Remember when you watched Honey I Shrunk the Kids, and the dad had these fantastic contraptions that were his own personal devices that were clearly FOR HIM and him only and you thought “Man that’d be so cool!”

That’s what it feels like to make personal software right now.

One of the weirdest things about AI is that it has really…smoothed out my day. It used to be I’d run hot and be dead ass tired by 2PM, so I always front-loaded my coding because I knew I wouldn’t have it in me to start after 1PM.

Now…I’m just kinda steadily working all day.

Claude…did you verify your code with tests?

“No, no I didn’t”

Claude…we talked about this!

Starting to feel like I’m reprimanding a child 😆.

Messing with openClaw today. Took a while to get it moving but I’m officially texting a bot on my computer that’s helping me manage my todos. Really cool! DEFINITELY beta. Needs work. Not for the feint of heart. But cool!

The WEIRDEST side effect of using Claude code is that I am observing how it uses the CLI and by osmosis I’m getting really good with bash

If you’re not setting yourself up with a code review phase in your AI-written projects, you’re setting yourself up for a world of hurt later. It’s not just about validating the quality, it’s also about knowledge transfer. otherwise, your codebase will devolve into a black box.

Swirling around setting up my ralph loop so that it intelligently chooses the right model based on the context of the task that’s asked. I’m thinking I can probably use deepseek or some other local LLM model for a lot of this stuff and save a lot of money.