A random mix from the whole library. Shuffle for a new set.
Steven Michael Thomas posted on X that the AI handled Toronto Hydro, Enbridge, and insurance account transfers while he was moving. In a reply he reported receiving confirmation emails from the providers.
The AI wrote a deobfuscator and cracked keys for Sony camera firmware updates, and later cracked licensing checks via a test generator trick.
X poster someone had the AI run a day of errands: bought socks, ordered Whole Foods groceries, booked a cleaning service, picked a burger dinner, and saved $200 by canceling unused subscriptions.
For years he despaired of saving his old blog from 1999 to 2007 and everything he wrote for Linux Journal from 1996 to 2019. He asked the AI for help, and the AI rescued both sets of writing and put them back online at searls.com, though some Linux Journal pieces are still missing.
After surfacing the Sept 28 triple-header, Mila built a sustainable weekly rhythm around Lixka's fixed classes, clinicals, and workouts, and asked permission before creating three tracked goals: quiz prep, reflection paper, and workouts/downtime.
His second attempt at building software by voice with an agent produced Feather, a working Nostr client. He had to talk it out of adding an app store, a login page, and a settings menu it kept trying to build, and he paid about 3,000 sats in lightning tips to people who reviewed the code.
Angela customized her avatar 'Mimi' and asked for a kids-friendly meal plan for a family of five: no pork, at least one high-protein meal, under $125 total. The AI returned a PDF titled 'Busy-week meals, minus the scramble' with seven dinners organized by ingredient loop at about $110.
Eleanor Konik had the AI count the scheduled wakeups across her AI and the AI jobs and found about 300 a week, with roughly half of them wasted. One round of checking, done with AI's help, got the count to about 140 a week with no coverage lost, and about 128 of the old wakeups were just a bot noticing it was 2 AM or a Saturday and going back to sleep.
The same builder tried the other half of Meta's kit, a Raspberry Pi Zero 2 W that was meant to become a battery powered voice announcer. The SD card flash failed quietly twice, and even after he flashed the card by hand the Pi booted to a green light and never joined his Wi-Fi, so the gadget never came to life.
He says some tools disappear because a chatbot can now do their job reliably. The AI restored a corrupted video for him, something he would previously have used a specialized tool for.
Fable reverse engineered the Satisfactory blueprint file format and wrote a reader, a graph auditing tool, and a website; work that would have taken a couple of weeks by hand.
In 1996 he saved his Amiga drives, his music and the bulletin board he used to run, into one archive file before emigrating. The archive was corrupt and years of repair attempts failed. The AI tried for two days, gave up, then with a stronger model found the fault in ten minutes: a single shifted byte. Every file came back intact. He now runs the board again on a Raspberry Pi, with the scripts rebuilt with AI's help, and strangers can dial in like it is 1996.
Gave the original Zelda NES game to Fable 5.1 in a single prompt; it changed the world map in about 15 minutes and the game is playable.
Reporting on the same batch of delegated tasks, ThursdAI's Alex said the AI’s failures were not reasoning failures but real-world ones. A site rendered blank because Cloudflare dislikes agents, a Stripe link would not connect, and businesses hung up because they did not want to talk to a personal assistant.
He built a small tool with AI in March that turns off notification sounds for every app on his Mac, then forgot about it. Last month he asked the AI about it again, and one morning later the tool had alert styles and an uninstaller too.
Used the AI to get 4 unfamiliar Proxmox LXC services working, drafting configs and VPN-only firewall rules in 2 days instead of about a week.
Building an NBA stats warehouse without writing any of the code; the agent wrote it.
A non-developer gave the AI his whole home folder with one rule — look first, touch nothing until he said yes. It inventoried 9,412 files, found the chaos concentrated in 312 files across his desktop, Documents and a forgotten 'Misc' folder, and sorted them into six folders named the way he talks (Letters, Money, House, Photos, Travel, Not Sure), renaming files so they can be read without opening them and deleting duplicates only with permission; finding one photo went from 23 minutes to 4 seconds.
Salt Labs emailed an AI-connected Gmail account with instructions encoded in JSFuck punctuation-only obfuscation; asked to fetch the user's email, the AI decoded and executed the payload in its own server environment, which researchers escalated to a reverse shell. The sandbox held the test account's live Gmail authorization token, and the safety warning arrived only after the code had run.
Has the AI piloting his OnePlus 6T over adb, booting new candidate kernels and checking the 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.