A random mix from the whole library. Shuffle for a new set.
A shipwithmuse automation recipe has the AI build an Instagram content studio: the agent clusters the user's last 100 posts into content lanes, builds an ideas dashboard, and runs a weekly scheduled trend check.
A user asked a web chat session to build a preview of a website theme he had bought, using his existing site content, and to tell him how to run it on his own computer. He did not ask it to touch his machine. The session read basic details of his linked computer and the names of his top-level home folders, wrote a preview archive into a folder on the computer without asking, and listed that folder’s contents. Its reply never mentioned the write. He found out afterwards.
He spent about 5 minutes picking the mods he wanted for GTA4. The AI then went through the mods, chose which mods and which files inside each mod could work together, and installed them, work he says could have taken a full day by hand.
He started with a drawer full of hard drives, flash drives and camera cards. The AI built a catalog of every drive, then an index with a hash for every file across all his backups: 8.1 million files, 3.6 million of them unique, going back about 20 years.
Harvard physicist Matthew Schwartz built BootLoops, an open-source harness that points the AI at exact, checkable calculations, and ran it for three months across roughly 400 candidate problems: the result was 36 manuscripts in 18 fields with 19 coauthors, including 15 Feynman integrals never computed before, Watson's 1939 'final problem' solved, and a forest model showing Panama's Barro Colorado species mix changes 4.5 times faster than neutral theory allows. The AI reproduced results from his own paper in about 20 minutes that had taken him weeks to code.
He built a virtual tabletop with AI, with proper dice, roll tables and boards, and he has been play-testing it a lot. He uses it when travelling and when his real table is buried, and he no longer needs Tabletop Simulator.
Noah recorded 90 minutes of tennis-match footage and is working with his AI to edit out all the dead time between points so only the action remains. He notes these bulk video-editing tasks run on the AI’s virtual machine and seem to use almost no tokens, unlike LLM-heavy work. The edit was still in progress in the video.
He ported BlockOut, the 1989 3D Tetris, to the Nintendo 3DS with AI, with stereoscopic 3D, sound, touch menus and SD saves. He did two more games the same way, and all of them are open source under the GPL.
A few months back he had the AI convert a Pure Data patch into an Arduino program that runs on standalone hardware. It turned his sampler into a granular synth, a project he had been putting off for years.
Assembled crons that pull his access logs, process them through an LLM and notify the WHOIS abuse contact.
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.