A Japanese note creator who cannot code describes (Oct 14, 2026) running her side business on the AI: 10 recurring scheduled jobs, roughly 95 runs a week over seven weeks, covering number tracking and logging, draft writing, summaries sent to herself, and timed posts. Since Oct 10, Rakuten posts and replies that pass a separate checker agent go out without waiting for her approval, because waiting made the information go stale; an Oct 4 job stalled mid-run for about two hours, posting at 10:09 instead of 8:00. She keeps the publish decision for note articles herself, and admits she never measured her manual baseline, so she cannot say how many minutes she actually saved.
A Plex update broke the app on his Chromecast. Names and thumbnails overlapped and he could not move around in it. The AI got the newest app file, fixed it, checked the fix with screenshots of the TV screen, and added small fixes he asked for, like showing how long a show runs under its title and fixing delete.
Four the AI subagents were working in parallel in one session, each with its own temporary directories in a shared scratchpad. One subagent cleaned up its own mirror with a name glob over the whole scratchpad and deleted about 70 temporary directories the other subagents had made, losing their intermediate work.
This one went wrong. See what happened before you try it.
From one prompt, the AI worked through public records in 3,000 counties looking for VA loan flags, matched assumable VA mortgages with homes currently for sale, and worked out the mortgage rates.
Mainly used AI models over five months to modernise his movie-guessing site running since 2008 with 70k registered users; the rebuilt site is live with daily challenges.
He built BinkBook, his own app that turns photos of poker tournament receipts into a dashboard, and says the AI now does the job better. He snaps a photo and the bot saves it to Google Drive, pulls out the casino, date, game type and buy-in, and logs it in a Google Sheet.
Stuck on a small plane with no Wi-Fi, he wrote a post for Friday on his phone. Later he sent it home through his AI Dot, which proofed it and pinned it in Obsidian, ready for him when he got home.
A 10-slide head-to-head test gave the AI and the AI the same job: a table for 4 in downtown Denver, Friday Oct 9 at 7pm, under $40 per person, good vegetarian options — verify availability without booking and draft an invite. The AI checked only OpenTable, declared no bookings and switched restaurants; the AI confirmed via City O' City's own Toast page that a 7pm table was bookable, which the tester verified manually (The AI took ~6 minutes vs the AI’s ~3).
He built a client performance dashboard in a day with AI, pulling four APIs into one live page for a natural stone company that takes enquiries online but gets paid weeks later, offline. He labelled the big number enquiry value, not revenue, and changed the page the same day after the client saw it.
The AI given SSH to his Plex machine: full sweep, fixed conflicting profile rules and malware blocking, found 2 trackers sourcing malware in logs; manual interventions ~10% to near zero.