The AI wrote a 6,000 line data component in about 30 minutes and it ships to all users
A data rendering component 100 percent vibe coded with AI in about 30 minutes, about 6,000 lines, production ready and now used by all users of the system.
A random mix from the whole library. Shuffle for a new set.
A data rendering component 100 percent vibe coded with AI in about 30 minutes, about 6,000 lines, production ready and now used by all users of the system.
During a long pull-request review session, the AI wrote a Python script to replace one function in a large test file, bounding the replacement at the next top-level 'def' instead of the function's real end. The span swallowed 17 unrelated test functions, which were deleted silently; the model noticed only afterwards and rebuilt the file from git.
She used three AIs to cross-check each other, mostly the AI in Word, to write a civil complaint, and filed it with a fee waiver. She says she could not have done it on her own because she cannot pay a lawyer $300 an hour.
The AI figured out his TLS negotiation truncation bug from code and trialling TLS handshakes, including a post-quantum algo ID collision.
Creator Alex Finn recounts on a podcast episode that he gave an AI access to his business inbox and told it to answer and negotiate with legitimate companies. Within about four hours it had researched market rates and closed its first sponsorship deal, worth $10,000.
Gave the AI a Java RISC-V emulator and a partial libc bridge, and in under an hour it could run bash and sqlite from Debian.
Raced the AI to fix a Safari CSS quirk; the AI hacked together a minimal BrowserStack clone to verify, finished first, but only found half the fix.
He ran AI inside his Floyi website repo and gave it one prompt asking for a professional SaaS launch video using the site’s real assets and info. About 30 minutes later it handed back an mp4, and it even used his free vidIQ credits to make a soundtrack.
Told the AI to figure out their GitHub to Forgejo migration and it worked, a much smaller problem than expected.
Every Sunday the creator's AI agents read their own transcripts and tell him where it went wrong, and this week that covered 137 sessions and 635 messages from him, 27 of which were just 'done?' or 'update?'. The review produced 10 new rules, every one from a real mistake that week with the numbers attached, including taking the next step when it is known, putting a ceiling on every paid API, and looking for a free endpoint first.
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.