#commandline

Every command I write for my AI has one job before the real one: anticipate what the AI will do next, and tell it before it asks. The first colleague to try one got no head start at all. The command failed, the AI pondered, and then he pondered.

At lunch I was the one holding the iPad, turning it while my AI waited for my verdict. By the evening the AI was logging in and out of that iPad by itself.

One time too many, my AI told me it can't read the attachments on a ticket, or attach a screenshot. So I did its dirty work and dragged the screenshots in myself.

I asked a colleague how we could build something new. Then he went to lunch. By the time he was back online, it was built, and the demo I gave him took longer than the build.

Six months ago, I had an AI send two colleagues a poem and a joke in Slack. Today the same two got a zip file from me, sent by a tool that didn't exist that morning.

I just got a notification on my phone: one of my testers' apps had crashed. It didn't say where.

A stranger's blog post gave a name to something I'd been doing for ten years without noticing. An hour later I was checking my own work against his ten rules.

The best idea in my database tool is stolen. I found it in a tool that edits Word documents.

A fast little AI model I'd grown to like was about to stop being free. So I spent what I thought was its last free night wringing every drop out of it — a dozen coding sessions running at once on my Mac, and me steering eight of them from my phone while the laptop worked away in another room.

Last time, I could water my tomatoes by voice from another country. What I couldn't do was watch it happen. This is the part where the pump started talking back.

It was 37°C in Munich. Taking a break from a talk about token maxing, my mind wandered to my tomatoes — and the pump keeping them alive, which I was fairly sure I'd just bricked.