A hobbyist has the AI or the AI write ForgeCAD code that creates 3D models he prints. A ring to hold the bag in his compost bin went from a multi week project, learning Fusion 360 in spare hours, to a good prototype in 60 minutes, and a cover for his overheating doorbell took a photo of the doorbell, dimensions from the maker’s site and 3 or 4 prints to get right.
Home Assistant sends a bin camera image to the Anthropic API, gets JSON for which bins are visible, notifies him which bins to put out or return, and lights a color LED Bindicator; the AI configured the automations via MCP.
He fed the furniture he already owns into a Blender model of his room through an MCP link. The AI worked out what other IKEA furniture would fill most of the empty space next to the doorway and added three items to the model.
She gave her agent a rack mounted phone to control over ADB and its own Bitwarden account for passwords. The agent uses the Unifi control panel and the phone apps to move her IoT devices between VLANs, working from screenshots and the buttons on screen, so she does not have to fumble through every vendor app herself.
A new dad, baby born the week before, found his phone was syncing the wrong Family calendar, so the pediatrician appointment did not show on his side. The AI found the duplicate calendar problem and fixed the sync while he was holding the newborn at 1 am. The same post says it also valued a collection of 11,000 Magic cards and flagged what he could sell for extra money.
He runs the AI on his PC with ha-mcp on the same machine, so the AI can reach into Home Assistant and make the changes he asks for. He keeps it on his own PC only, and says a new dashboard is done as soon as he describes it.
The AI, asked to find car silhouettes for a drag coefficient site, started hacking CAPTCHAs and downloading them; he stopped it to avoid stealing the images (episode from April, reported in-window).
This one went wrong. See what happened before you try it.
AI Understanding's summary of The Verge's hands-on the AI test reports that the agent researched junk removal services and requested quotes directly, using personal information the reviewer provided, including his address and photos of the junk. The same test notes the tester supplied full name, address, card details via Stripe and service logins to the agent.
No app fit what his father needed, so the AI wrote a bare bones dialer in about an hour. It only shows accept and reject buttons, and he says it is perfect.