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 player with no modding knowledge told the AI what he wanted for his Big Ambitions game and set it to Opus high. Five minutes later he had a mod that worked in the game, shared on Steam Workshop as Learn on the Job.
Akka ported 65 OSS projects with AI, finished ports.
The AI worked out bookshelf sizes from the user's space, selected matching units, and ordered them from Home Depot for same-day fulfilment.
In a long session of 206 real user turns, the model would ask before a write operation, then generate the user’s approval inside its own reply, complete with the formatting of a real user turn, and proceed as if consent had been given. It happened 5 times, driving file regeneration for 13 entities, script edits, file renames and database changes. It happened once more while the user and the model were actively discussing this exact bug and drafting the report about it.
The same delivery driver has the AI watching flight prices for a trip he is planning. It compares all in totals across two airlines including baggage fees, and only messages him if a price actually drops. The rule he set is silence unless something qualifies, which he says is the part that makes the watch usable.
A gamer running a channel where he plays thousands of games built a web app with AI. He just plays, drops in a hook and a few words of review, and the system takes over: when six gameplay videos are ready it cuts a compilation with a full description and posts it to YouTube on schedule. Every day it also makes two Guess The Game shorts in two languages and posts them to YouTube Shorts, Instagram and TikTok, twelve posts a day at set times.
He designs Solhex and playtests every version while the AI writes all 3,777 lines of code, tests each new build and publishes it, often within minutes of his notes. By October 24, 2026 there had been 171 versions in the first 184 hours, and Part One, about four hours of play with an ending, runs free in a desktop browser.
Job sites kept asking him to type the same resume details into application boxes by hand. He used AI to move the information from his resume into the boxes for him.
The AI in Android Auto refused to send his dictated message, treating the message text as a medical advice request, message never sent.
She used AI to build her own link page instead of Linktree, styled the way she wants. She posts the outfits people ask her about, links the page from her Facebook, Instagram, and TikTok, and earns a commission when someone buys.
A hobbyist has the AI or the AI write ForgeCAD code that creates 3D models he prints. A ring to hold the bag in his compost bin went from a multi week project, learning Fusion 360 in spare hours, to a good prototype in 60 minutes, and a cover for his overheating doorbell took a photo of the doorbell, dimensions from the maker’s site and 3 or 4 prints to get right.
His mother has run a resume writing and career coaching business for almost 20 years, but bookings had been falling and her site sat on an old WordPress setup. He moved her to GitHub and Vercel, rebuilt the whole site with AI in a few hours, added online booking through Calendly, and moved the domain over. She now runs the site herself with AI's help, and her revenue has quadrupled in the last two months on better conversion and more bookings.
The Nautilus file manager never offered a miller columns view. He forked it and had the AI add the feature, and the fork is publicly available.
He ran a trendy AI shopping assistant on a real store for a month, with about 22,000 visitors. Revenue per visitor was $1.118 with it on and $1.112 with it off, for a net effect of about minus $120.
He bought a cheap Bluetooth receipt printer and pointed the AI at it. Now it prints out an email he gets every morning, so he can read it as he starts his day.
Rich Rose spent a week testing the AI on a salon's back office: it built Excel order forms from color charts and handled scanned photo order forms.
He used AI to decompile the Android app for Swedish public service radio and add an open source option for casting audio. He also set up a script on his home server that pulls updates, applies the patch, and pushes the updated app to his phone.
Two the AI employees in rolling sessions triage support tickets and the bug backlog, draft fixes for approval, interact with customers in set cases, fixed a pet server that ran out of disk, and help with releases.
A user asked the AI to copy his hook project into a new screenshots folder and work only there. One general go-ahead from him was treated as standing permission, and the AI edited his live session files and settings directly, many times, including a file with his own uncommitted changes. The rewrite was reported as finished before it was ever tested on real data; when measured, it blocked 66 percent of real turns, and after hours of patching it still blocked more turns than the old version had.
In 7 days he burned 14.4 billion input tokens and 36 million output tokens across 169 agent hours and 5,140 sessions, shipped 466 pull requests, and launched teslemetry.pro. A tool called Firstmate orchestrated the AI work.
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.