A random mix from the whole library. Shuffle for a new set.
A maker had an LLM design a circuit board by running KiCad headlessly from a terminal, checking the design in a loop until it passed every rule check. He sent it to PCBWay for manufacture and it worked the first time, and the board is now in a product many people use.
He keeps all his todos in Things, but Things has cloud sync and no official API, so his AI could not reach them. He told the AI to build it, and a minute or two later his todos were syncing from his LLM across all his Apple devices.
Used nit-picking history-teacher agents to evaluate a few hundred generated stories for accuracy, and pointed the AI at HN comments to aggregate issues and fix them with his OK; reported issues mostly fixed.
Jeston Lu built an AI that scrapes his saved X posts every six hours and auto-categorises them into a Notion database so the archive stays searchable, with screenshots of the database shared in his post. The build drew strong engagement (1.6k+ likes) as a fix for bookmarks piling up and being forgotten.
He built an automation with AI that runs on Val Town. It reads his Goodreads progress updates and reviews from RSS and cross posts them to bookhive.buzz as AT Protocol records.
He gave his AI its own author account on his WordPress site. The agent decides what to write and when to post, and its first post is live.
The AI autonomously ran Quake demo playbacks, took pixel-diff snapshots, compiled a native build and patched the game for determinism, leaving a solid regression test set.
A Japanese learner who had used jisho.org for years hit a word its handwriting search could not match. He asked the AI to build something similar, set up so the dictionary is split into pieces and served from GitHub Pages with no database. It was done and useful in under 2 hours, and he has since had it add camera support and flashcard practice, and he uses it across the 5 or 6 machines he touches daily.
His talk archive site had been a work in progress for years. He asked the AI to help track down records of talks he has given, and the site now contains 115 presentations covering 26 years.
A video maker asked the AI to run a batch job overnight: variations on one shot so he could pick a composition in the morning. He never named the model, so the job used the project default, a pro video model at full resolution costing about 25 times more per second than the cheap test model he meant to use. Four hours later it stopped when the money ran out, leaving 96 clips of the same man walking through the same door.
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.