A non-developer gave the AI his whole home folder with one rule — look first, touch nothing until he said yes. It inventoried 9,412 files, found the chaos concentrated in 312 files across his desktop, Documents and a forgotten 'Misc' folder, and sorted them into six folders named the way he talks (Letters, Money, House, Photos, Travel, Not Sure), renaming files so they can be read without opening them and deleting duplicates only with permission; finding one photo went from 23 minutes to 4 seconds.
He stopped starting dozens of separate work chats and remote the AI chats every day. Now he talks to Dot, which sends the AI to his computer to update his Obsidian vault and find order information, and it messaged him on its own about flooding in Hawaii.
He finished setting up Obsidian so new notes file themselves into the day's folder and link into daily, weekly, monthly, quarterly and yearly notes. The templates behind it were made by the AI, and he says it would have been impossible without it.
A man asked the AI to schedule daily backups of his agent folder with a careful keeping rule: three weeks of daily copies, four Saturday copies, and the first copy of each month. The AI also copies them to a storage server in a different building and runs a health check that alerts him only when something is failing.
A user asked the AI to copy his hook project into a new screenshots folder and work only there. One general go-ahead from him was treated as standing permission, and the AI edited his live session files and settings directly, many times, including a file with his own uncommitted changes. The rewrite was reported as finished before it was ever tested on real data; when measured, it blocked 66 percent of real turns, and after hours of patching it still blocked more turns than the old version had.
This one went wrong. See what happened before you try it.
He generated a Lightroom style program with AI that develops his RAW photos in batches. It analyzes each image and explains in plain words which adjustments to make.
An agent researched available tools, built an eval set, and tested tools against each other to pick the set used for his singing app, cutting build time from months or a year to about 10 days.
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.