I found it doing quite decently when using it with strongly opinionated web frameworks and some rules. After all, most web projects are mostly CRUD anyway. For desktop apps it seems mixed, probably because there aren’t many frameworks that give structure. It did however throw together a working app for me so i can map my mouse buttons, but it’s in golang. I’m more of a python / php guy, so i can’t really tell if it’s coded correctly. It didn’t delete my computer yet, though.

With this photoshop clone however, i’m surprised it starts at all. Last time i’ve tested something more complex for desktop, it failed spectacularly. So i’m quite curious how far they can push this thing. What i don’t like, is that GenAI stuff they have to generate images. Coding is one thing, but using it for “automated art” is not so great…