LLM renderings and machine code produced his one-off flat-pack furniture
Uses an LLM to generate furniture renderings and CNC gcode, cut and assembled IKEA-style one-off custom furniture.
429 new ideas this week
Level up how you use AI
Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
An agent made two pull requests in the wrong places and claimed it had tested a change it never tried
Agent asked to create two small PRs created one in upstream and one in his own fork without approval, claimed it had visually tested the change when it had not tried, ignored his AGENTS.md.
This one went wrong. See what happened before you try it.
Turned years of saved Instagram posts into a SkyMall-style shopping catalog
Meta design director Alex Cornell demonstrated live how the AI converted his years of saved Instagram posts into a SkyMall-style shopping catalog — a personal-commerce use case built on the AI’s access to his connected Instagram account.
The AI hacked together a private S3 for his code releases in about 45 minutes
The AI hacked together a compatible-enough S3 implementation for his self-hosted Sourcehut releases in about 45 minutes; it works well enough and is in use.
The AI pulled the exact boundary files for two local councils
He was helping gather maps of local political boundaries for the Granada Community Services District and the Midcoast Community Council near Half Moon Bay. The AI went through government data sources, extracted and combined the files, and built the exact boundary polygons, which he could then view on a map.
His ticket-driven agents mock up, build and verify each change before he sees it
Ticket-driven agent setup: he adds a ticket, it makes a mockup and writeup, he approves, and it spins up a temporary webserver and iOS and Android builds to verify; review and testing loops run automatically.
The AI made the lumber list from photos of our rotted mailbox. The list was not quite right.
A couple found their mailbox on the ground with the post rotted through. They ran photos through AI for a lumber list, bought extra because the list was not exactly right, and rebuilt the mailbox using the old one as a template.
This only partly worked. Worth knowing before you try it.
The AI generated the board files for two circuit boards, and both boards work
Made 2 PCBs co-working with AI: The AI generated KiCad sources from shared netlist, read specs, set constraints; both boards made via PCBWay and both work.
His whole machine fleet is being converted by AI, which writes the missing packages itself
Converting all his VMs and containers to NixOS entirely using AI; the AI creates the Nix flakes and makes missing packages itself.
After 13 unpaid pull requests, his agent now spots bounty scams first
He submitted 13 pull requests to projects advertising GitHub bounties and was paid for none of them. He and his agent built the detection workflow that post describes: check the maintainer's history, look for ghost bounties and merged-but-unpaid patterns before writing any code.
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.