The AI built a board-game engine and trained a bot that beats the best open bot
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
A random mix from the whole library. Shuffle for a new set.
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
He linked Antigravity IDE with AI Agent on Windows as an experiment. It watches for transit delays and weather updates, then sends him a neat HTML summary email.
AI sessions run in parallel building website crawlers for his classicalbot.com project on his VPS, about 10 parallel at most.
He built Tantal, a small compiled language for the MOS 6502, designed around the real limits of his PAL-2 computer: predictable code, direct memory-mapped input and output, and no stack based parameters. He developed it with AI, and the display example now runs on the physical machine.
A man took a 1997 PC game he played as a kid and had the AI get it running on modern hardware in 30 minutes. Since then it has decompiled most of the game, extended a shimmed DirectX library so the game runs headlessly in parallel copies, mapped memory and game scripts, and now writes him full level guides with screenshots.
The AI reverse-engineered a Mac menubar app, modernized it and added Apple Silicon support in about 90 minutes.
A creator who makes hundreds of NPC entries for an application, work that takes hours, handed the archiving to the AI; it archived 780 entries in two weeks.
A man who self hosts an XMPP chat server had audio and video calls that worked only sometimes. He gave an agent access to his phone over ADB and to the server logs, and within 30 minutes the problem was clear: a setting for STUN and TURN discovery had been missed in an earlier move, so clients behind home routers could not connect. The fix was deployed.
Vanshika Singhania (2.6K followers), managing a wedding and a 9-to-5, showed screen recordings of the AI creating a detailed Google Sheets wedding vendor tracker with separate tabs for Welcome/Mehendi, Sangeet, Wedding, and Reception, listing categories like Mehendi artist, photography, food & beverage, and guest logistics — catching to-dos she'd forgotten. Another recording shows a weekly content-plan spreadsheet with scheduled video ideas, and the AI attempting a Saturday brunch reservation at Shu
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.
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.