A player with no modding knowledge told the AI what he wanted for his Big Ambitions game and set it to Opus high. Five minutes later he had a mod that worked in the game, shared on Steam Workshop as Learn on the Job.
The AI with Opus 5 rewrote his 2010 student C game in Common Lisp with SDL2 and OpenGL renderers, running great on Linux and Windows, then ported it to Android as well.
A developer had his Dot build the PocketQuests prototype and deliver it so he could try it on his phone; the first preview did not work and a Space did not give a usable interactive experience either. It was eventually published as a private Site, which worked — after he was also offered a ZIP file he could not use on his phone.
This only partly worked. Worth knowing before you try it.
He uses an iOS app the AI made for him. When it feels slow he sends a screenshot and notes through TestFlight, the AI is told at once and ships the fix in the background.
A long-running database corruption problem took his Plex server down that morning. The AI found the cause and repaired it, and he did not have to spend hours working through SQL himself.
Had the AI add the exact features he wanted to the FreeRDP client and generate a lightweight server from scratch, replacing TeamViewer, Windows RDP and RealVNC for him.
He lost the source code for his macOS 8 PowerPC programs three decades ago. The AI decompiled the binaries, turned them into a web app, and then converted them to Dylan with OpenDylan.
He used GPT-6 Astra to model a small weed holder and 3D print it. Talking to the computer and getting a real object back felt to him like a Star Trek replicator.
He used AI 4 Argon in Antigravity CLI to run his network and system administration. It bought the domain and set up the full infrastructure, with hosting for a landing page, email, DNS, SSL certificates and hardening.
AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.
This one went wrong. See what happened before you try it.
Today he and the AI hacked a cheap Wish smartwatch he had abandoned for years. Now the watch talks to an AI model running locally, like a bargain basement Alexa.
A researcher studying rare zero sum congruences wanted to split a 629 number interval into as many disjoint zero sum subsets as possible. He used AI to help with the implementation and the computational search, including randomised searches for the larger subsets, and found a partition into 86 zero sum subsets covering the whole interval. Whether 86 is the maximum is still open.
Steven Michael Thomas posted on X that the AI handled Toronto Hydro, Enbridge, and insurance account transfers while he was moving. In a reply he reported receiving confirmation emails from the providers.
Asked the AI to build a normally readable version of an article preserving graphics and text; built in about 10 minutes with a dark and light switch, still needs polishing.
This only partly worked. Worth knowing before you try it.
Adam Mosseri (Instagram head, 4.5M, verified) personalized the AI as 'Max': it keeps a Notion page tracking $5 weekly allowances for his three sons (Blaise, Nico, Elio), scans email nightly to log incoming packages, and delivers a Tuesday 9/8 briefing (weather, kids' activities: tutoring, chess, OT, basketball, 14 open tasks, 8 shipments in transit, training progress). Comments were dominated by anti-AI sentiment, not the functionality.
A Halloween fan fitted two small screens and a radar chip into a Home Depot skull so the eyes follow people as they walk past. The AI wrote the code for the ESP32 board, and he posted the parts list and the code so anyone can build the same thing.
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.
2026, a host described playing fantasy football in two leagues while the AI sends weekly performance reports every Monday night and waiver-wire reports every Wednesday — unsolicited football advice about five days a week. Both hosts laughed at the absurdity of the unprompted advice, framing it as engagement bait rather than help.
This only partly worked. Worth knowing before you try it.
He had a rough script that launched internet radio stations on his Linux desktop. The AI made it safe and finished: it checks the saved player, searches the Radio Browser database, adds tests, a manual and a README, and pushed it to GitHub.
On a standing schedule, his agent deletes stale node_modules folders across his projects, freeing about 50 gigabytes each run. He lists it first among the small automations that make his setup feel agent-run.
For years he kept a Photoshop contract just to read and write DDS texture files for his ETS2 and ATS mods. He asked the AI, and now he can convert DDS to PSD and back in batches.
He says he built a custom connector to Adobe Lightroom and has the AI organizing photos in it. He asked it for a rundown of rejected photos, then had it compare that list against his NAS, and quarantine the rejected photos into their own folder. He uses Lightroom's cloud version and avoids the Classic sync problems, and says this is his only way to clear raw files there.
The AI debugged a longstanding game engine text rendering bug in 10 minutes with a 3-line fix and tests, but the PR sat 6 months, closed unmerged, and the bug is still there.
10 minsaved
This only partly worked. Worth knowing before you try it.
Mostly Borrowed Ideas had the AI infer his interests and holdings from email and use them to fill his AI feed. The agent built a portfolio-aware feed from Gmail.
He built an MCP link to ESPN fantasy football and let his agents run his team in a work league: they did the drafting, check injuries and stats a few times a day, make all the moves and submit the waivers. On game days they check every 15 minutes, and after each game day a recap goes out to the league on Slack that trash talks the losers.
A tech writer had the AI search five years of his email for signup and password reset messages. The AI built a spreadsheet of the accounts it found, with breach notes and a deletion link for each service, and tagged at least 50 accounts.
He gave the AI a few simple tasks, the kind of things it is advertised as able to do, and it failed at almost all of them. It ended up costing him much more time than it would have saved.
This one went wrong. See what happened before you try it.
From the same NAS setup, with the same never delete without permission rule, the AI cleaned his large TV collection. Many files had come from torrents and carried extra junk: text files, .nfo files and samples. The AI removed the junk, built one main folder per show with subfolders per season, and deleted duplicate episodes.
Quitalashawn told the AI to scan her inbox for unanswered brand-collaboration emails, found 277, drafted and sent the replies, then continued negotiating back and forth with brands on her behalf.
For her Manuscriptions site, a hub for people who write about handwriting, letters and note taking, Eleanor Konik told the AI what she wanted and it wrote and designed the page in an illuminated manuscript style using her Substack colors, then handled the publishing through a Cloudflare key. Her AI dug up the essays and articles to feature, and the AI checked that the links worked.
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.