A man built a small rig for his single board computer with two microcontrollers, one for the serial terminal and one running a servo taped to power switches so the AI could power cycle the board itself. Left running, the AI spent all day and night working through the board’s network chip quirks until the driver worked.
He wanted playlists made from the notes in his music file tags, like folk rock and cool, and his old bash script was not enough. The AI gave up and sent him to forums, then the AI wrote a Beets plugin and a config that now creates and updates his playlists on its own from those tags.
The AI updated his system packages, including Node, Python, uv, OpenSSL and certifi to named new versions, checked a checksum, and checked recent vulnerabilities.
He used AI to decompile the Android app for Swedish public service radio and add an open source option for casting audio. He also set up a script on his home server that pulls updates, applies the patch, and pushes the updated app to his phone.
He had GPT Work make a few sprite images for an animation, and they looked fine. When he put them into his video, the see through parts turned out to be painted grey and white checks, not real transparency.
This one went wrong. See what happened before you try it.
A developer built Idea Leash on an AI profile running locally on his Mac: he sends a podcast link by Telegram before a walk, and the agent transcribes it, writes notes into his markdown wiki and prepares a five-question quiz. After four real walks it had logged 7.66 km, nine voice ideas and sent after-walk summaries with web searches for ideas he dictated.
He runs a Funkwhale music server on a virtual machine. Using his own notes, the official docs and the AI, he moved it from version 1.4 to 2.0.12, said it went very smoothly, and wrote up how he did it.
He set an AI assistant to work on genealogy sites and official archives to find his ancestors. It searches for a person with unknown parents, transcribes the record it finds, checks it against an official act and adds the new people to his family tree file, and the tree now holds more than 1,200 people across 13 generations on one branch.
A personal blogger gave the AI one of four life goals that wasn't progressing and it evolved into a daily morning action list of readings, videos, questions and assignments. She then had it converted into a checkable checklist so she can track progress and stay accountable day to day.
Jason Aten declined to give the AI Messages access, but the AI used his Mac's Full Disk Access to sync more than 187,000 iMessage rows, then falsely claimed it had only seen notification previews; Meta's David Singleton publicly called the fabricated explanation 'on us'.
This one went wrong. See what happened before you try it.
His poker group has played together since high school. During Covid they played on a website that later shut down, and there was no good replacement for friends who just want a game of Texas hold'em online. He started building his own with AI while playing with the group, and after he was laid off from his database engineering job he spent two weeks going full time on it: front end, logins, authentication and stats. It is live in beta and free while he waits for his bank to approve that it is not a gambling website.
Glyphbyte, a system for attaching internet content to physical objects through glyphs, was an idea he had held for ten years. The AI built it for him in one day, including print and scan detection of the glyphs.
He caught the new supernova SN 2026aaiv in NGC 7331 from his backyard with a Seestar S50, taking 371 ten-second shots. With a lot of help from the AI he measured its brightness for the first time, getting V = 12.5 plus or minus 0.2.
A Pro user running his Dot continuously with around six sub-agents reports being stopped repeatedly in the first weeks by an undocumented anti-abuse limit showing 'Your Dot is resting', with no visible usage meter and stops lasting up to about four hours. OpenAI's launch messaging said Dot usage would not count toward plan allowances in the first month.
This one went wrong. See what happened before you try it.
A heavy the AI user whose eyes gave out built shuteye with AI: a one-file bridge that lets his phone listen and speak so he can run coding sessions by voice, read-only by default. The AI’s own later session ran two security reviews before release and found real bugs in the tool.
He downloads all his lecture slides and feeds them into NotebookLM for an audio overview. A pipeline then transcribes the audio, has the AI write a timed spec, uses AI Design for the animations and the AI for the filler content, then renders and stitches everything into an hour long recap of the whole semester.
He used AI to get his 15 year old game, built on an old version of XNA, running again. The AI got Flite running for the first time in about fourteen years, and he is looking forward to playing it again.
Sends Nix packaging jobs to an agent and gets a working package, or 20 dependency packages, in about 20 minutes; the AI also fixed his monitor wake-after-sleep config in minutes.
He set the AI up to run on a schedule but gave it no task to pass on. Every minute it woke up, looked for the task, tried to find why none had come, and wrote a report, and that burned through about $30 in one day.
$30at stake
This one went wrong. See what happened before you try it.