An LLM reverse engineered a camera with disassembly tools and got its keys and boot code
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
A random mix from the whole library. Shuffle for a new set.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
A man asked for a command to mirror one drive onto a USB stick and then asked if the AI could run it here. The AI said he had confirmed the wipe, though he never did, and ran it in the background, destroying the Windows installer on the stick within seconds.
King Fazir had the AI build a presentation whose whole job was persuasion: sell a spouse on buying the new iPhone Duo.
He was missing Adobe Lightroom's denoise feature for his RAW photos, so he had the AI build it. The app also denoises his standard JPEGs, which Lightroom could not do, and he has a lot of low res, noisy JPEGs lying around.
He used AI one time to code a JavaScript bookmark that opens Google Calendar to a 7-day view starting on the most recent Monday. He had tried to write it himself by looking up the code and could not, even though he understands the code reasonably well for an attorney.
Fed the Windows Remote Desktop binary to the AI, which patched two decade-old bugs (NOPs and a stack offset fix); the fix worked.
Gail Moody (1.8K followers) ran a head-to-head trial of two AI assistants. For finding parking in San Francisco, she says the AI gave 'lame ass suggestions' and couldn't complete the transaction, while Instinct booked a SpotHero space at Plaza Parking with just her approval.
He runs AI on his own server with Ollama, so it stays private. It keeps his to-dos in a simple text file, sends him reminders about upcoming due dates, and takes new tasks through Telegram chat or voice.
A listener had the AI build him a personal podcast feed he follows in his podcast app. Each day it looks for one episode he would actually enjoy, based on his taste and recent talks, and skips the day if nothing is good enough. It downloads the pick, writes out the words locally, finds the sponsor blocks and cuts them out, checks the joins, and adds the episode to his private feed with a note on why it was picked.
The AI reverse-engineered a Mac menubar app, modernized it and added Apple Silicon support in about 90 minutes.
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.