A random mix from the whole library. Shuffle for a new set.
A builder created a skill that converts a user's Instagram saved collection into a private, searchable personal library. Every saved post is deep-read by vision AI, and everything runs on the user's own machine.
After surfacing the Sept 28 triple-header, Mila built a sustainable weekly rhythm around Lixka's fixed classes, clinicals, and workouts, and asked permission before creating three tracked goals: quiz prep, reflection paper, and workouts/downtime.
The AI took a webinar email and made a calendar event for it on its own. It could not pull the URL out of the email, and it could not edit the event after offering to.
The AI walked his Android TV box through installing SmartTube, changed the playback settings, and imported his channel list from a NewPipe backup. It was done in minutes and replaced a setup he called poor man's Netflix.
An AI-designed split keyboard, built and now on his desk.
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.
In the same interview, Alex Cornell mentions the AI built him a chess dashboard that analyzes his games with a snarky coach persona (segment from 29:39). It sits alongside his golf tracking as one of the personal dashboards he actually lives with.
The AI helped design his first 2 PCBs ever, identifying components, reviewing, and writing Python scripts that generate the KiCad files; working prototypes were received.
Ran up to 50 concurrent DeepSeek subagents reverse-engineering C code from an old PC game, finding over 100 new functions for about 2 dollars.
Since the end of August he has added three new CI servers to his own setup. The AI wrote each NixOS setup and he checked the work, so now he can rebuild any of the servers from scratch in minutes.
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.