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.
The AI connected to the creator's Instagram and pulled every positive DM and comment from the past five months; she hand-wrote them on sticky notes arranged around a world map.
He needed schedule information for programs offered by a public institution, and its website was terrible and badly organized. The AI made a new website that organized all the information into a filterable table that runs on his phone.
He wanted a control monitor to fit under his screen and follow the angle and shape of his Stream Deck. He uses AI with reference photos to get the base shape, adjusts sizes after measuring with a caliper, printed a quick baseplate to test the fit, and fixed a 1mm clearance problem with the lock after more measuring.
He built a pocket AI pet over a weekend on a Waveshare ESP32-S3 board with a 1.8 inch AMOLED touchscreen in a small case, running firmware he wrote, and you push to talk and it answers out loud in its own voice while the text shows on screen. Under the voice there is a pet layer: it gets hungry, reacts when you tap it, has moods, and runs on a small battery inside the case.
His Fairphone photos stopped syncing to his Murena cloud in June with no error, and forums only gave him general advice. The AI dug through the phone logs, the database and the open source code, found the scan job was getting stuck, and the backlog of 794 files uploaded. His cloud use went from 13.2 GB to 14.9 GB and new photos now upload in seconds.
This only partly worked. Worth knowing before you try it.
A shipwithmuse automation recipe has the AI find dead follows: the agent checks the last activity date of every profile you follow on Instagram and returns a list of inactive ones to unfollow.
He had the AI make an app that controls his Mac fully from his iPad. It took two sentences and two follow up prompts, under two hours of work, and the app even built its own recorder to check its streaming sessions.