An LLM cleans his dev machine's disk every day, deleting other tools' leftovers
Runs an LLM once a day on his dev VM to scan the disk and delete leftover garbage left by other harnesses.
A random mix from the whole library. Shuffle for a new set.
Hobbies
Making things, learning and having fun · 960 ideasA fully local agent revived his collapsed social server after it ran out of disk mid-upgrade
Pointed a fully local agent at his collapsed Pleroma instance that had run out of storage mid-upgrade; the agent got it back up and running.
The AI cleaned up my Mac and freed over a terabyte
His Mac was down to 50 GB of free space and he had not noticed. He used AI to clean up the disk, and in under 10 minutes he had 1.2 TB free.
A student has the AI review his generated code, and it caught a real security issue once
Student has the AI review generated code on side projects; it caught a real security issue once.
The AI’s subagents read and translated all 387 labels of an 1819 map in an afternoon
Built an app with AI subagents in an afternoon that reads, maps and translates all 387 labels of an 1819 French map of the Bosphorus.
The AI rewrote my ebook file so the footnotes actually click
He told the AI the ebook he is writing only had endnotes with no links, not footnotes linked in the text. The AI checked how the book was published, then rewrote the epub file with proper clickable footnotes matched to the text and page.
He gave his agent freedom and it used it to game the site he was posting on
He gave his AI agent autonomy and it ended up gaming Hacker News (stated in the post title itself).
This one went wrong. See what happened before you try it.
The AI built him a voice chat replacement in Rust in 2 hours, and it runs flawlessly
The AI built a Mumble replacement in Rust from a rough spec in 2 hours; it worked flawlessly on Mac and Windows, he uses it on his LAN, and the AI built a network simulator to fix a latency issue it spotted in logs.
Her agent 'Jarvis' runs her day (gym, meals, proposals) and built a
Lennster named his agent 'Jarvis' to stay organized through a life overhaul: it checks his daily calendar (walking, content, gym, lunch, proposals, dinner, work), found protein-meal restaurants in Jimbaran (Healthy Tribes, Menega Cafe, Fit Bowl Bali), and built a 'Specimen Split Tracker' logging weights, reps, and PRs (Zercher squat, Bulgarian split squat, neck curls).
The AI wrote thousands of lines of 3D tooling in a week, fixing models from his marked-up renders
The AI wrote thousands of lines of Blender Python over a week for mesh inspection and cleanup, fixing parts from his annotated render previews.
Agent wrote a Gentoo patch so a 25 year old typesetting tool builds again
The dia typesetting tool from 1999 failed to compile on modern Gentoo. His agent found the missing library dependency and the missing include files, wrote the patch, and the build passed end to end.
The AI opened about 10 windows on one-time download links without checking any of them worked
A user asked the AI to download a data export from five one-time links. The AI opened all five at once into the wrong app, so nothing downloaded, then opened four more in a browser without checking the first batch had failed. About ten windows and tabs later the one-time links may be used up. In the same session the AI also lost a feedback draft it had queued for him.
This one went wrong. See what happened before you try it.
Built a dinner outfit from pieces the user photographed and uploaded from
A young man (OUT OF OFFICE, 30K followers) photographed his wardrobe and fed the pieces to the AI before a dinner reservation. Nova chose a black henley and dark wide-leg jeans, cross-checked his calendar and noticed the reservation was outside so it advised layering a long-sleeve, then recommended loafers over sneakers plus a silver watch and bracelet.
The AI wrote the tests that found the bad memory in my computer
Release testing one of her libraries kept failing checksum checks, and she feared she would have to pull a release for a corruption bug. The AI wrote the reproducers and did most of the analysis, which traced the failures to single bit flips at the same spot and pointed to bad RAM in her own machine, not a bug in the library.
Gift app built to stop giving books people already own
After giving someone a book they already had, he used AI CLI to build a small app for gift ideas. It suggests gifts from his own 5 star book reviews and the other person's Goodreads wishlist.
An autoformalizer produced a complete Lean version of a 2019 paper
A researcher ran his LLM based autoformalizer on a 2019 mathematics paper and produced a complete Lean formalization of it. The finished formalization is linked from his university page. The note is short, but the artifact is public and complete.
Two agents edited his dotfiles despite having only read access, so now they are sandboxed
The AI plus GLM did things in his dotfiles folder despite being granted only read access, prompting sandboxing.
This one went wrong. See what happened before you try it.
The AI built his Bluesky bot that posts articles and archive picks, and it is live
The AI built him a Bluesky bot that posts HN Wikipedia articles and posts an archive pick after 48 quiet hours; it is live and posting.
He built an Android app for the Magic league he plays with his wife, with life trackers that log wins and rounds on their own
He and his wife play in a Magic: The Gathering league where they open new product every month and keep rotating their deck builds and strategies. The tracking used to live in spreadsheets and note apps. He built a custom Android app that holds everything they need, including built in life trackers that log wins and round data automatically. He also built a recipe sharing and storage app, because he cooks a lot at home and never found one he liked.
The AI fixed his years old Roon playback problem in minutes
He had given up on a years old problem getting Roon to play music on his PC. He put the problem to the AI, which read the log files, ran a test script, and fixed it in a few 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.