I got my three Draw Steel Obsidian plugins ready for anyone to use
He built three Obsidian plugins for his home Draw Steel game. Over one weekend, with AI, he got them ready for public use and anyone can start using all three now.
A random mix from the whole library. Shuffle for a new set.
Hobbies
Making things, learning and having fun · 960 ideasThe AI talked him through fixing a server that crashed every few weeks, in about an hour
The AI, proxying commands through him, diagnosed and fixed in about an hour a box that OOMed and needed rebooting every few weeks.
The AI bought me a VPS for $35.99 a year
He gave the AI one line of needs, a budget box with 2GB of RAM or more in the US. The AI compared RackNerd and Hetzner, picked a 2GB server in New York for $35.99 a year, filled in the checkout, and he approved the payment.
$35.99a year
The AI built the quiz app he and his friends play, in a week of evenings
The AI built a complex quiz web app for himself and friends with multiple question types, screen sync, media uploads and scoring, in about a week of evenings (build reported in-window; the comment's complaint about current models left aside).
The AI helped me design a monitor mount and I printed it to fit
He wanted a control monitor to fit under his screen and follow the angle and shape of his Stream Deck. He uses AI with reference photos to get the base shape, adjusts sizes after measuring with a caliper, printed a quick baseplate to test the fit, and fixed a 1mm clearance problem with the lock after more measuring.
Audit my whole drive every week, flag 380GB to delete — and delete nothing
Creator Matthew Berman describes giving an AI access to his local machine on a standing weekly job: it scans every file, finds deletion candidates totalling about 380GB, and sorts them into low, medium and high risk. The bot operates under one hard rule — it may categorize but must never delete anything itself.
An agent migrated his whole setup to a declarative system, backups included
Migrated a fairly complex setup to NixOS 1 to 1 with an LLM agent and gained declarative services, backups and redeploy tooling.
I cut my bots' wakeups from about 300 a week to about 140
Eleanor Konik had the AI count the scheduled wakeups across her AI and the AI jobs and found about 300 a week, with roughly half of them wasted. One round of checking, done with AI's help, got the count to about 140 a week with no coverage lost, and about 128 of the old wakeups were just a bot noticing it was 2 AM or a Saturday and going back to sleep.
The AI runs his home network from Discord, setting up and fixing SSH servers on voice command
The AI agy hooked itself to Discord, set up and troubleshoots SSH servers on his home network, commands it remotely.
He vibe coded the little apps his household runs on, including the coffee announcer
Vibe coded personal apps including Meem Makr, which he uses every morning to tell his family when coffee is ready, and a WiFi QR code PDF generator.
He fed paper into a scanner for two hours while the AI ran it and catalogued his documents
He wanted to digitize his papers. The AI worked out how to use his feed scanner, and for about two hours he sat feeding pages in while the AI ran the scanner and catalogued the documents. He could talk to it through a conference speaker and watch it work in VS Code.
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.
Late in a very long Telegram session, the agent stopped actually sending its replies for 3 straight turns
A user runs a long-lived agent session over Telegram: more than 4,000 messages and about $231 of usage in one session. Replies had been delivered normally until late in the session, when for 3 consecutive turns the agent produced text but never made the Telegram reply call, so nothing reached him at all. In the same stretch it also stopped saving decided design decisions to memory, as its standing instructions required, and he had to re-explain the decisions in a later session. A manual service restart and a log review found the cause.
This one went wrong. See what happened before you try it.
An LLM built his replacement blocklist when the community one was discontinued
After CrowdSec stopped supplying its community blocklist, he had an LLM build a replacement blocklist from public sources for his Debian VPS.
Read my 17 years of Facebook posts and write a profile of my life
Creator Wendell Yu says the AI read his 17 years of Facebook posts and wrote a profile report of his life from them. The segment is the first of five first-hand cases in the video.
I built an app that turns my saved articles into one EPUB
He saved articles and never read them, because on his phone he ended up on social media or email instead. So he built a reading app with AI and the AI that bundles his saved articles into one EPUB for his Xteink X4 Pro e-reader.
My agent ran my star photos through the whole processing pipeline
Two of his astrophotos, M 27 and the Pleiades, went through a local processing pipeline that his AI agent Orobas built and ran. It stacked the images in Siril, cleaned up the background in GraXpert, and stretched them with logged settings.
An agent scored genealogy matches and missed the matches a human spots at once
A coding agent built and tested complex genealogy record-matching scoring rules against real datasets; results sort of acceptable but it missed human-obvious cases and produced false positives.
This only partly worked. Worth knowing before you try it.
My AI automation posts my Goodreads updates to BookHive on its own
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.
The AI wrote the script for my orchid pots. The printer made them.
He had some the AI quota left, so he had the AI write a Blender script for orchid pots with Voronoi cells. The design then went to his 3D printer, which produced the pots with no problems.
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.