I just set this up for the project I'm working on last week, and felt dirty because it took me a couple of months to get to it. There are like 5 or 6 users.

There's something so unnerving about the people pushing the AI frontier being sloppy about testing. I know, it's just a CLI wrapped around the AI itself, but it suggests to me that the culture around testing there isn't as tight and thorough as I'd like it to be.