I photographed my Lego sets and my agent filed all the manuals in my iCloud Drive
He says he took pictures of his Lego sets and asked the AI to download the manuals and organize them into folders in his iCloud Drive. It worked great.
A random mix from the whole library. Shuffle for a new set.
He says he took pictures of his Lego sets and asked the AI to download the manuals and organize them into folders in his iCloud Drive. It worked great.
Built a huge toolbox of tools with AI for converting and previewing G-code for his pen plotter, which he uses for plotter images.
He built a small notes setup for himself in about an hour. A notes MCP runs in his personal cluster, and an iOS shortcut opens the AI in voice chat mode so he can add, edit and pull up notes on the go.
The AI rewrote the touchpad stack on his ThinkPad T14 running Linux and Hyprland. Touch to cursor time went from about 33 ms to about 18 ms.
The AI connected to the user's VPS over SSH, ran a health check and applied updates, all directed from the couch.
He asked the AI to set a timer for 4 minutes. The AI said it would set the timer, but no timer was set at all.
Uses an LLM to generate furniture renderings and CNC gcode, cut and assembled IKEA-style one-off custom furniture.
He set the AI to export his liked songs from a streaming platform, track 365 artists, and send weekly concert notifications — commenters describe the Saturday roundup as a standing routine.
Four days into a 30-day the AI trial, the writer gave the AI the synopsis of Creative Eye Forward, the community education initiative he is building through Creative Eye Studios to teach young people AI literacy, critical thinking and digital creativity. The AI produced a 23-page master curriculum, giving him substantial material to review and shape around the people he will actually teach.
A statistician had argued that class balancing helps mini batch gradient descent. He had the AI Astra design and run a simulation to test the claim, and the results partly corrected him: oversampling sped convergence but hurt probability accuracy, while importance weighted oversampling kept most of the speed and the accuracy. The code was cross checked with AI, and he posted the corrected conclusion as an answer.
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.