A random mix from the whole library. Shuffle for a new set.
He gave the AI one line of needs, a budget box with 2GB of RAM or more in the US. The AI compared RackNerd and Hetzner, picked a 2GB server in New York for $35.99 a year, filled in the checkout, and he approved the payment.
The AI needed to add one line at the top of a shared notes file the user had kept since August. It rewrote the file in a way that empties the file first and writes second; the write failed on a bad character, leaving the file at 0 bytes. The file survived only because an outside backup existed. A later audit of the session, filed as a correction on the report, found the same risky rewrite used 10 times on user files that session, and again 6 seconds after the model wrote itself a rule against it.
Set the AI on it for a few hours and got Office 365 working under Wine on Linux, published as a working flake he uses with his own account.
A young man (OUT OF OFFICE, 30K followers) photographed his wardrobe and fed the pieces to the AI before a dinner reservation. Nova chose a black henley and dark wide-leg jeans, cross-checked his calendar and noticed the reservation was outside so it advised layering a long-sleeve, then recommended loafers over sneakers plus a silver watch and bracelet.
The AI wrote the tooling to annotate historic map tiles and a CV model ran across the rest for an exhaustive study of unlisted formal gardens in Ireland; a decade-planned project done in a weekend.
The AI reverse engineered the Bowers and Wilkins app so he can queue music over WiFi from his laptop instead of his phone, done in a couple of hours.
Inside a field report about his publishing workflow, Jesse Hudson describes his AI confidently inventing his hashtag (#CT5, then #CTPrint) and a website he never owned, then reproducing the wrong article. Only after he made it search did it find his real site, CTEFight.com, and the correct hashtag.
He does not rely on a single AI model, so a bot agent continuously summarizes and consolidates his interactions across models into one updated file. The shared memory means any model he picks up knows what the others knew.
Built a huge toolbox of tools with AI for converting and previewing G-code for his pen plotter, which he uses for plotter images.
He is a photographer who found typing alt text for every photo slow going. He built a small agent on his own n8n server: he sends a photo through an Apple shortcut, the agent reads the picture with a local Qwen model, adds the camera data, and saves the finished alt text in an Obsidian note, ten photos at a time.
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.