A random mix from the whole library. Shuffle for a new set.
Used the AI to reverse-engineer a neural network accelerator in a Chinese WiFi camera SoC and implement an ONNX compiler and runtime, resulting in a working 20 dollar AI smart camera.
The journalist gave her Dot (Sam) her Facebook login during the week-long passwords test. Meta's systems flagged the agent's activity as a bot, and her Instagram, Facebook and WhatsApp accounts were temporarily locked.
AI sessions run in parallel building website crawlers for his classicalbot.com project on his VPS, about 10 parallel at most.
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
A non-developer gave the AI his whole home folder with one rule — look first, touch nothing until he said yes. It inventoried 9,412 files, found the chaos concentrated in 312 files across his desktop, Documents and a forgotten 'Misc' folder, and sorted them into six folders named the way he talks (Letters, Money, House, Photos, Travel, Not Sure), renaming files so they can be read without opening them and deleting duplicates only with permission; finding one photo went from 23 minutes to 4 seconds.
A man had an obscure Alcatel modem with undocumented hardware. He soldered on serial pins, plugged it in, and asked an agent to reverse engineer the firmware. DeepSeek v4.1 Flash took about an hour to get a full OpenWRT build and flash pipeline running in an isolated container, the driver changes worked, and the whole job took under half a day and $0.86 in AI cost, work he says would have taken weeks or months.
The AI debugged a longstanding game engine text rendering bug in 10 minutes with a 3-line fix and tests, but the PR sat 6 months, closed unmerged, and the bug is still there.
Thanks to the AI he has been working on a 4 player version of Wizard of Wor for the Atari 800 that uses all 4 joystick ports, so far in an emulator, with a real Atari test to come. He says he can now play his favorite games with fun options that never existed before.
A Japanese learner who had used jisho.org for years hit a word its handwriting search could not match. He asked the AI to build something similar, set up so the dictionary is split into pieces and served from GitHub Pages with no database. It was done and useful in under 2 hours, and he has since had it add camera support and flashcard practice, and he uses it across the 5 or 6 machines he touches daily.
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.
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.