I had tried the browser screenshotting feature for agents in Cursor and found it wasn't very reliable - screenshots eat a lot of context, and the agent didn't have a good sense for when to use them. I didn't try it in this project. I bet it would work in some specific cases.
The Gas Town piece reminded me of this as well. The author there leaned into role playing, social and culture analogies, and it made a lot more sense than an architecture diagram in which one node is “black box intelligence” with a single line leading out of it…
Claude knows the game pretty well! It can struggle with nitty-gritty stuff like placing a path on a specific tile. I tried to make the CLI errors semantically useful, like why an operation failed, not just that it failed
I print RCT 'rollercoaster coasters' out of my kitchen for Etsy. Free Dynamite Dunes candles this year because we ordered too many (write in that you want one).
Fivetran is infamously bad to its users