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.