Comment by kylehotchkiss
7 days ago
I mentioned this elsewhere, but if LLMs are improving developer performance so drastically, why are none of these gains being used to get back towards native app development?
7 days ago
I mentioned this elsewhere, but if LLMs are improving developer performance so drastically, why are none of these gains being used to get back towards native app development?
Because devs lack the will to build native apps. Even on HN, native app dev is seen as somewhat esoteric because it isn't cross-platform by default.
There's plenty of pragmatic reasons not to build a native app. The concerning thing IMO is the hegemony of opinion here. After all, nothing says "hacker" quite like following all the rules properly and always doing the sensible thing. :)
> if LLMs are improving developer performance so drastically
IMO the jury is out on how much they are.
> why are none of these gains being used to get back towards native app development?
because the different platforms are still radically different in a way an LLM can't easily and simply paper over. How do I specify a UI in a way that an LLM can competently implement it in HTML, SwiftUI and whatever Windows is using these days?
> why are none of these gains being used to get back towards native app development?
One argument might be that, like with any LLM output, you still do need to know it well enough to know if it's good or not implementation-wise. You still need that knowledge to understand if your performance for rendering in some scenarios is going to fall off a cliff.
Web (via browsers or Electron/etc) are mostly one train of thought. When you're doing native application development using host OS frameworks, you have to actually know the framework. LLMs don't really save you from that; i.e, I could have an LLM spit out whatever flavor of Windows-specific UI I need. I have zero way of knowing whether it's correct or not.