[wasmainiac]

Because its failure rate is too high. Beyond boilerplate code and CRUD apps, if I let AI run freely on the projects I maintain, I spend more time fixing its changes than if I just did it myself. It hallucinates functionally, it designs itself into corners, it does not follow my instructions, it writes too much code for simple features.

It’s fine at replacing what stack overflow did nearly a decade ago, but that isn’t really an improvement from my baseline.

[leptons]

That's my experience too. It's okay at a few things that save me some typing, but it isn't really going to do the hard work for me. I also still need to spend significant amounts of time figuring out what it did wrong and correcting it. And that's frustrating. I don't make those mistakes, and I really dislike being led down bad paths. If "code smells" are bad, then "AI" is a rotting corpse.

[thewebguyd]

> If "code smells" are bad, then "AI" is a rotting corpse.

This is what's so frustrating about the hype bros for me. In most cases, everything AI spits out are code smells.

We're all just supposed to toss out every engineering principle we've learned all so the owner class can hire less developers and suppress wages?

I'm sure it's working great for everyone working on SaaS CRUD or web apps, but it's still not anywhere close to solving problems outside that sphere. Native? It's very hit and miss. It has very little design sense (because, why would it? It's a language model) so it chokes on SwiftUI, it also can't stop using deprecated stuff.

And that's not even that specialized. It still hallucinates cmdlets if you try to do anything with PowerShell, and has near zero knowledge about the industry I work in, a historically not tech-forward industry where things are still shared in handcrafted PDF reports emailed out to subscribers.

I'm going to leave this field entirely if the answer just becomes "just make everything in React/React Native because it's what the AI does best."

[fragmede]

That's interesting because I've been having pretty good luck with AI on SwiftUI. It didn't use to be but at some point they got good at that.

[qudat]

It’s not that it just makes mistakes but it also implements things in ways I don’t like or are not relevant to the business requirements or scope of the feature / project.

I end up replacing any saved time with QA and code review and I really don’t see how that’s going to change.

In my mind I see Claude as a better search engine that understands code well enough to find answers and gain understanding faster. That’s about it.

[anthonypasq]

can you imagine two years in the future and still believe this will be true? You are just dragging your feet. You will give in sooner or later, and i would suggest sooner.

[qudat]

Nah I’m using it extensively, I know the limits. I do not think scaling is going to magically fix the fundamental limits of attention LLMs