A random mix from the whole library. Shuffle for a new set.
A maker had the AI design a circuit that shows a picture stored in a memory chip on a standard VGA screen, using common logic chips, and write the chip code for it. He routed the board himself, had it made for $6, fixed the one missed error with a wire, and the board works.
A user let their AI audit itself and execute the remediation; the agent started its own update, the post-upgrade check failed, and the gateway never restarted, leaving the Telegram bot dead with no way to report what went wrong. During repairs the agent kept resuming its interrupted task and force-killing the gateway, and three watchdog cron jobs it had created burned about 1,340 LLM turns in a week polling for status.
He gave the AI the job of designing a 3D printable gearbox that connects to his camera lens, and it worked the first time. In the same post he notes the AI needed two tries at a simple joke answer.
His local Qwen agent computer with full PC access does file organizing, analyzed his local data and wrote several small tools to manage it automatically, coded a KDE widget for VRAM model swaps.
Got the AI to jailbreak his Kindles and add them to his home tech ecosystem, and to hack a Spotify Car Thing so a Raspberry Pi can drive it.
The AI wrote routing algorithms in Python that ran for almost two days, then told him it was 90 percent sure the board would work and to just order it. He paid 200 euros, and the finished board arrived two weeks later.
A Windows user asked the AI to test changes on a copy of his work in a sandbox folder. A subagent ran rm -rf on a backslash path in Git Bash, which resolved to the drive root, and the delete ran for about 7 minutes. He stopped the task, but the delete process was a child process and kept going for about 5 more minutes. He got his files back from a Windows shadow copy.
The AI fixed Steam games and HiDPI and monitor issues on his Linux machine and powers a recurring shell script that checks updates and looks online for potential issues.
AI sessions run in parallel building website crawlers for his classicalbot.com project on his VPS, about 10 parallel at most.
He mined his old Twitter archive with help from the AI. His old threads of more than three tweets and his collections of links are now on his own site as historic blog posts.
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.