Claude Code Can Now Build and Test iOS Apps in Apple's Simulator

[budselectjr]

Brace yourselves for an avalanche of vibe-coded slop.

Whatever. I’m a small business owner and just replaced a SAAS CRM with one customized just for our industry and needs. Will save us hundreds a month.

 

[turbineseaplane]

Whatever. I’m a small business owner and just replaced a SAAS CRM with one customized just for our industry and needs. Will save us hundreds a month.

As a small business owner in particular (in a similar camp myself), do you ever worry about the implications of all this for people and wages and being able to survive?

 

[Luftkopf]

AI could barely string a function together 2 years ago. A year ago half the code I got from ChatGPT wouldn't even compile. Now tools like Claude Code and Codex iteratively work through the problem, compiling and testing as they go. You may be correct right now but the trajectory clearly shows AI coding is getting exponentially better.

People who continue to bang on about how experiences software engineers are better are, IMHO, just sticking their head in the sand. Soon there will be zero need for engineers to write code.

It won't be disastrous either. Yes Corporations could 'slash staff' to hit a quarters target, but at the same time someone in their bedroom can put together a tool/app that could undermine that entire corporations product line. AI is actually taking power away from big business and handing it to anyone with a great idea.

Its going to be a really exciting future I think!

You’re a lot more optimistic about this than I am.

The cracks are already beginning to show. Anthropic ran out of compute, major corporate AI users are drastically scaling back their AI usage as the benefit isn’t scaling and is way too expensive, etc.

It’s not going to go away, but it’s not going to usher in tech-utopia either.

 

[gsapienza]

AI could barely string a function together 2 years ago. A year ago half the code I got from ChatGPT wouldn't even compile. Now tools like Claude Code and Codex iteratively work through the problem, compiling and testing as they go. You may be correct right now but the trajectory clearly shows AI coding is getting exponentially better.

People who continue to bang on about how experiences software engineers are better are, IMHO, just sticking their head in the sand. Soon there will be zero need for engineers to write code.

It won't be disastrous either. Yes Corporations could 'slash staff' to hit a quarters target, but at the same time someone in their bedroom can put together a tool/app that could undermine that entire corporations product line. AI is actually taking power away from big business and handing it to anyone with a great idea.

Its going to be a really exciting future I think!

Someone without an engineering background cannot make anything too complex with even the best models out there. So that part is simply not true. The code output is actually really good but if youre an engineer you know thats a small part of the job

 

[Sosab123]

Guideline 4.3(b):

"Don’t submit apps that are indistinguishable from what’s already widely available. Opportunistically creating variants of existing app categories or popular apps degrades App Store discovery, reduces overall app quality, and harms both users and developers. [...] Other kinds of apps, such as drinking games, Kama Sutra, fart, and burp apps, are mediocre, low-quality, or low-effort and do not add value to the App Store. Repeated submissions of this kind may lead to removal from the Apple Developer Program."

Kama Sutra being a widely available app is pretty interesting I’ve never seen one

 

[ducknalddon]

That’s a bit like saying having a hammer is not an advantage… if I want to hammer in some nails, it’s a solid advantage. Beats fists or rocks…

It doesn't beat someone else with a hammer though. The original post implied some competitive advantage which just doesn't exist.

 

[Mac Fly (film)]

Kama Sutra being a widely available app is pretty interesting I’ve never seen one

Indian App Store?

 

[Dev-Guy]

Like some have already commented, I have mixed feelings about this.

In one hand, discovering genuinely good apps will be harder, because you won’t be able to know whether an app is code-vibed, containing many bugs that the “code prompter” doesn’t know how to properly solve, or has been written by a coder even if it’s with the help of AI. No way to know unless you already know the dev.

But on the other hand… like user @CalMin said, this tools, that are getting better and better at coding, allow us, mere mortals that never were able to learn code, to easily make small programs or scripts.

Let me share an example. There’s been a software niche that wasn’t covered until a few months: an Obsidian-like knowledge management software, with local LLM integrated RAG system. Most of the local RAG systems I know are based on complex configuration that involve several software components.

So there’s a guy (or gal, idk) that six months ago started building this app for macOS, Canto, using AI to develop it much faster, quickly implementing new features in few days. I haven’t tried it yet, so I still don’t know how polished it is, but if it wasn’t for AI-assisted development, apps such as this one wouldn’t exist.

Good points on both sides. I'd push back a little on the "code-vibed = buggy" idea though. The real divide isn't human-vs-AI code anymore, it's careful-vs-careless.

Where these tools genuinely shine is architecture and testing. A solo dev with zero CS background can now get code that's actually well-organized, not spaghetti, because the AI tends to default to sensible structure. And it's relentless about testing in a way a tired indie dev often isn't; it'll happily grind through edge cases most solo projects would just skip. So ironically, a "vibe-coded" app can end up more thoroughly tested than plenty of hand-written indie software that never had a test suite at all.

That doesn't solve your discovery problem, though. None of this guarantees the person using the tool actually understands what it built or catches it when the model confidently gets something wrong. There's no badge for "a competent person reviewed this," and there probably should be.

Still, Canto is a good example of the upside. That's a genuinely hard app to build solo. If AI is what makes that possible in six months instead of needing a small team, that's a real win for the niche, even with the tradeoffs you're describing.

 

[budselectjr]

As a small business owner in particular (in a similar camp myself), do you ever worry about the implications of all this for people and wages and being able to survive?

No. You can either sit and complain about how it’s not fair or find a way to adapt and create value.

 

[Dev-Guy]

The App Store has been full of human-coded slop from the start. Or do you think fart apps and flashlight apps were programming masterpieces? Slop is slop no matter who authored it. Very few apps are actually good and it will be the same for the one produced by coding agents. Most will suck and a few will be good.

The App Store was never a craftsmanship museum; humans shoveled in fart apps and flashlight apps long before AI could write code.

You're also right that "perfect software" is a myth. Software isn't a sculpture you finish; it responds to new OS versions, new needs, security holes nobody saw coming. Even the best apps ship constant updates, not because they were broken but because "good" keeps moving. Software that never updated wouldn't prove it was perfect. It would more likely mean it was abandoned.

One thing though: the real divide isn't who coded it, it's whether anyone's iterating with real users and actually cares. That produced junk in 2010 and it will produce junk with AI tools too. The tools change who can ship something, not whether they bothered making it good.

 

[Enlightened Doggo]

What's a harness? What's a swarm? A swarm of what? Against what cloud? Honestly!

Sweet child you'll understand when you are older

 

[cjbryce]

It gives you no advantage because everybody else has access to the same tools.

I strongly disagree. Not everyone has the same abilities for e.g. logic, imagination, business sense, solving &etc.

It’s the old adage: garbage in, garbage out.