Hi!
I'm at least two decades overdue to have a blog but I'm on a plane over the Pacific and can't sleep so it's time to finish setting this up!
Hi, I'm Andy!
My day job is enabling agents to use Google Cloud databases. In my spare time I'm exploring AI and learning to build new things with new tools. The ones that might be useful or interesting I share.
Please note that one of my goals is to test the capabilities of new models and coding agents - so virtually all of the code is written by AI and only lightly reviewed by me.
You're welcome to use anything here - but if you're working on something that matters, please review the code before you deploy it.
How much of this is AI?
- 100%of lines AI-written
- 111hours with Claude
- 137chores by hand
- AI-written
- By hand
Writing
Wind Spirit: balance is measured, not argued
Before the UI, before the LLM chiefs, a headless harness ran a civilization sandbox for hundreds of years across many seeds. Four ways the villages collapsed, the fixes, and what the numbers said about the game I thought I was designing.
Wind Spirit: how much intelligence does a stone-age chief need?
Thirty-four models, 96 sampled game situations and about $22 of API credit: where an AI village chief needs a good model, where a cheap one is just as good, and how format failures looked like stupidity in the first pass.
Grammar Garden: evolving plants from tiny recipes, thirty years later
A Saturday-night return to L-systems: a browser game where plants grow from a few rewrite rules, fall over if they can't hold themselves up, and get bred by bees and butterflies under two different climates. I wrote no code.
What time is "last week"? Tools for AI agents to stop fumbling dates
A benchmark for how well LLM agents handle date/time in the tool calls they make and the answers they give — and what happened across seven models when I gave them a deterministic time library instead.