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…
Yeah, there are scenarios that it can ‘one shot’, either very straightforward variations of common themes or a use case that is comprehensively instrumented in a way to “know” if it is correct or not automatically, and having the solution iterate against that criteria evaluation until all criteria pass (though in the latter case, I have seen it change the criteria deciding the criteria was a mistake instead of fixing a problem).
If you spend enough tokens, let it rebuild and test on its own, and let it churn and churn, then I’m not too surprised it could make this launch and be superficially intact. The real pain starts when trying to close the gaps the project has in this sort of scenario.
I will say that GenAI makes golang a lot less tedious. Lot’s of obvious but required boilerplate to force the developer to abide by consistent structure. Though I still prefer reading python code since I don’t have to peruse a ton of boilerplate there.
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…
Yeah, there are scenarios that it can ‘one shot’, either very straightforward variations of common themes or a use case that is comprehensively instrumented in a way to “know” if it is correct or not automatically, and having the solution iterate against that criteria evaluation until all criteria pass (though in the latter case, I have seen it change the criteria deciding the criteria was a mistake instead of fixing a problem).
If you spend enough tokens, let it rebuild and test on its own, and let it churn and churn, then I’m not too surprised it could make this launch and be superficially intact. The real pain starts when trying to close the gaps the project has in this sort of scenario.
I will say that GenAI makes golang a lot less tedious. Lot’s of obvious but required boilerplate to force the developer to abide by consistent structure. Though I still prefer reading python code since I don’t have to peruse a ton of boilerplate there.