The author describes using AI to resolve a six-month-old travel medical insurance claim with Cigna. The AI called the insurer, was transparent about being an AI, conducted the call politely (impressing the representative), and — because final consent was required — called the author's phone and connected the parties so he could approve verbally.
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.
A Stanford doctor gave the AI his own genome file and a 180 word prompt based on the framework his team published in 2009. In about 30 minutes for about $5, the AI matched the main findings of that team’s work, flagged genes that affect how he responds to some medicines, and warned that his file did not have enough data for disease risk scores.
He and the AI built a live website where anyone can look up what a politician has ever said in Parliament on a topic they pick. He calls it a moral manoeuvrability monitor.
Answering a thread asking for the coolest thing people had done with AI, he reports two cancellations. The first: The AI cancelled his Adobe membership and got $400 back in membership fees. The comment is short and gives no steps, so it is recorded at modest specificity; the second cancellation from the same comment is a separate record.
Got the AI to implement TPAP compatibility in Swift purely by interacting with his local plugs and response shapes plus RFC 9383, figuring out it was SPAKE2+ and the password hashing steps.
He had wanted a small Home Assistant remote on an old M5Paper eInk module for 3 years and never built it. The AI did it in half an hour, and the remote now pulls up all his rooms and shows the sensors and buttons he tagged as Remote.