AI is good at giving artifacts that are not necessarily grounded in understanding of the system, which works for prototypes and one-off experiments but leaves you lost the moment you need to debug.

I think what AI is really good at doing is giving us artifacts, but they're not necessarily grounded in understanding of the system, which I think can be really great with making prototypes, little one-off experiments, but the moment you need to debug something, you're like, "Oh, man, I don't even know where to start."