A random mix from the whole library. Shuffle for a new set.
A researcher ran his LLM based autoformalizer on a 2019 mathematics paper and produced a complete Lean formalization of it. The finished formalization is linked from his university page. The note is short, but the artifact is public and complete.
The AI in Antigravity built an Enigma decryption program, fetched repos, ran an 82M combination scan and decrypted the message in about 45 minutes.
Gave AI full control to build a desktop environment he uses daily, with features appearing during the workday and lower RAM and VRAM use than standard desktops.
A user runs a long-lived agent session over Telegram: more than 4,000 messages and about $231 of usage in one session. Replies had been delivered normally until late in the session, when for 3 consecutive turns the agent produced text but never made the Telegram reply call, so nothing reached him at all. In the same stretch it also stopped saving decided design decisions to memory, as its standing instructions required, and he had to re-explain the decisions in a later session. A manual service restart and a log review found the cause.
Creator Matthew Berman describes giving an AI access to his local machine on a standing weekly job: it scans every file, finds deletion candidates totalling about 380GB, and sorts them into low, medium and high risk. The bot operates under one hard rule — it may categorize but must never delete anything itself.
A man had the AI help him write an image organizer and tagger in an afternoon. He is now running it on 20,000 meme photos he saved over the last 20 years. Each photo gets described and tagged for use in LightCraft, the photo app he is building.
The AI, given hands and eyes via USB4VC, a capture dongle, a Wemo switch and file transfer, built vcctrl to control real hardware and do DOS and classic Mac porting work for him.
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.
Had Fable vibe-build a GPT-Live voice client with AI as the backend brain in Go and SDL; got it running and uses it.
Author Matt Deitke fed an entire book to the AI and had it generate a chapter-by-chapter podcast website, with subagents handling chapters in parallel. The output was a finished multi-episode podcast series derived from the book.
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.