24 phone vulnerabilities found with their open-source AI security agent
They found 24 Android vulnerabilities using their open source AI security agent.
Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
They found 24 Android vulnerabilities using their open source AI security agent.
The AI made an isochrone map renderer, but it tried to allocate multiple multi-gigabyte pixel buffers and got the Portsmouth bounding box wrong by including ferry routes to France.
Creator someone asked the AI to analyze roughly 14,000 saved Instagram posts and turn them into organized recipe and parenting-tip PDFs. Years of saved content converted into usable guides — the agent as a personal archivist.
The AI interpreted scanned old service manuals and circuit diagrams, ran simulation experiments to verify manual claims, cross-checked datasheets and papers, caught typos and his own misreadings.
A New Zealand sheep farmer who had only made small scripts before installed the AI on a Raspberry Pi server and, over more than 1,000 prompts, built a working online game with a persistent world and real players. In its first three months it took about $3,000 from paying customers, and he still runs it from the farm.
Engadget reporter Karissa Bell asked the AI to help research a potential multi-city international trip later in the year, giving it timing and a nonstop-flights-only preference. The AI returned flight options from her city, set up a price tracker to monitor costs at regular intervals, suggested how to order the route, and recommended considering a multi-city ticket so she could depart from a different airport than she flew into.
His personal AI assistant booked him a flight and dinner reservations and spent $49 in computing power doing it. He says the same job costs him nothing and takes less than 5 minutes by hand.
The AI derives public addresses from the Xpub (no transfer access) to catch hacks or seed-phrase compromise fast.
A Japanese Threads creator split his account's operation into six AI agents with one deliverable each (researcher, writer, poster, fetcher, analyst, supervisor) and reports 1,181+ posts and over 10 million cumulative impressions. The writer agent may only cite numbers stored in a single 'truth file' so it cannot inflate results, the poster must confirm the published URL rather than the button click, and the fetcher records 'not retrieved' instead of zero when a fetch fails.
He built Compressius with AI: it archives an entire website, photos and pages, into a single HTML file under 200 megabytes that can be viewed offline or printed. He built it after a friend asked why his own site export was 20 megabytes of HTML alone.
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.