Ben Davis (co-host of one of my favorite new podcasts this year, Nerd Snipe) has a fascinating take on a question I’ve seen many in the Apple community ponder as well: if these frontier models are so good, why do most AI apps from the big labs still kind of suck?

Davis wrote about this in relation to the ChatGPT/Codex desktop app, which has turned into a bit of a kitchen-sink design phenomenon with all kinds of features crammed into a UI that has two left sidebars, multiple modalities, and all sorts of disjointed menus.

To me the most interesting thing here is the implied question of “if the Codex team has unlimited tokens on really powerful unreleased models, why is the product getting worse?”

The lazy answer is “it’s just vibe coded slop, real artisanal code wouldn’t be like this”. Anyone who still says this is a moron and you can ignore them.

“Vibe coding” is not the problem. Frankly, these models are better at writing code than pretty much anyone at this point. You tell the model to make something and it’ll make that thing quite well. And also to be clear, Jira was horrid before LLMs existed. Good and bad products have always existed, and I actually think you can make infinitely better products now when using the agents properly (see T3 Code and Grok Bot).

I’ve been reviewing apps for over 17 years. Without a doubt, the most basic “vibe-coded” app created with Opus 5.5 today is infinitely more stable and nicer than any first app from an amateur developer in 2009. So if we agree that these models can write good code now, why is it that so many apps are still bad?

As we argued in our interview with OpenAI’s own Andrew Ambrosino (the irony is not lost on me), it comes down to human discernment, taste, and other qualities that can’t be turned into “metrics” for a model…at least not yet.

Davis continues:

To put a more precise definition on it, I think this “taste” is the ability to make good decisions in places where there isn’t a programmatic verification function.

For example: “make this function really fast” isn’t a “taste” task it’s a hill climbing task (make changes => test changes => repeat until goal met) which the models excel at right now (I think that any problem which can be expressed in this shape can be solved now by Opus 5.5)

“Which of these color palettes do you prefer?” is a “taste” question. You can’t really put a verifier on it other than your own opinion AKA your own taste. It’s a simple little example, but everything from codebase structure to dashboard layout to how features in chatgpt fit together all fit under here. Their implementations are “correct”, the tests pass, I just hate the choices they made.

“The tests pass, I just hate the choices” sums up my experience with coding agents perfectly. We’re working on our first two apps for MacStories (more in the near future), and while I’m not writing the code, I have to spend so much time thinking about usability decisions, onboarding flows, iOS best practices, and “it just doesn’t feel right” issues that models haven’t been able to abstract yet. I have to wonder if, in a rush to maximize infinite token usage and build everything “because why not?”, perhaps the big labs may have ignored these other aspects of good software design. I strongly believe that there’s more to a great app experience than elegant code that passes tests.

Knowing how these things can change so quickly in this scene, I’m sure this post will be obsolete in a few months. Maybe even weeks. But at this moment in time, Davis’ article is spot-on and human decisions still make a dent in software coded by agents.

Source: Apple.

Yesterday, Apple announced on its developer blog that it has begun taking App Store submissions for iPhone Duo apps. The new foldable phone will be in customers’ hands in just over two weeks on October 23 and with Xcode 27.1, developers can recompile existing apps and build new ones.

To prepare for the launch, Apple has provided links to design and App Store asset guidance, as well as submitting apps to App Store Connect.

Federico’s Frames CLI.

Also, if you’re a developer, don’t forget to check out Federico’s Frames CLI 1.5.0, which includes experimental support for the iPhone Duo. The feedback from developers has been that it saves a lot of time when preparing screenshots for the App Store. The Frames CLI is available on GitHub and there’s more information on MacStories here.

Today, on its developer blog, Apple announced plans to “…introduce additional controls to ensure that users who genuinely wish to grant an app this extraordinary level of access can only do so with very explicit user action.” The company says it’s doing so because of the dangers posed by AI agents.

According to Apple’s post:

Full Disk Access largely sidesteps these controls in order to allow backup apps to function properly on the Mac.

That’s nonsense. Looking at this MacBook Pro, only a handful of apps to which I’ve granted Full Disk Access are backup apps. Others include the Finder replacement Bloom, launchers like Alfred, the wonderful selection utility PopClip, Apple’s own Pixelmator Pro, Setapp, TestFlight, Supercharge, Madden NFL 27 Arcade Edition, Hazel, and many others. It’s a diverse selection of apps covering everything from Apple’s own apps to Mac utilities that are longtime favorites of MacStories readers, and even one Apple Arcade game.

What is valid is that AI agents pose risks if common-sense steps aren’t taken to limit their access to your data. So while the suggestion that Full Disk Access is just for backups doesn’t pass the smell test, Apple’s concerns about agents are well-founded.

The thing that bothers me about this post, though, is that it’s vague. On the one hand, it seems to suggest that users will simply have to jump through additional explicit hoops to grant Full Disk Access to their agents and other apps. On the other hand, claiming that Full Disk Access was designed solely for backup apps raises red flags that could signal that the company intends to restrict the kinds of apps that can use Full Disk Access. I sure hope not.

Even if you want nothing to do with AI agents, the changes that Apple is contemplating could impact a wide variety of the Mac apps you rely on every day. Apple needs to find a way enable reasonable customer protections without hamstringing the Mac’s utility.