In my opinion is possible to stop being slop, if an app is very well made thanks to human checks (like fix garbage code made by llms). Llms can't be trusted to competely write code imo, but if a good programmer knows how to use llms to improve their workflow I think that's a good llm usage.

artcraft apps are too new and still have a lot of bugs, but maybe someday it will be more useful in my opinion.

If the code is checked by humans, like on the linux kernel for example, id say I trust it. And I dont think its slop.

and llms have great uses for programming in my opinion, like the opensuses OpenQA, etc. ai has found cves on linux too which is a great usage for it. what I disloke its that some people think that by using tons of tokens they can be programmers by just prompting something...

Artcraft, has a problem that they release quantity over quality, there are like 15 apps now and they aren't well tested... but who knows, maybe in the future it gets better. Maybe id change my mind of it being slop