in his voice for him to review and send. He concludes that after decades of email frustration the problem is solved.
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.