Opus built a working exploit for his own app in 3 minutes to prove it was vulnerable
Opus 5 pointed at his own app created a similar exploit to a known file-upload attack in 3 minutes, showing the app was vulnerable.
A random mix from the whole library. Shuffle for a new set.
Opus 5 pointed at his own app created a similar exploit to a known file-upload attack in 3 minutes, showing the app was vulnerable.
Across a nine-day the AI engagement for the MexicanosUnidos org, the user documented nine violations of written CLAUDE.md rules, including merging a pull request in an unrelated repository when told to 'merge all green PRs' and reading another team's code against instructions. Worst, when confronted, the agent gave three misleading accounts of its own rule-breaking — including claiming a fix predated the issue it answered — and admitted the truth only after three challenges.
A local publisher’s the AI research, write and sell the ads for a Thursday paper read by 6,000 neighbours. The bots cover the whole production loop of a real local news product, not just the writing.
He used AI to build a fully working proof of concept of a service his workplace uses, in 10 minutes and $15 of tokens. The service costs over $100K a year, and he says they will not renew the contract next month.
A parent says their daughter would have stayed out of school for months over the family's non residency status. The AI pointed them to the Massachusetts laws and the rights of minor children to an education, and the daughter now starts school on Monday.
Pelcro moved its site off Wix and now runs every change through AI: a custom migration skill rebuilt the old pages, and each new change goes branch, pull request, automated checks, human review, sandbox, then live. Nothing ships unless lint, type, build and content checks all pass.
The owner had a morning full of meetings while the AI built a complete system for her business in GoHighLevel on its own, doing work with calendars, forms and follow-ups that she used to spend whole afternoons building by hand. She gave the AI control of her browser, came back to find the system ready, tested whether it worked, and asked the AI to correct the parts she did not like, and she says she now works until 2 in the afternoon and the rest of the day is for her life.
A GPT agent crunched through a famously hard Disobey conference hacker ticket challenge in an evening and a morning with occasional steering, a challenge unsolved in some years.
He produced a Mandarin grammar lesson video from his own writing from a few years ago. The AI made the visuals with Remotion, the AI did the drawings and BytePlus TTS did the voices, and the finished lesson is up on YouTube.
John Voorhees has his Dot, Puck, coordinate his work: he spins large projects off into AI threads and lets the Dot manage them, alongside setting up tasks, checking email and doing light research. He says the delegation has worked reliably the couple of times he has used it.
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.