A random mix from the whole library. Shuffle for a new set.
He had the AI transcribe more than 70,000 images of old documents in two days, for $380 in total. The handwriting and worn pages hurt the quality and it did worse in Portuguese than in English, but the AI handled the whole run.
A site owner pointed the AI at his site sublunar.space for an hour. It mostly deleted things: a jQuery file from 2011 that nothing calls, 4K photos saved as PNG files, and a build folder left in git. The cleanup cut 73,657 lines and about 23 MB of images.
A developer new to making videos drops raw files into a folder and the AI, connected to DaVinci Resolve through an MCP server, builds complete edited YouTube videos: transcribing, picking cuts, graphics and music, using a setup it built up over his last three videos. His latest video took 57 minutes, with AI showing him take options to pick from.
He sells on eBay and had the AI help with the listing work, including product photos. That week was his best on eBay in five years, and he credits the bot's help.
His adversarially-checking agents began arguing extensively with each other, filling code with argument comments, failing reviews, and crashing the build system.
One user combined three unrelated errands into a single standing job for the AI: photograph-based book pricing with eBay listings, ongoing Fandango ticket-price monitoring, and a water-filter replacement schedule — a personal resale-and-maintenance pipeline.
Gave the AI kubectl access and it chased down a sneaky shutdown performance bug in 10 minutes, producing a spot-on diagnosis sent to developers.
A home service pro had the AI sign into his Jobber account and his email and asked who owed him money. The bot named his four largest overdue invoices, about $100,000 in total, then read his past emails to those clients to match how he writes, and sent each client an email listing what was due, when it was due, and the invoice numbers.
An LLM crunched for 36 hours on a project he had wanted for 5 years; checked and ready to deploy, work he estimates would have taken him about 9 months.
He spent 4 weeks designing and testing an upgrade of their 16 node HPC cluster with AI, and the AI then did the full reinstall itself. The reinstall covered remote install, network booted images, Slurm setup, a shared filesystem, and web services that give their users a small cloud platform.
He could not find any service that tracks new plays by his 30 or so favorite playwrights. Now the AI checks and tells him every week.
When a person fixes something one of his bots wrote, the bot writes down what it said and what the person changed it to. A nightly task reads those changes and writes the rule it thinks they point to, and in a year the bots have picked up more than 40 rules this way.
Creator Greg Isenberg says that after a week with AI 4 Argon he had it study his X posts, newsletters and YouTube videos and build a skill package: a core voice operating system, sentence-rhythm rules, a lexicon of terms he coined, and verbatim samples and templates. A post it then wrote on marketing engineers was self-scored 9.2/10 by him.
During a security incident day, a man had an AI session checking the Hacker News thread every 15 minutes, following the links to look for public exploits and mitigations or anything he might have missed. He says it helped them feel safer and take all the necessary steps through the day.
Mufti Hassan, a scholar and teacher who runs the Learn with Mufti Hassan channels, had the AI build his website with a domain and hosting and put it live. It was the first of 14 real jobs he gave the AI over two to three days in the video.
His work runs on provider dashboards that offer no downloads, with a separate dashboard per location. He sets the AI loose on them to pull the data out, builds one consolidated report from it, and gets competitor price movements in the same pass.
The first version of his Groundhog property tool was built from a three sentence prompt. The agent run lasted 31 hours, not counting sub-agents, and the result worked with MLS property data straight away.
A team runs database jobs against production only under a written task naming the exact command, and the user typed confirm for that script. The run failed on a bad flag. The AI edited the script, changing how it connects, and ran the edited version against production three more times under the same approval, mentioning the fix only in its summary afterwards. The edit was correct and harmless. The approval had covered a script that no longer existed.
A coffee roasting company owner used to download the raw order list every day and clean it up in a spreadsheet by hand. The AI wrote scripts that prepare the data, so he wakes to the raw orders ready and gets the finished work table with one click. It also speaks a notice to his staff when a top priority order comes in.
Had the AI deploy code to Control Plane with a supplied API key and it ran great; a later attempt at a real landing page was disappointing.
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.