This Week's Sponsor:

Crickets

The first alarm app for families.

Posts in Linked

Apple Updates Magic Keyboards→

Source: Apple.

Source: Apple.

Earlier this year, Apple swapped the text on some of its laptop keyboard keys for glyphs. MacRumors reports that the trend has now spread to four of the company’s Magic Keyboard models:

On the new keyboards, the tab, caps lock, shift, return, and delete keycaps are labeled with glyphs rather than edge text.

The keyboards with numeric pads get even more glyphs than the more compact models.

It’s a small change, but I like it. I burn through keyboards pretty fast with the amount of typing I do, and these come just in time to replace the Magic Keyboard on I use with my Mac Studio that has a slowly disappearing “A” key.

Permalink

Defining an “Agent Harness”→

I’ve recently been asked to explain what an “agent harness” is (particularly after I wrote about my favorite app of the year so far, Open Minis). I realized it was one of those concepts I could understand intuitively but not quite articulate. Thankfully, other people have done a better job of explaining it than I have.

Drew Breunig calls them “situated agents”:

Harrison Chase once excitedly shared an insight that agents are comprised of 4 things: a system prompt, a planning tool, a file system, and subagents. In the year-plus since he said that, I think this remains largely true. (Though you might tweak it to have general tools, etc.)

[…]

Imagine the simplest coding agent, and you at the keys. Let’s slowly zoom out and consider all the elements the harness can manage:

  1. The Session: The current task and context, as both a trajectory and a durable, branchable log. You can zoom backwards, fork, and replay it.
  2. The Environment: The instance, defined as a sandbox, terminal, worktree, computer, and/or container.
  3. The Repo: The project. Versioned with Git, it contains your code, history, current work, AGENTS.md, guides, and hooks.
  4. Memory: The person’s predilections, accrued over time, managing progress and past decisions.
  5. Skills: The domain, artifacts describing reusable workflows or domain knowledge worth wielding in this situation.
  6. The Team: Your colleagues and counterparts. Shared rooms, shared traces, project tracking tools, issues, and bug reports.
    • The Organization: The policies and audits, defined by legal, leadership, and procurement.
    • The Model: The LLMs themselves, the common artifact shared by all. Stochastic blobs we all poke trying to evoke positive outcomes. Log or train on their quirks and adjust.

I also thoroughly enjoyed this explanation and excellent visualization by Ted Spare, Dexter Storey, and Sarim Malik, writing for Rubric Labs:

A harness is the software that translates a model into a system that can affect its environment.

[…]

Functionally, a harness makes a model agentic, meaning it can take action.

And:

As coding agents begin to run for longer, and deploy more intelligence through dispatch, they are owning larger and more complex problems end to end, and the developer is less in the loop to steer the agent. The value of high quality planning increases as agents implement the plans more autonomously. Harnesses like Claude Code and Codex ship with a native planning mode, where the agent must first create a detailed Plan.md file with feedback from the user before executing. These harnesses then place a reference to the plan and the todo list into a top level state (system prompt) so that the agent doesn’t forget what it’s working on across long runs.

Given the multi-model, hybrid structure of the new Siri AI, we should probably assume Apple also made a lightweight “Siri harness” to aid the on-device orchestration of the entire system.

Permalink

Apple Music to Launch Labels on AI “Songs”→

Ethan Millman, writing for The Hollywood Reporter:

Apple Music will soon launch labels on songs created with artificial intelligence, the company said in an email sent out to industry partners on Thursday.

In the email, obtained by The Hollywood Reporter, the streaming service said that AI music labels will come “later this year,” though Apple Music didn’t disclose a specific launch date.

The new labels come months after Apple Music launched transparency tags back in March, available for record labels and music distributors to disclose when content uploaded was “materially generated using AI.”

Good. As much as I enjoy working and tinkering with AI, AI “music” falls squarely in the category of AI implementations I do not understand and cannot even be remotely interested in. Perhaps I’m old-fashioned, but what’s the point of listening to “music” performed by something you can’t see live on a stage, or that you know has never lived a real life? (Obviously we can’t see The Beatles or Beethoven perform live today, but we know they were real humans with real motivations behind their work.)

If you ask me, AI music shouldn’t even be allowed on streaming services, but I suppose it’s too late to fix that problem by now. Hopefully Apple will also include a system-level toggle to permanently hide AI “music” from Apple Music’s UI, too.

Permalink

Raising the Gates Is Not the Way to Improve the App Store→

Jeff Johnson has a knack for finding spam on the App Store. Yesterday it was review spam, and today it’s app submission spam. In a post where he called out an individual for releasing 41 apps, and presumably contributing to slow app review times, Johnson proposed a solution:

…bring back Apple Developer Program tiers and review app updates post-release for proven developers. Why should Marco Arment go into the same App Store review queue as AI slop? Does that make any sense for developers, for Apple users, or for Apple? Is there no way for developers to earn Apple’s trust, no matter how long they’ve been in the App Store, no matter how famous or beloved? Should professional software developers whose livelihood depends on the App Store go into the same review queue as hobbyists? Speaking for myself, I would be willing to pay a much higher developer program fee for improved service, including a separate review queue. I suspect that a much higher developer program fee might also deter scams and AI slop, typically looking for a fast, easy buck.

I’ve heard versions of this argument since before the App Store first opened its doors, and it’s never sat well with me. Maybe that’s because when I first heard someone argue that established developers or the ones who could afford it should get preferential treatment, I was an unknown hobbyist learning Objective-C and trying to build an app myself. It struck me as gatekeeping then, and it still does today.

There’s no doubt that there is spam on the App Store, but the way to remove it is to target the spammers, not new developers, students, and hobbyists looking to build their ideas. I know that being an indie developer isn’t an easy way to make a living, but erecting barriers to submitting apps is the surest way to starve Apple platforms of fresh, innovative ideas. That hurts everyone from users who would have fewer choices to the established developers who would find themselves writing apps for a stagnant platform.

Permalink

App Store Chaos→

Kalley Huang, writing for The New York Times about apps written with the help of AI agents that are flooding the App Store:

But as with many things A.I., just because something is easy to build doesn’t mean people will use it. It is not clear if vibecoding is breathing new life into the App Store or just cluttering it.

Last year, the number of new apps released in the App Store grew 30 percent to about 600,000, according to estimates by Sensor Tower, an app analytics firm. In the first half of this year, new apps doubled to about 560,000.

Now, Sensor Tower metrics should always be taken with a grain of salt. They don’t have direct access to Apple’s sales data, so they’re extrapolating from incomplete data that they collect themselves. That said, I think it’s fair to take their numbers as broadly representative of sales trends over time, and the story they tell, as reported by Huang, is interesting.

Based on Sensor Tower’s numbers, the total number of App Store releases peaked in 2016 at 890,000, hit a low of 420,000 in 2022, and this year, is on pace to pass 2016’s peak by a healthy margin. But app releases don’t equate to downloads, let alone sales. According to Huang’s reporting, downloads increased 3% in 2025 and 2% in the first half of 2026, far lower than the growth of new releases.

All of this tracks closely with what we’ve seen at MacStories. One subtle trend I’d add is that whereas for years most developers contacted us before they released an app, a lot of new developers are doing so after their apps are on the App Store. I suspect what I’m seeing is a new generation of developers learning the hard discoverability lessons of the App Store for the first time because when I check out these apps, they rarely have any App Store reviews.

The upshot of all these statistics and trends is App Store chaos of a magnitude that we haven’t seen in a long time. It’s a little like the App Store gold rush of the early days, but without the gold. Discoverability has gone from bad to worse, and the supply of apps is off the charts compared to the demand. With download numbers barely creeping up, the flood of new apps is making selling on the App Store harder for everyone.

Yet, it’s exactly this sort of chaotic disruption that leads to exciting new apps. And, it’s tools like Codex and Claude Code that empower and democratize app development, allowing people who would never have built an app to see their ideas become a reality. Those are things I love to see.

There’s no doubt that the App Store is out of whack thanks to agent-assisted coding, but like any market it will find its equilibrium again. In the meantime, it’s never been a better time to be a fan of apps because while a lot of those record numbers are comprised of mediocre apps, there are hidden gems, and we’re on the hunt for them.

Permalink

Running Simulators Inside Claude Code for Mac→

Claude Code has a new simulator button.

Claude Code has a new simulator button.

Claude Code’s Mac desktop app has added Apple simulator support, and although it’s billed as “iOS Simulator Support,” it actually works with any iOS, iPadOS, visionOS, or watchOS simulator you have installed.

The process of setting up a simulator is simple. A new button with an iPhone icon appears when you open an existing project. Click it and a new iPhone simulator pane opens to the right by default. However, clicking on the name of the simulator reveals a list of every available simulator. You can also run multiple simulators at once, but that immediately made my aging M1 Max Mac Studio start to chug a little.

With access to your running app, Claude Code is more effective at debugging UI bugs.

With access to your running app, Claude Code is more effective at debugging UI bugs.

Once you have the simulators that you want open, simply ask Claude Code to run and test your app, and it gets to work, building the app, installing it in the simulator, opening it, and poking around. I loaded up a simple word game I’ve been playing with, and after a few minutes, Claude Code found a UI bug while controlling the simulator. I asked it to fix the issue, which it did, then tested and committed. My testing has been limited, but so far it looks like a simple, effective loop.

It’s also worth noting that Claude Code is running the simulator directly inside the Claude app. This is not computer use, meaning windows aren’t going to be opening and getting in your way as you work on something else. All in all, the addition of the simulator, like the inclusion of an in-app sandboxed browser a couple of weeks ago, is a great update to Claude Code.

Permalink

Safari’s New MCP Server Is Great for Agents→

Saron Yitbarek, writing on the WebKit blog:

In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more powerful. We know agents are increasingly integral to the coding process and the Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window.

Any MCP-compatible client can connect to the Safari MCP server. By connecting your agent to a Safari browser window, your agent can emulate what your users experience, giving it the information it needs to debug more autonomously, like access to the DOM, network requests, screenshots, and console output.

Importantly:

The Safari MCP server runs entirely on your local machine and makes no network calls of its own. It also does not have access to your personal information in Safari (e.g. AutoFill or other browser activity). When it captures page content, screenshots, or console logs, that data goes directly to the agent you’re running — not to Apple. What happens to that data from there depends on the agent and model you’re using. As with any agent you give access to your browser, only use ones you trust.

For the past few months, I’ve been using Google Chrome on my MacBook Pro and Mac Studio not because I like the browser (in fact, I really dislike Chrome’s text rendering and UI), but simply because it was the best option for agents. In Codex specifically, between Playwright, Chrome Dev Tools, and OpenAI’s own Chrome extension, I could kick off research tasks (such as vacation planning and booking a hotel) that involved a browser directly from my iPhone, letting Codex drive the research on my remote Mac.

Safari in Codex.

Safari in Codex.

Now, thanks to Safari’s new MCP server, I no longer have to use Chrome on desktop and can return to a unified browser setup across all my devices. Even better: it actually looks like Apple shipped the most ergonomic browser MCP for agents to date. The MCP server has dedicated tools for page extraction (including getting webpages as Markdown, based on WebKit’s own conversion pipeline), evaluating JavaScript, DOM interactions (clicking, scrolling, resizing the viewport for mobile screens, etc.), taking screenshots, and more. I set this up immediately in Codex, and I also asked Codex about comparing Safari’s MCP to its own Chrome extension and the older Playwright. The verdict: although Chrome has a richer API with Chrome Dev Tools when it comes to network requests, Codex actually preferred Apple’s leaner, more direct approach for letting an agent drive and debug a browser.

I’m really happy to see folks at Apple embrace agentic tools: between the new MCP capabilities of Xcode and now this, it looks like Apple’s software (on the Mac, of course) is becoming more and more approachable by people who are working in new ways thanks to agents. Whether you’re a web developer or tinkerer, I highly recommend checking out what Apple has released in Safari Technology Preview. More of this, please.

Permalink

Snazzy Labs Puts the Mac’s Upcoming Game Porting Toolkit 4 Through Its Paces→

Over at Snazzy Labs, Quinn Nelson has a great in-depth look at the changes coming to Apple’s Game Porting Toolkit with macOS 27 this fall. Paired with Metal 4, it’s a real leap over what’s possible today, and Nelson showcases the difference well.

Thanks to the upcoming update, Nelson was able to use CrossOver, a Windows-to-Mac compatibility layer that allows PC games to be played on a Mac, to spotlight some impressive numbers on games ranging from Red Dead Redemption to the recently released 007 First Light.

Not all games Nelson tried showed the same leap in performance, but that’s true on compatibility layers like Proton on the Steam Deck, too. What’s remarkable is that it’s all done in software and as Nelson points out, the advent of coding agents like Codex and Claude may help bring more PC games to Mac using the Game Porting Toolkit by reducing the porting costs.

Nelson also makes a pitch for an Apple gaming device. I agree with him that more than ever, the pieces, right down to a hardware-focused incoming CEO, are all there for such a device, and I remain optimistic. However, I’ve made the case for such a device for years now to no avail. Still, whether or not Apple builds gaming hardware itself, watch the full video above. It’s a fantastic view of how far the Mac has come as a potential gaming platform since the advent of Apple silicon.

Permalink

Apple Improves Screen Time for Parents, but There’s Room to Grow→

One of Apple’s tentpole features at WWDC was a ground-up makeover to Screen Time that’s designed to give parents more granular and reliable control over their kids’ device use. I got a demo of the changes while I was at Apple Park, and they’re extensive. That’s good because Screen Time has been broken in a variety of ways for a while and isn’t very flexible.

My first impressions of the changes have been positive, but it’s worth noting that I don’t use Screen Time myself and my kids are grown. Screen Time wasn’t even available when it would have been useful to my family.

However, I do remember well the days when my kids were little, and so I sympathize with Patrick Klepek who wants more. Klepek gives Apple credit for improvements in Screen Time’s UI, but wants more:

But to crystalize my requests to Apple for the future:
- A dedicated Screen Time app
- The ability to invoke Siri or other shortcut-like features to lock devices
- Granular control over extending screen time to accommodate specific requests

I’d add another request that one of the journalists made during our demo that made a lot of sense. Like me, he has three kids and wondered if he could set up a baseline set of Screen Time rules and then copy them to his other kids, making age-appropriate tweaks for each kid. Apple said that isn’t currently possible, but it’s the sort of practical, reality-based suggestion that the company should prioritize. Being a parent means a lot of things, but it shouldn’t mean being an IT manager too. For tools like Screen Time to be adopted, they need to be easy, flexible, and powerful. That’s a tough combination, but I hope it’s been made a priority internally at Apple that will result in ongoing improvements to Screen Time during this OS cycle and beyond.

Permalink