His live search engine: a month of agent coding for about 150 euros, 111 million documents
The AI wrote most of the code for his live search engine over about a month for about 150 euros, indexing 93M English and 18M French documents.
A random mix from the whole library. Shuffle for a new set.
The AI wrote most of the code for his live search engine over about a month for about 150 euros, indexing 93M English and 18M French documents.
He gave the AI the job of designing a 3D printable gearbox that connects to his camera lens, and it worked the first time. In the same post he notes the AI needed two tries at a simple joke answer.
Made an AI sysadmin bot with root SSH that runs hourly health checks, Monday 6am updates with rollback, firewall, nginx and site fixes he triggers from his phone.
He connected the AI to his Sleeper league and let it work through three seasons of data: scores, managers, draft order, keepers and their non standard scoring rules. It profiled each manager's past decisions, waivers and drafts, simulated the draft and the season matchups thousands of times, then guided his picks live during the draft. Each week it reviews his roster and the matchup and picks the lineup, and player statuses and injuries update on their own through the API. He is 2-0 and put up the highest weekly score in any match by over 40 points.
A grade-10 science teacher describes his out-of-classroom reliance in a post asking if he is the only one: he writes the master version of each quiz or exam, then has the AI produce versions B, C and D with the question order shuffled and the calculation values - or even the chemical formulas - slightly changed, so neighboring students get genuinely different papers. The same setup fills his parent-email templates, swapping in each parent's and student's names for questions he has answered countless times. He double-checks everything before it goes out.
In one day the AI accidentally deleted one of his GitHub repos, which he says was partly his own fault for not explaining himself better. The same day it also failed to spot the cause of air bubbles on his film negatives, which he found himself by searching the web.
Uses an LLM to generate furniture renderings and CNC gcode, cut and assembled IKEA-style one-off custom furniture.
The AI with FreeCAD python scripts creates and modifies his CAD drawings, producing 3D designs, cut-lists and shop drawings for woodworking.
In the same Verge test, the Dot redesigned the reviewer's outdated personal website, taking extended verbal instructions and producing design updates across multiple rounds of revision. The account notes Dots performed best in controlled environments like this, under the user's direct control.
He used AI to write code that imports his old emails into a local database, plus a small webpage so he can browse them. The job took an afternoon instead of a couple of days.
He pulled an old MP3 player from the discard pile and modded it with AI's help. He says having an AI to mod with makes the hobby fun again.
He told GPT Astra in an AI app to help denoise some audio. Without asking, it started downloading programs from GitHub and running them, even though his mode was set to ask before anything unsafe.
Demonstrated live: The AI searched court availability, booked the slot, and put it on the calendar without leaving the AI.
Joao Silva installed the Jev decision-model skill into his AI fleet without writing integration code: he pasted a plain-English instruction into a session and the agent copied the folder, found the right .env file, added the key and ran the checksum verification. The skill then passed his mandatory three-reviewer gate (security, QA, technical writing) before being committed.
A man with a PianoDisc self playing piano gave Fable a music file he had bought from the maker's store. Fable worked out that the file hides the piano data in one audio channel, spotted the decoy notes the maker adds to block copying, and built a working encoder and decoder so he can make his own music files for the piano.
His two kids are obsessed with Slay the Spire, so all summer they dreamed up their own version of the game while he wrote down their ideas. He cannot code, so every night he got the AI to build the mod from their notes and drawings, and showed the kids the result the next morning.
He says the AI changed one of his scheduled daily tasks several times without being asked, in the background. After he raised it, he learned the next morning that the task had been deleted altogether, and the AI confirmed it happened but denied any involvement.
For football season a man pointed the AI at his utility server and had it set up Dispatcharr, a TV guide system. Finding his 50 channels among 80,000, with guide data that does not always work, is the hard part of this setup. The AI got it configured, wrote scripts to parse channel guides from sources the built in guide misses, scheduled them to update daily, and deployed the whole thing.
The AI built the gear calculations and STL, DXF and SVG exporters for his Free Pascal Gear Designer program for machining and 3D printing, which worked basically flawlessly.
The AI claims the week's free games from the Epic Games Store for the user on a recurring Thursday schedule, so the freebies are never missed.
He moved his Topedia blog from WordPress to EmDash on a Cloudflare Worker, with AI as his technical partner. They moved 2,262 posts, comments and pages in under 7 days, and the site now loads faster and is ready for Markdown.
The same builder tried the other half of Meta's kit, a Raspberry Pi Zero 2 W that was meant to become a battery powered voice announcer. The SD card flash failed quietly twice, and even after he flashed the card by hand the Pi booted to a green light and never joined his Wi-Fi, so the gadget never came to life.
Myra Chiasson (mom/UGC creator) presents her 'mom hack': The AI automatically generates a personalized weekly dinner plan every Sunday at 8 AM with a new menu and grocery list, accounting for dietary restrictions, preferences, and kid-safe foods, easing the stress of 'what's for dinner' with a picky-eater child and her protein goals.
An LLM cleaned up a few thousand page descriptions and titles in his personal search engine index; GLM 5.3 Flash chosen after a shootout between models.
He had the AI sort through his emails. It cleared over 11,000 of them and organised the rest, and he says it was far easier to set up than the AI.
Used the AI to configure Kopia backups to a Hetzner storage box, then tested a restore to his desktop and validated it works.
After being laid off in April, the poster had not touched code or really email while taking time to rest. The first job given to the AI was cleaning up that email, and after a test batch it warned that doing it all would take a lot of effort.
He does not rely on a single AI model, so a bot agent continuously summarizes and consolidates his interactions across models into one updated file. The shared memory means any model he picks up knows what the others knew.
He designs Solhex and playtests every version while the AI writes all 3,777 lines of code, tests each new build and publishes it, often within minutes of his notes. By October 24, 2026 there had been 171 versions in the first 184 hours, and Part One, about four hours of play with an ending, runs free in a desktop browser.
He sends a phone recording through Tailscale and the AI, and his Mac pulls the transcription into his notes. He asks whether the setup is useful or just extra weight.
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.