The iPhone Duo.

Apple’s iPhone lineup is taking a different shape this year.

At today’s Surprise and Shine event, the company introduced the iPhone 18 Pro and 18 Pro Max alongside the iPhone Duo, its first foldable iPhone. The Pro models build on the familiar design introduced last year, while the Duo marks the debut of an iPhone with a brand new form factor that combines a smaller, outer display with a larger, almost iPad mini-like internal display.

As a longtime iPad user who’s long been fascinated by foldables (and I’ve tried some over the years, too), I’ve been eagerly anticipating Apple’s debut in this space. Based on what we’ve seen today, it looks like Apple was able to deliver on the promise of a new iPhone category that combines the best of iOS with concepts borrowed from iPadOS, turning the iPhone into a versatile pocket computer that epitomizes Apple CEO John Ternus’ concept of the “personal hub”.

As we’ll see in this article, while the iPhone 18 Pro’s story largely revolves around the camera (unsurprisingly) and improved performance (some of the A20 Pro’s numbers are, in fact, a surprise merely a year after the A19 Pro), the iPhone Duo marks a new beginning for iOS, which now supports features that never existed on the platform before, as well as a series of interactions that Apple is exploring for the first time.

Let’s dive in.

iPhone 18 Pro and iPhone 18 Pro Max

Let’s start with the iPhone 18 Pro and Pro Max, which follow a familiar approach: take the existing design from last year’s Pro models and improve the cameras, performance, and battery life.

Both phones feature the same 6.3-inch and 6.9-inch displays as last year, respectively, with 3,000 nits of peak outdoor brightness (also unchanged). The Dynamic Island is smaller, and because of that, it can now show more data – up to three Live Activities at once – without sacrificing Face ID.

The new Dynamic Island with more Live Activities in the iPhone 18 Pro.

“With iPhone 18 Pro, we’ve made advancements to the areas our users care about most: camera, performance, battery, and intelligence. And we didn’t just make incremental improvements in these areas — we took huge leaps forward to create the best Pro iPhone we’ve ever made,” said Greg Joswiak, Apple’s senior vice president of Worldwide Marketing. “iPhone 18 Pro makes it easy for anyone to capture stunning photos and videos using variable aperture, while providing more versatility for creators and more control for pros. Paired with impactful upgrades to Photographic Styles and powerful video capabilities, iPhone 18 Pro unlocks entirely new ways for users to express themselves.”

Cameras

As you know, I’m not a professional photographer, and I seldom take advantage of the latest “pro” features in the iPhone’s camera. But I, too, have to admit that the camera additions to the 18 Pro line sound remarkable.

The biggest change is the 48MP Fusion Main camera’s variable aperture. Six blades physically move inside the camera and adjust the opening between four settings: ƒ/1.48, ƒ/1.8, ƒ/2.8, and ƒ/4. In practice, this means the camera can let in more light in a dark scene or keep more people in focus in a group photo.

This can happen automatically, but you can also take over with the Camera app’s new Pro controls, which include aperture, shutter speed, white balance, and a histogram. As of the release candidate version of iOS 27 released a few hours ago, the Camera app supports the long-rumored control customization (on all iPhone models, including the current 17 Pro), too, giving you even finer control over the, well, controls you want to see available at all times.

New customizable controls in the Camera app for iOS 27.

Of course, there are also 48MP Ultra Wide and 4x Telephoto cameras, plus the usual optical-quality 8x option. On the software side, Photographic Styles is gaining texture and grain controls, Cinematic effects can be applied after capture to videos shot at up to 60 fps, and time-lapse now supports 4K Dolby Vision. Audio Mix is getting improved voice processing and music isolation as well.

What I find especially interesting, however, is the concept behind Apple Reference Image. When you take a photo in Reference mode, the Main camera captures signed sensor data that Private Cloud Compute authenticates and turns into an unalterable reference image. You can think of it as a digital negative. You can view the authenticated version of an image alongside the main one in Photos to see what was changed after capture, and, as Apple notes, this has interesting implications when it comes to AI. In an era where validating image authenticity is turning into a real challenge, I think we have to commend Apple for trying to do something in this field.

Apple Reference Image in the Photos app.

It’s also worth noting that Apple will add support for SynthID, the industry standard for watermarking images created with AI adopted by OpenAI, Google, and others. According to Apple, “SynthID will be available in a software update later this year and will be included for most edited images, depending on the edits applied”.

Performance and Battery

The new 2 nm A20 Pro features a 6-core CPU, 7-core GPU, and Dual 16-core Neural Engine. According to Apple, it offers up to 40% faster graphics and twice the AI processing power of A19 Pro.

Now, having recently written about the potential of the M5 Ultra and M6 for local AI on the Mac, I’m obviously very keen to see what the A20 Pro will mean for running local LLMs on the iPhone 18 Pro (and iPhone Duo, since it has the same chipset). For instance, would this chip run an edge-optimized model such as Liquid’s LFM2.5-8B-A1B at higher than 30 tokens per second? What about small specialized models such as Desert Ant Labs’ family of small language models – how much more efficient would they be on the A20 Pro compared to the A19 Pro? I can’t wait to find out.

In any case, to visualize Apple’s numbers announced today against current and previous generations of iPhones, I’ve put together some handy widgets and visualizations to help you put things in perspective.

Moving on to other performance-related changes, a redesigned vapor chamber with three times the surface area helps deliver up to 40% better sustained performance than iPhone 17 Pro. Given Apple’s focus on gaming and AI for these phones, I look forward to comparing heat dissipation between my 17 Pro and 18 Pro.

As for battery life, Apple quotes up to 36 hours of video playback for the Pro and a whopping 45 hours for the Pro Max – the longest battery life ever in an iPhone. (There’s a caveat: those figures apply to eSIM-only models; versions with a physical SIM get two hours less.) Also new this year: both phones can charge to 50% in around 15 minutes with a compatible 60W-capable USB-C adapter that supports Adjustable Voltage Supply, whereas MagSafe and Qi2 still top out at 25W.

Pricing and Availability

The iPhone 18 Pro starts at $1,199 in the U.S., while the Pro Max starts at $1,299 (a $100 price hike compared to last year for both versions).

Both models come in black, silver, glacier, and the new burgundy (which I think looks great), with storage ranging from 256GB to 2TB. Preorders open September 12 at 5 a.m. Pacific, with availability on September 18.

iPhone Duo

Alright, let’s now talk about the iPhone I’ve been dreaming of for the past several years.

The basic idea is easy enough to understand: the iPhone Duo is a foldable device with a passport-style design that has a smaller screen on the outside, and can be opened to reveal a larger one. You’ve seen foldables before. This one goes from a 5.4-inch display that opens up to reveal a 7.6-inch one inside – effectively almost reaching the dimensions of an iPad mini. When taking a look at pictures and videos of the iPhone Duo in portrait and landscape, it’s hard not to think of Apple’s diminutive tablet.

What’s more interesting, however, is what Apple has done with the iPhone Duo’s software to take advantage of that extra space. First off, it’s important to clarify that the iPhone Duo does not run iPadOS and it is not an iPad when you open it. The iPhone Duo runs a special version of iOS that was “inspired” by certain elements of the iPad – such as Split View multitasking, or inter-app drag and drop – but which also introduces new ideas never seen before in either iPadOS or iOS, such as tabletop layouts, Liquid Glass controls on the side of the screen, and more.

Design, Displays, and…Apple Pencil?

First, the hardware. The Duo is made of mirror-polished titanium and weighs 254 grams. Closed, it measures 117.8 × 84.1 × 11.3 mm; open, it’s 117.8 × 164.6 × 5.2 mm. Both OLED displays support ProMotion up to 120Hz, Always-On, and 3,000 nits of peak outdoor brightness. According to Apple, the inner screen gives you 50% more display area than an iPhone 18 Pro Max, and it supports any orientation.

The inner display, just like high-end iPad Pro models, has a nano-texture finish, which has been designed to reduce glare and make the crease less visible. Note the distinction here: Apple isn’t saying there’s no crease; they’re saying the material “minimizes crease visibility”. Judging from early pictures and hands-on videos posted online, it appears that the crease will be slightly visible when the inner display is viewed from certain angles.

During the event’s video, Apple was also very proud to show off the hinge mechanism they designed for the iPhone Duo, which is comprised of over 100 components that support the center of the display:

Johny Srouji’s salary, visualized.

Ceramic Shield protects the back of the device, with Ceramic Shield 2 on the outer display. The Duo also carries an IP68 rating for dust and water resistance. These are reassuring details in theory, but, as with any foldable, durability will have to be tested over time.

Now, what is arguably a pain point of this first-generation iPhone Duo is the lack of Face ID. Instead, Apple has put Touch ID in the side button, similar to the iPad mini, so it works regardless of whether the phone is open or closed. After nine years of Face ID on the iPhone, it’s going to be tough to get reacquainted with Touch ID; I hope that Apple’s placement of the button and support for multiple fingerprints will alleviate those concerns. We’ll see.

You can also unlock the Duo with an Apple Watch, which I assume is going to be similar to how this feature works with a nearby paired Mac. If that method works well, there’s a chance we won’t miss Face ID’s simplicity much, after all.

Lastly, in a first for an iPhone, both screens will support the Apple Pencil (USB-C model). This is what it looks like:

Sorry, wrong file. This is what it looks like:

In the announcement video, Apple said Pencil integration will be available “later this year”.

Cameras

The camera system is another area where the Duo differs from the Pro models. In the Duo, you get a 48MP Fusion Main camera with a fixed ƒ/1.6 aperture, plus a 48MP Fusion Ultra Wide with an ƒ/2.2 aperture and macro support. There’s no dedicated Telephoto lens, although the Main camera offers an optical-quality 2x option. The outer display has a 12MP Center Stage camera, while a separate FaceTime camera sits underneath the inner display and records video at up to 1080p and 60 fps. From Apple’s demo videos, it appears that the area surrounding the under-display camera will look slightly dimmer; I’d like to understand if this is something that will be visible at all times, or if it’s a UI decision to indicate where the camera actually is.

The under-display camera “lights up” in software during a FaceTime call.

What the Duo offers is also a series of features designed around the idea of having two screens. With Duo Preview, the person you’re photographing can see the live camera view on the outer display and adjust their pose or framing if they want to. You can use that screen to take selfies with the rear cameras, too. Kid Cue takes a more playful approach, putting Peanuts animations (and ideally something else, too?) on the outer display to get children to look at the camera while you’re framing a shot.

With the Duo propped up thanks to one of its “halves”, the new Smart Take feature uses on-device AI to recognize when people are posing and automatically take their photo. And Duo FaceTime lets someone sitting with you join a call using the outer screen and camera, rather than having everyone squeeze into the same shot.

We’ve seen some of these features on other foldables before, but I think Apple is offering a more complete, consistent package with these different “postures” for the iPhone Duo and the Camera app from the get-go.

Performance and Battery

The Duo runs the same A20 Pro as the Pro models, paired with its own vapor chamber.

Battery life is a little more complicated to describe when a phone has two displays. Apple quotes up to 31 hours of video playback on the inner screen or 44 hours on the outer one. The company also gives a separate estimate of up to 24 hours of “typical use”, based on using the two screens equally. Obviously, how you divide your time between the displays will make a difference here.

For charging, you’re looking at up to 50% in around 20 minutes with a 60W-capable wired adapter, or around 30 minutes with a compatible MagSafe charger and adapter. MagSafe and Qi2 both support up to 25W.

iOS and Multitasking

As a longtime iPad user, this is the part of the Duo’s story that interests me most. And I feel that, as someone who’s spent over a decade witnessing the iPad’s multitasking evolution, I’ve been waiting for this kind of iPhone model to arrive, and I can’t wait to get my hands on it.

Apple will ship the iPhone Duo with iOS 27.1, and the iOS interface has been adapted to function as a hybrid of a miniaturized iPadOS and an enlarged iOS that moves several controls off to the side of the screen.

For starters, Lock Screen controls, the Home Screen dock, and app navigation are moving to the side to make more vertical room for content. This makes sense given the device’s atypically short aspect ratio; as you can see from one of Apple’s shots, it seems like bottom tab bars will automatically be anchored on the right side of the screen and displayed vertically.

The Music tab bar on iPhone Duo.

More toolbars on the Duo.

When you open the Duo, the Home Screen displays two pages at the same time, which you can customize with widgets. It’s unclear, at the moment, whether the dock will support adding more than four app icons to it (my money is, sadly, on “no”).

The Home Screen.

Even the Dynamic Island has been rethought as a vertical element along the side of both displays.

Thus, the idea here is that iOS should follow along as you fold, rotate, or flip the Duo. This kind of layout flexibility is unprecedented for iOS, and when you factor in the fact that iOS 27 will be able to measure the angle to which the Duo is open in real time, it opens the door to some fascinating software design decisions. For example, iOS can dynamically adapt to a not-fully-open Duo and change the keyboard layout to move the keys away from the folding area:

Or, it can put the keyboard on the part of the screen that’s sitting flat on a surface:

Or, you can turn the device to portrait mode, and type on it as if it were a smaller iPad mini:

Then there’s Split View, which brings two apps side by side to the iPhone for the first time. You can also open two windows of the same app (like on an iPad) and save pairs of apps to return to later (like on Android). At the moment, it seems like the only way to add apps to Split View is from the Home Screen on one side of the screen; I’d love to know if dragging apps from Spotlight will also be supported.

Starting Split View from the Home Screen.

Creating app pairs to come back to later.

Another nice touch: StandBy no longer requires a charger on the Duo.

Prop the phone up, and you can use either display for widgets, photos, or a clock. There are new Calendar and Weather faces, Shared Albums in the Photos face, and more customization options, too.

Pricing and Availability

The iPhone Duo starts at $1,999 in the U.S. and comes in night sky and star white, with 256GB, 512GB, 1TB, or 2TB of storage. Preorders open October 16 at 5 a.m. Pacific, with availability on October 23 and a second regional rollout on October 30.

Apple is also selling a $79 Duo Case in navy blue and sand, plus a $129 Duo Folio with Kickstand in navy blue and taupe. The latter adds an adjustable stand for reading, watching videos, or FaceTime; both support MagSafe and can be ordered starting October 16. The full hardware specifications are available on Apple’s website.

As you can probably tell from this story, I’m going to get an iPhone Duo as soon as possible, and it’s going to be my primary device for the foreseeable future. I’ve been waiting for Apple to make an iPhone inspired by the iPad for a long time.

From what I’ve seen today, I think Apple is right: the iPhone Duo truly feels like the most transformational iPhone since the original.

October 23 can’t come soon enough.

You can follow all of our September 2026 Apple event coverage through our September 2026 Apple Event hub or subscribe to the dedicated September 2026 Apple event RSS feed.

Apple covered a lot of ground at today’s Surprise and Shine event, and the numbers help put the announcements in perspective.

After every Apple event, we like to collect the notable specs, comparisons, and other stats from the presentation and Apple’s supporting materials (Tech Specs pages and Newsroom posts). This year, I wanted to make this article a little more special than usual, so I did two things: I set up a workflow to collect even more data during the event (a combination of transcription and, later, YouTube summarization), and I’ve created a few interactive widgets explore some of the latest specs and numbers in more detail.

You can find the complete set of numbers below. Enjoy memorizing all of these.

iPhone 18 Pro and iPhone 18 Pro Max

Dimensions and Displays

• 150 x 71.9 x 8.75 mm: Height, width, and depth of iPhone 18 Pro, respectively.
• 211g: Weight of iPhone 18 Pro.
• 163.4 x 78 x 8.75 mm: Height, width, and depth of iPhone 18 Pro Max, respectively.
• 249g: Weight of iPhone 18 Pro Max.

Camera

• 48MP: Fusion Main camera resolution, with a 24mm-equivalent lens and variable aperture.
• 6 blades: The Main camera uses laser-cut blades to adjust its aperture.
• 4 settings: Manual Main-camera apertures: f/1.48, f/1.8, f/2.8, and f/4.0. Apple’s examples use f/1.48 for low light, f/1.8 for portraits, and f/4.0 for groups.
• Around 50% more light: Enters when the variable aperture opens in darker environments. 23:48
• 12MP at 2x: Optical-quality Telephoto option from the Main camera, at a 48mm-equivalent focal length.
• 48MP at 4x: Fusion Telephoto camera with a 100mm-equivalent f/2.8 lens.
• 12MP at 8x: Optical-quality Telephoto option with a 200mm-equivalent f/2.8 lens.
• 16x: Optical-quality zoom range: 8x optical-quality zoom in and 2x optical zoom out.
• Up to 40x / 24x: Digital zoom for photos and video, respectively.
• 18MP: Center Stage front camera with an f/1.9 aperture.
• Up to 4K at 120 / 60 fps: ProRes recording from the rear and front cameras, respectively, with external recording.
• 1080p at 30 fps: Spatial video recording.
• 4 microphones: Studio-quality microphones for recording.

A20 Pro and Performance

• 3x more surface area: Vapor chamber comparison with iPhone 17 Pro.
• Up to 40% gain: Sustained performance with the redesigned thermal system, compared with the previous generation.
• Up to 2x better: Sustained performance compared with iPhone 16 Pro and older. 20:12
• Up to 120 fps: Monster Hunter Outlanders supports iOS-exclusive Cinematic Graphics using the A20 Pro GPU; the game is due later in 2026. (22:19)

Battery and Charging

• Up to 36 hours: Video playback on eSIM-only iPhone 18 Pro.
• Up to 45 hours: Video playback on eSIM-only iPhone 18 Pro Max.
• Up to 50% in around 15 minutes: Wired charging on both Pro models, using a 60W-capable USB-C cable and a compatible 60W-capable-or-higher adapter with Adjustable Voltage Supply (AVS).
• Up to 50% in 30 minutes: Wireless charging on both Pro models, using MagSafe and a 35W-or-higher adapter, both sold separately.
• 5 minutes: Wired charging provides around 7 hours of video playback on iPhone 18 Pro Max.
• Up to 30 hours: iPhone 18 Pro Max usage on a full charge under Apple’s new representative usage model.
• 2 additional hours: Video playback on eSIM-only models compared with models that retain the physical SIM.
• Up to 24 hours: iPhone 18 Pro usage per charge under Apple’s new representative battery usage model. (21:06)
• 5 minutes: Faster wired charging provides around 6 hours of video playback on iPhone 18 Pro. (21:33)
• Up to 33 hours: Streamed video playback on iPhone 18 Pro in the U.S. eSIM-only configuration.
• Up to 40 hours: Streamed video playback on iPhone 18 Pro Max in the U.S. eSIM-only configuration.

Dynamic Island

• Up to 3 Live Activities: Can appear together in the Dynamic Island now.

Finishes, Storage, and Pricing

• 4 finishes: Black, silver, glacier, and burgundy.
• From $1,199: U.S. starting price for iPhone 18 Pro.
• From $1,299: U.S. starting price for iPhone 18 Pro Max.
• From $49.95 and $54.12 per month: U.S. Apple Card installments over 24 months for iPhone 18 Pro and Pro Max, respectively; eligibility and carrier selection apply.
• $175-$885: U.S. Apple Trade In credit for an eligible iPhone 13 or later; value depends on the device.
• Up to $1,200: U.S. select-carrier credits toward either Pro model for an iPhone 14-or-later trade-in, in any condition; carrier eligibility rules apply.
• From $34.99 per month: U.S. Apple Upgrade lease for iPhone 18 Pro over 24 months through Klarna; eligibility and an eligible carrier are required.

Availability

• September 12, 2026: Pre-orders begin at 5 a.m. PT in more than 65 countries and regions.
• 20 more countries and regions: Availability expands on September 25, 2026.

Accessories

• $49 each: U.S. price for the Clear Case or Silicone Case with MagSafe.
• $59 each: U.S. price for the TechWoven Case, FineWoven Wallet, or Crossbody Strap.
• $29: U.S. Wrist Strap price.
• 6 colors: Wrist Strap options: black, taupe, olive, crisp blue, magenta, and burgundy.
• 100% recycled polyester: Yarn used in the Wrist Strap.

iPhone Duo

Displays

• 7.6 inches: Inner Super Retina XDR display; 7.58 inches diagonally as a standard rectangle, with a smaller actual viewable area.
• 5.4 inches: Outer Super Retina XDR display; 5.36 inches diagonally as a standard rectangle, with a smaller actual viewable area.
• 90%: Outer display screen area relative to iPhone 18 Pro.
• 50% larger: Inner display screen area compared with iPhone 18 Pro Max.
• Later in 2026: Planned support for Apple Pencil with USB-C on either display.
• 80% larger: Inner display screen area compared with iPhone 18 Pro. (1:02:00)
• 1878 x 2670 pixels: Inner display resolution at 430 ppi.
• 1398 x 2034 pixels: Outer display resolution at 460 ppi.

Design and Durability

• Grade 5 titanium: Material used for the enclosure.
• 3x better: Ceramic Shield 2 scratch resistance on the outer display compared with the previous generation.
• More than 100 components: In the hinge controlling opening, closing, and center-display support.
• Up to 40% higher stiffness: Custom polymer in the inner display’s nano-textured cover layer, compared with other materials used in the industry.
• 2 colors: Star white and night sky.
• 3x stronger: Ceramic fibers in the antenna-split reinforcement inserts compared with Grade 5 titanium. (1:03:31)
• Up to 25 microlayers: Of custom photopolymer are 3D-printed after a laser scans each unit, to eliminate residual display waviness. (1:09:55)
• 117.8 x 164.6 x 5.2 mm: Height, width, and depth with Duo open.
• 117.8 x 84.1 x 11.3 mm: Height, width, and depth with Duo folded.
• 254g: Weight of iPhone Duo.
• 4 sensors: Ambient light sensors.

Cameras

• 48MP: Fusion Main camera with a 26mm-equivalent f/1.6 lens, photo capture at up to 48MP, and zero shutter lag.
• 24MP: Default rear-camera photo resolution.
• 2x: Integrated optical-quality Telephoto option from the Fusion Main camera: 12MP, 52mm-equivalent, f/1.6.
• 12MP: Outer Center Stage camera with an f/2.2 aperture.
• f/1.8: Under-display FaceTime camera, with 1080p video recording at 30 or 60 fps.
• 4x: Optical-quality zoom range: 2x optical-quality zoom in and 2x optical zoom out.
• Up to 10x / 6x: Digital zoom for photos and video, respectively.

Multitasking

• 2 Home Screen pages: Shown when Duo is open, with Today View on the left.
• 2 apps or windows: Split View can show apps side by side, or two windows of the same app.

Performance

• Up to 35% better: Sustained performance with A20 Pro and Duo’s custom vapor chamber, compared with iPhone 17 Pro.
• Up to 20% faster: A20 Pro’s 6-core CPU compared with A19 Pro, as described for iPhone Duo.

Battery and Charging

• 2 batteries: One high-energy battery on each side, managed together by energy-rebalancing algorithms.
• Up to 31 hours: Video playback using the inner display.
• Up to 44 hours: Video playback using the outer display.
• Up to 24 hours: Usage per charge when the inner and outer displays are used equally.
• Up to 50% in around 20 minutes: Wired charging with Duo open, using a 60W-capable-or-higher USB-C cable and a compatible 60W-capable-or-higher USB PD adapter.
• Up to 50% in around 30 minutes: Wireless charging with MagSafe or Qi2; Apple’s MagSafe test used Duo open and requires a 35W-or-higher adapter.
• 5 minutes: Fast charging provides up to 5 hours of video playback using the outer display. (1:12:43)
• Up to 37 hours: Streamed video playback on iPhone Duo using the outer display.
• Up to 26 hours: Streamed video playback on iPhone Duo using the inner display.

Pricing and Availability

• From $1,999: U.S. starting price for iPhone Duo.
• From $83.29 per month: U.S. Apple Card installments over 24 months; eligibility and carrier selection apply.
• From $57.99 per month: U.S. Apple Upgrade lease over 24 months through Klarna; 12-month terms are also offered.
• October 16, 2026: Pre-orders begin at 5 a.m. PT in more than 70 countries and regions.
• October 23, 2026: Initial availability for iPhone Duo.
• 28 more countries and regions: Availability expands on October 30, 2026.

Accessories

• $79: U.S. price for iPhone Duo Case, in navy blue or sand; orders begin October 16.
• $129: U.S. price for iPhone Duo Folio with Kickstand, in navy blue or taupe; orders begin October 16.
• Qi2 25W: Charger compatibility for both Duo cases, alongside MagSafe and Qi-certified chargers.

iPhone 18 Pro and iPhone Duo

Displays and Durability

• 3,000 nits: Peak outdoor brightness on both Duo displays and both Pro-model displays.
• IP68: Laboratory water- and dust-resistance rating for all three iPhones, tested at a maximum depth of 6 meters for up to 30 minutes.
• Up to 120Hz: ProMotion adaptive refresh rate on both Duo displays and both Pro-model displays.
• 2,000,000:1: Typical display contrast ratio.
• 1,000 / 1,600 / 1 nits: Maximum typical, peak HDR, and minimum display brightness, respectively.

Camera Features

• Up to 60 fps: Videos can receive Cinematic effects after capture.
• 4K: Time-lapse recording now supports this resolution and Dolby Vision HDR.
• 48MP: Fusion Ultra Wide camera shared by the three iPhones: 13mm-equivalent, f/2.2, 120-degree field of view, and 48MP macro photography.
• 4K at 120 fps: Dolby Vision recording with the Fusion Main camera on iPhone Duo and both iPhone 18 Pro models.
• Up to 4K at 60 / 30 fps: Dolby Vision Cinematic mode capture from the rear and Center Stage front cameras, respectively.
• Up to 2.8K at 60 fps: Dolby Vision Action mode recording.
• Up to 240 fps: Rear-camera slow-motion video at 1080p; Fusion Main also supports 4K Dolby Vision slow motion up to 120 fps.
• Up to 4K at 30 fps: Dolby Vision Dual Capture recording.
• Up to 4K at 60 fps: Dolby Vision QuickTake recording from the rear or Center Stage front camera.
• 8MP: Still photos captured while recording 4K video.
• Up to 63MP: Panorama photo resolution.
• 6 effects: Portrait Lighting effects.

A20 Pro

• 2 nm: Manufacturing process for A20 Pro.
• 6 cores: A20 Pro CPU: 2 super cores and 4 efficiency cores, with integrated Neural Accelerators.
• 7 cores: A20 Pro GPU.
• 50% more: A20 Pro memory bandwidth compared with A19 Pro.
• Up to 40% faster: A20 Pro graphics performance compared with A19 Pro.
• 32 cores: Total in the A20 Pro Dual 16-core Neural Engine.
• 2x: A20 Pro AI processing power compared with A19 Pro.
• Up to 20% faster: New A20 Pro super cores. (16:49)
• 2x faster: 8-bit floating-point math on the new GPU Neural Accelerators. (17:30)

Connectivity

• Wi-Fi 7 and Bluetooth 6: Supported by the N1 wireless chip, alongside Thread.
• 15% less energy: C2 modem consumption compared with C1X.
• Over 500 carriers: Support eSIM worldwide.
• 2 iPhones: Users can switch between them with the same phone number through iPhone Handoff; launch carriers are T-Mobile in the U.S. and Telekom Germany.
• Up to 50% faster: C2 modem uploads compared with C1X. (1:11:42)
• Up to 10Gb/s: USB 3 data transfers through USB-C, requiring a USB 3 cable rated for 10Gb/s.

Charging

• Up to 25W: MagSafe and Qi2 wireless charging.

Storage and SIMs

• 256GB, 512GB, 1TB, and 2TB: Storage options for iPhone 18 Pro, iPhone 18 Pro Max, and iPhone Duo.
• 2 active eSIMs: Dual eSIM support; stores 8 or more eSIM profiles.
• Approximately 7GB: Storage used by on-device Apple Intelligence models; the models can be removed by turning Apple Intelligence off.
• Approximately 12-24GB: Space used by a standard configuration, including iOS 27 and removable Apple apps.
• About 4.5GB: Storage used by Apple apps that can be deleted and downloaded again.

AirPods 5

Noise Cancellation

• Up to 50% more: External noise removed compared with AirPods 4 with Active Noise Cancellation.

Battery Life

• Up to 5 hours: Playback with Active Noise Cancellation on a single charge, on the Wireless Charging Case model.
• 1 hour longer: Single-charge playback with Active Noise Cancellation on the Wireless Charging Case model, compared with AirPods 4 with ANC.
• Up to 22 hours: Playback with Active Noise Cancellation using the Wireless Charging Case model and its case.
• Up to 4 hours: Listening with Active Noise Cancellation on a single charge, on the $129 model. (36:11)
• Up to 20 hours: Listening with Active Noise Cancellation using the $129 model and its charging case. (36:11)

Pricing and Availability

• $129: U.S. price for AirPods 5, including Active Noise Cancellation.
• $149: U.S. price for AirPods 5 with Wireless Charging Case, longer battery life, and on-stem volume control.
• More than 65 other countries and regions: Pre-orders are available in these markets in addition to the U.S.
• $30 less: U.S. price reduction for AirPods 5 with Wireless Charging Case, compared with AirPods 4 with Active Noise Cancellation. (37:16)

Apple Watch Series 12

Battery and Charging

• Up to 24 hours: Everyday battery life under Apple’s test profile, which includes sleep tracking.
• Up to 10 hours: Outdoor workout battery life, tested during Outdoor Run sessions without iPhone and with the heart-rate sensor on.
• 25% more: Outdoor workout battery life than the previous model.
• 15 minutes: Charging provides up to 12 hours of additional battery life, tested with Apple’s Magnetic Fast Charger and 20W USB-C adapter.
• 50% more: Additional battery life from a 15-minute charge compared with the previous model.

Design and Bands

• 60% tougher: Ceramic Shield 2 on aluminum models compared with the Ion-X glass on aluminum Apple Watch Series 11.
• 42mm and 46mm: Case sizes for Apple Watch Series 12.
• 4 aluminum finishes: Dark bronze, black, light gold, and space gray.
• 2 titanium finishes: Radiant gold and natural titanium for the standard titanium models.
• 2 ceramic finishes: Pearl white and night blue.
• 5 new colors: Nike Sport Bands and Nike Sport Loops: essential white, chalk calm, pavement grey, after dark black, and green spark.

Pricing and Availability

• From $399: U.S. starting price for Apple Watch Series 12.
• From $11.99 per month: U.S. Apple Upgrade lease over 24 months through Klarna; Apple’s 42mm example is $21.99 per month for a 12-month term, excluding taxes and trade-in credit.

Apple Watch Ultra 4

Battery and Workout Modes

• Up to 50 hours: Everyday battery life under Apple’s mixed-use test profile.
• Up to 84 hours: Battery life in Low Power Mode.
• 15 minutes: Charging adds up to 18 hours of battery life, tested with Apple’s Magnetic Fast Charger and 20W USB-C adapter.
• Up to 25 hours: Outdoor workout tracking in Extended Workout mode with full GPS and heart-rate readings; Low Power Mode is enabled and running-form metrics are unavailable.
• 25% increase: Extended Workout battery life compared with the previous model.
• Up to 45 hours: Outdoor runs, walks, and hikes in Max Extended Workout mode; Low Power Mode is enabled, with alerts, splits, and some metrics unavailable.
• Every second: GPS readings continue in Max Extended Workout mode.
• Up to 18 hours: Workout tracking with full GPS and heart-rate readings. 52:03

Finishes and Bands

• 2 titanium finishes: Natural and black titanium.
• 3 Trail Loop colors: Dark umber, sand, and burgundy.
• 3 Alpine Loop colors: Desert, dark olive, and burgundy.
• 3 new Ocean Band colors: Translucent gray, translucent kelp, and translucent black, in translucent silicone.
• 4 options: Fathom and Wonder watch-face options on Apple Watch Hermes Ultra 4, from the ocean surface to the seabed.

Pricing, Availability, and Satellite

• From $799: U.S. starting price for Apple Watch Ultra 4.
• From $24.99 per month: U.S. Apple Upgrade lease over 24 months through Klarna; Apple’s $799 model example costs $44.99 per month over 12 months, excluding taxes and trade-in credit.
• 2 years free: Emergency SOS, Find My, and Messages via satellite with activation of Ultra 3 or later; Find My and Messages require a carrier plan.

Apple Watch Series 12 and Ultra 4

Health Sensing and Readiness

• Over 1,000 participants: In Apple’s heart-rate accuracy study comparing the new sensing system with leading wearables.
• Every 5 seconds: Passive heart-rate measurements throughout the day.
• Up to 24 times more often: Heart rate variability (HRV) measurements.
• As often as every 5 minutes: Heart rate variability (HRV) measurements on Series 12 and Ultra 4.
• 2 HRV variants: Recovery HRV and overall HRV are available in the Heart Rate app.
• 0-10: Readiness score, updated throughout the day, with recommendations of Recover, Pace Yourself, Ready, or Go For It.
• 1,000 steps: Accuracy test used for Apple’s step-tracking comparison, checked against video step counting.
• 22 years or older: Intended age range for the ECG app.
• 18 years or older: Intended age range for sleep apnea notifications, for people without an existing sleep apnea diagnosis.
• 40 years or older: Age range for cycle deviation notifications that include perimenopause.
• 3 core elements: Improved in the Health Sensing System: electrode surface area, photodiode arrangement, and green LEDs. 39:58
• 60 times more frequent: Background heart-rate readings compared with before. 40:37

Health App and Lab Tests

• Over 50 biomarkers: Planned lab tests ordered through the redesigned Health app will measure these key biomarkers.
• $119: Price for the planned lab tests ordered through the Health app in the U.S.
• Approximately 2,000 locations: Quest Diagnostics sites in the U.S. for the planned Health app lab service.
• Later in 2026: The redesigned Health app is planned to launch, starting in U.S. English, with more languages to follow. 46:02

Intelligence and watchOS

• 15 seconds: Previous conversation shown as text by Live Rewind, arriving in beta in late 2026, initially in English and outside the EU.
• 5 apps: Siri-suggested icons in the dynamic app grid in watchOS 27.
• 2 languages: Workout Buddy supports English and Spanish; use without iPhone nearby requires Wi-Fi or cellular, a paired Apple Intelligence-enabled iPhone, and Bluetooth headphones.

Availability

• More than 50 other countries and regions: Watch Series 12 and Ultra 4 pre-orders are offered in addition to Australia, Canada, France, Germany, India, Japan, the UAE, the UK, and the U.S.

And More…

Siri and Apple Intelligence

• Over 2.5 billion requests per day: Made by Siri users. 11:39
• Over 300,000 apps: Already work with Siri AI, including existing actions such as messaging and audio playback. 12:28
• 16 languages: Supported by Apple Intelligence with the September OS releases. 15:35

Software and Services

• 13 years: Minimum age for Siri AI.
• 1 additional year: Free satellite features for eligible existing iPhone 14, 15, and 16 users activated in a supported country before Apple’s September 9 midnight PT cutoff.
• 3 months free: Apple One for new or qualified returning subscribers buying an eligible device, including either Pro model; offer begins September 17 in selected markets.
• At least 12GB: Unified memory required for Apple’s most powerful on-device model on supported iPads with M4 or later and Macs with M3 or later.
• 3 months: Apple Fitness+ and Apple Music offers for new subscribers buying Series 12, SE 3, or Ultra 4; regional and service eligibility applies.
• Up to 80% faster: AirDrop transfers with iOS 27. 30:07

You can follow all of our September 2026 Apple event coverage through our September 2026 Apple Event hub or subscribe to the dedicated September 2026 Apple event RSS feed.

At today’s Surprise and Shine event, Apple announced a lot of dates. Most of the new hardware arrives on September 18, but the brand new iPhone Duo won’t launch until October. Before then, Apple’s next round of major OS updates arrives on September 14.

Here’s a rundown of the preorder, release, and rollout dates. Later today on MacStories, John and I will be sharing detailed overviews of all the major announcements from today, and you can expect our annual OS reviews to be published – as always – next week.

As a bonus, check out the calendar widget we’ve prepared to visualize all of Apple’s release notes. Stay tuned for more of these on MacStories today: we’re going to have some fun with our coverage this year.

iPhone 18 Pro and iPhone 18 Pro Max

Pre-Orders: Saturday, September 12, 2026, at 5:00 a.m. Pacific / 8:00 a.m. Eastern

In Stores and Deliveries: Friday, September 18, 2026

According to Apple’s announcement, the initial launch covers more than 65 countries and regions. Availability expands to 20 additional countries and regions on Friday, September 25.

iPhone Duo

Pre-Orders: Friday, October 16, 2026, at 5:00 a.m. Pacific / 8:00 a.m. Eastern

In Stores and Deliveries: Friday, October 23, 2026

iPhone Duo launches in more than 70 countries and regions, with 28 additional countries and regions following on Friday, October 30. It ships with iOS 27.1. Apple’s iPhone Duo Case and iPhone Duo Folio with Kickstand will be available to order on October 16, too.

Apple Watch Series 12 and Apple Watch Ultra 4

Pre-Orders: Today, Wednesday, September 9, 2026

In Stores and Deliveries: Friday, September 18, 2026

Both Apple Watch Series 12 and Apple Watch Ultra 4 follow the same schedule. The new Apple Watch bands are also available to order today and arrive in stores on September 18.

AirPods 5

Pre-Orders: Today, Wednesday, September 9, 2026

In Stores: Friday, September 18, 2026

The dates apply to both AirPods 5 and AirPods 5 with Wireless Charging Case, launching in the U.S. and more than 65 other countries and regions.

iOS and iPadOS 27

Release Date: Monday, September 14, 2026

watchOS 27

Release Date: Monday, September 14, 2026

macOS Golden Gate

Release Date: Monday, September 14, 2026

tvOS 27

Release Date: Monday, September 14, 2026

visionOS 27

Release Date: Monday, September 14, 2026

Siri AI

Initial Beta Rollout: Monday, September 14, 2026, in English on supported devices with iOS 27 and watchOS 27

Additional Languages: French, Japanese, Korean, Portuguese, and Spanish in October; Apple has not announced a specific day yet.

We have also prepared a widget that helps you visualize the availability of different features in multiple regions, based on what Apple revealed today (mostly in small print in footnotes of their press releases).

You can follow all of our September 2026 Apple event coverage through our September 2026 Apple Event hub or subscribe to the dedicated September 2026 Apple event RSS feed.

The new ChatGPT widget for iOS.

The most recent update to the ChatGPT app for iOS has introduced a new feature that will make those who rely on the company’s AI assistant for work-related tasks quite happy: a customizable widget that lets you control which shortcuts can be placed for convenient access on the Home Screen.

The new widget is called ‘ChatGPT shortcuts’, and it comes in two sizes – small and medium. Alas, the company didn’t add support for large widgets on iPhone yet, nor did they roll out an XL widget for iPad users. I hope more sizes will be coming soon. Unlike the existing ‘ChatGPT’ widget, the new one allows you to personalize which shortcuts are visible on the Home Screen. Once added, long-press the widget, select ‘Edit Widget’, and you’ll be presented with options to choose which buttons you want to show and whether labels should be displayed underneath them or not.

What’s especially nice about these widgets is that they cover the full spectrum of “ChatGPT surfaces” now offered by OpenAI: Chat, Work, and Codex Remote. For each, you can swap default buttons for the following ones:

• Chat
  • New chat
  • Camera
  • Photos
  • Dictation
  • Voice
• Work
  • New work chat
  • Work camera
  • Work photos
  • Work dictation
  • Work voice
• Remote
  • New remote chat
  • Remote camera
  • Remote photos
  • Remote dictation
  • Remote voice

I’m a huge fan of Codex Remote for iOS and iPadOS: as things stand right now in the AI industry, OpenAI’s Remote “app inside an app” for iPhone and iPad is the only intuitive, full-featured solution to start new chats in a remote agent running on macOS directly from iOS and iPadOS. (I am as surprised as everyone else that Anthropic, who were first to the “remote control” space, haven’t shipped a comparable experience in Claude for iOS. Supposedly, that is coming “soon”.)

What do you want to open – Voice or Voice?

Even more impressively, Remote voice (a version of ChatGPT Voice that runs in Codex on the Mac and lets you have bidirectional conversations from the iPhone while the agent is running on the Mac and orchestrating threads there) can now also be accessed from Control Center and the Lock Screen via a dedicated control. Unfortunately, this control has the same icon as regular ChatGPT Voice (which runs in the cloud, not on your Mac). I know: it can all be very confusing, and I hope OpenAI brings some clarity to these icons soon. On a similar note, I wish OpenAI’s iOS team also offered the widgets’ new shortcuts as proper actions in the Shortcuts app. Right now, these launchers are only available from the Home Screen.

The new customizable widgets are the latest entries in a larger push by OpenAI to improve the performance of Codex Remote on iOS and other design changes for iPhone and iPad users. The ChatGPT app recently received a redesigned ‘latest photos’ picker in Chat and Work modes (long-press the + button in the text box, and you’ll see), a tweaked reasoning selector, and the cloud browser we covered earlier this week on MacStories.

Earlier today, Apple unveiled the new generation of Mac mini and Mac Studio, featuring the latest entries in the Apple silicon family of chips: the M6, available in the Mac mini, and the M5 Ultra, exclusive to the Mac Studio. You can read more details about the announcement and related specs in John’s overview.

As someone who’s been working with an M3 Ultra Mac Studio (on loan from Apple) with 512 GB of RAM for the past year (plus two separate M4 Mac minis) with a particular focus on local AI models and performance gains enabled by Apple’s MLX framework, I obviously am very interested in these new machines. To give you some context: my current workspace for my upcoming iOS and iPadOS 27 review, which lives in Notion, is entirely managed by a series of local agents running the latest DeepSeek-V4-Flash via MLX on the Mac Studio, which continuously scan the project for new notes, sources, and research material that is automatically categorized and linked in the chapters that I’m writing. So, yes, I’m sure I’ll have more thoughts on the new Mac minis and Mac Studios soon. In the meantime, I thought it’d be fun to break down the local AI-related details from Apple.

First, the M6. While it may not be the powerhouse that the M5 Ultra is, it’s an interesting new chip because of its new 2 nm process and dual Neural Engine system:

M6 is built using cutting-edge 2 nm process technology, packing greater transistor density into a smaller die for a major leap in performance and power efficiency. M6 also introduces a Dual 16-core Neural Engine, providing up to 2x the peak compute over previous generations to make on-device AI workflows run even faster. System frameworks can automatically utilize both engines simultaneously, enabling applications to see faster model execution.

But that’s not all: the new 12-core GPU (which has two more cores than the M4’s old GPU) now features Neural Accelerators in each core for the first time on the Mac mini. The result, according to Apple, is “4x faster AI performance and 2x faster graphics than Mac mini with M4”. If these numbers hold up and scale linearly, a local Mixture-of-Experts model such as Qwen 3.5-35B-A3B, which would run at ~17 tokens/sec on average on a base M4 Mac mini with 16 GB of RAM, could realistically generate output at over 60 tokens/second with the base model M6 Mac mini.

Based on what we’ve seen so far, the one downside of the M6 Mac mini is that it does not have Thunderbolt 5 ports; those are exclusive to the M5 Pro model, also announced today. As Apple also notes, Thunderbolt 5 allows multiple M5 Pro Mac minis to run local AI models as a single cluster (for example, using something like exo). Alas, that won’t be possible with the M6 Mac mini and its Thunderbolt 4 bandwidth bottleneck. Nonetheless, I’d be intrigued to compare the performance of the widely regarded Qwen3.8-27B and DeepSeek-V4-Flash models on the new M6 Mac mini.

Moving on to the flagship M5 Ultra Mac Studio, let’s start here:

With M5 Ultra, Mac Studio achieves up to 4.3x the peak AI compute performance of M3 Ultra and a staggering 9.8x more than M1 Ultra. Combined with up to 512GB of unified memory and 1.2TB/s of memory bandwidth, 50 percent higher than before, Mac Studio lets users run massive models entirely on device with complete privacy — without counting tokens or worrying about rising cloud costs.

As seen on the Mac Studio’s product page, the 512 GB RAM version of the M5 Ultra Mac Studio will only be available in “late October”. Unlike the M6, the M5 Ultra supports Thunderbolt 5, which will allow customers to run multiple Mac Studios in a cluster with shared memory to distribute inference across machines. And, according to Apple, a cluster of four Mac Studios yields three times the performance of a single Mac Studio.

Speaking from personal experience, I know that my M3 Ultra Mac Studio using oMLX can run DeepSeek-V4-Flash locally with generation averaging 35 tokens/second. Assuming a linear 4x increase, that would put the same model at over 120 tokens/second on an M5 Ultra Mac Studio. To put things in perspective, that kind of performance would be faster than any AI chatbot website, it’d be faster than many providers who offer a “fast” mode for their models, and it’d only be second to either dedicated NVIDIA PC clusters at home or specialized inference providers such as Cerebras or Groq…which are running in full-blown data centers. Sure, you would need a computer that is likely going to cost more than $20,000 to make it happen, but it’d still be possible on a single machine that is small, quiet, and that – in theory – any consumer can buy off the shelf.

It’s also interesting to consider the implications of M5 Ultra for running much larger models that would have typically required aggressive quantization to even stay in memory and produce any useful output. For example, Z.ai’s GLM-5.2 (a 744B MoE model) could run at up to 17 tokens/second on an M3 Ultra Mac Studio with 512 GB of RAM; the same person was even able to get the massive Kimi K3 model to run on a single machine…with decoding performance up to 3 tokens/second. You see where this is going: by continuing to push the envelope of what is possible with M-series chips, Apple is gradually making it possible to run frontier open-weight models on local hardware that takes up as much space as four Mac minis stacked together.

Obviously, for now, this is all theoretical: we’re going to need actual benchmarks to objectively measure the improvements and performance gains of the new chips. But if Apple’s claims hold up – and I have no reason to believe they won’t – I believe both the M6 and M5 Ultra will meaningfully shake up the landscape of local AI models on macOS, reinforcing, once again, that Apple continues making the best computers for AI in the industry.

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.

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.

My Home Screen setup with Liquid Glass widgets powered by Lock Launcher.

I don’t think I ever mentioned it on MacStories (although I probably did at some point on AppStories or Unwind), but my favorite “launcher” app for iOS is a utility called Lock Launcher, which I’ve been using on and off for the last couple of years. Lock Launcher started as an app for adding URL schemes to the Lock Screen a few years back, and it gradually evolved into a comprehensive “widget studio” app to design launcher widgets of all kinds for the Home Screen, Lock Screen, Dynamic Island, Live Activities, and more.

Anyway, I’m covering the app on the site today because it was updated with two features that I didn’t think were possible or allowed on the App Store, and I want to highlight them for our readers. I’m not really sure how the developers were able to add these features to the app; you may want to download it from the App Store quickly, just in case.

For starters, Lock Launcher now lets you create launcher shortcuts that open apps directly and immediately, rather than redirecting you to the Lock Launcher app first.

For years now, launcher apps on the iPhone have had to employ this workaround: you’d tap on a shortcut that opened, say, Ivory, but you would see the launcher app flash onscreen briefly before redirecting you to the actual destination app you selected. Somehow, Lock Launcher is now circumventing this limitation with a ‘Direct Open’ mode that I haven’t seen in other launcher apps for iOS. That sequence of widget, host app, and destination app was, ultimately, the reason why I always stopped using third-party launcher apps, and I love that it’s been removed by Lock Launcher.

At long last, I’ve been able to create a dense Home Screen with 40 icons (36 in the widget plus 4 in the dock), and they all launch directly when tapped.

My new Home Screen powered by Lock Launcher.

The screenshot above brings me to the second feature added in the version of Lock Launcher currently available on the App Store: XL widgets on iPhone in iOS 27.

Now, as far as I know, if an app wants to adopt an API exclusive to a future version of iOS, it typically needs to be built against that version’s SDK using the corresponding Xcode beta. However, the App Store isn’t currently accepting apps built with the iOS 27 SDK. And yet, the Lock Launcher developers must have figured out a way to support the new systemExtraLargePortrait widget size and make it work on devices running iOS 27 even though the app was built with the iOS 26 SDK. My best guess: they’re using a workaround that involves visionOS 26 APIs, since the Vision Pro received support for that family of widgets last year. (I’d love to know more about this.)

These two features, combined with the ability to apply the Liquid Glass material to widgets for beautiful refractions of the system wallpaper, make Lock Launcher the most powerful and customizable launcher utility on iOS to date. I hope writing about it doesn’t get the developers in trouble.

Lock Launcher is available for free on the App Store, with advanced features available through an optional Pro in-app purchase.

Open Minis for iOS.

Every once in a while, I come across a third-party app that either resets my expectations for a particular niche of software on iOS or creates an entirely new category altogether. I’ve had quite a few of these moments in the 17 years I’ve been writing app reviews at MacStories: Editorial, Workflow, Obsidian, Sky, and, most recently, OpenClaw come to mind. Over the past few weeks, I’ve had another such moment with Open Minis, a new chatbot app for iPhone and iPad that I can best describe as getting a preview of Siri AI’s agentic future, today.

Open Minis is an on-device agent that lets you use any frontier model for conversations, with a twist: unlike other AI wrappers, this app deeply integrates with all sorts of native Apple system frameworks using official APIs available to third-party developers. Open Minis can control Reminders and Music, which we have seen before, but also Calendar, Maps, HomeKit, HealthKit, and Files; it can even work with frameworks such as Vision for OCR, Apple NLP for natural language processing, the iOS clipboard, speech recognition and dictation, NFC, and Bluetooth. Furthermore, Open Minis comes with its own configurable workspace in the Files app, has an on-device memory system, and features browser-use capabilities via a (once again, native for iOS developers) built-in WebKit web view.

Effectively, Open Minis is what would happen if you rolled Claude Code and OpenClaw into one intuitive agentic experience designed for Apple users, with a powerful tool-calling harness that can improve and tweak itself, and with integrations specifically designed for the Apple ecosystem. It is the most impressive indie app I’ve seen in a while. If you were disappointed by the lack of power-user capabilities in Siri AI, this is a real, currently shipping example of what Siri AI could be if only it were powered by a frontier model with truly agentic functionalities.

The iOS CLI

The trick hidden up Open Minis’ sleeve is as ingenious as it is obvious: all the Apple framework integrations it supports are powered by command-line interfaces (CLIs) that bridge native Apple APIs (EventKit, MusicKit, HomeKit, etc.) to a code environment that modern LLMs can understand and operate with. To make all of this work behind the scenes, the developer of Open Minis had to create dedicated CLIs for each of these frameworks, which – and here comes the other trick – are driven by a model harness that has access to a built-in Linux terminal and is sandboxed to the app’s workspace.

Specifically, Open Minis runs a version of iSH, a popular Alpine Linux shell that operates a persistent, emulated Linux environment for ARM64 architecture in a sandboxed fashion. The shell inside Open Minis can download external packages from the web using Alpine’s apk package manager (which means that you can access popular tools such as ffmpeg and yt-dlp directly from the app), has its own Linux filesystem (exposed in the Files app as a native file provider location), and is able to call bridged Apple CLIs, as well as any kind of MCP server (via MCP code execution, another trend in the AI industry these days). Think about it this way: if Claude Code or Codex on the Mac can do anything across the entire filesystem by virtue of running in the Terminal app, Open Minis can do (almost) anything within its app sandbox thanks to a built-in terminal emulator – including running Python, using Git and SSH, and accessing standard Unix text utilities.

Minis’ built-in shell (left) and dedicated workspace in the Files app (right).

However, this doesn’t mean that, when using Open Minis, you’ll be looking at a terminal UI all the time: the underlying shell is simply what makes all of this possible behind the scenes. The app can display a picture-in-picture terminal preview that you can open to preview what it’s doing, but you don’t have to. The app’s main interface is your classic, chatbot-style UI that, depending on the model you’re using, will display interleaved thinking blocks, tool calls, and messages in a conversation transcript.

The regular chatbot UI of the Minis app.

The other hidden power of Open Minis (which is reminiscent of OpenClaw, or, perhaps more aptly, a self-improving system such as Hermes Agent) is that it can inspect and modify its own workspace via dedicated Minis CLIs. For example, you can ask Minis – in natural language, of course – to add a new model or MCP server, and the app will bring up a native settings screen and ask for permissions to do so. If you want to store a password or API token, the app won’t do it in plain text: it’ll display a native, Keychain-based page where you can securely store your credentials. And more importantly, Minis’ own CLIs are used to recall previous conversations via the app’s memory system (based on Markdown files), create skills, and answer questions about the app itself. For instance, when I asked Minis to describe what Apple CLIs it has for iOS users, it happily provided a full guide:

Asking Minis about itself and the CLIs it has.

Or when I asked to recall all the things we worked on during the day, Minis used one of its CLIs to read transcripts of previous chats (which, again, are simply stored in the Files app), recall memories, and present me with a useful summary of all the tasks we completed.

Minis can inspect its own sessions as well as user memories to recall previous conversations.

The same is true for adding new functionalities to Minis. Since it’s running a Linux shell with access to Python and can store assets in a persistent Files workspace, I figured I could ask Minis to install my own Apple Frames CLI for itself by giving it a link to my GitHub repo. GPT-5.6 Sol (my model of choice in the app) didn’t hesitate: it found all the dependencies for the Frames CLI, installed them, pulled the CLI’s official skill, and was good to go a minute later. And since Minis also comes with a native Photos integration, I was able to ask:

Grab my three most recent screenshots, randomize their frame colors, merge them, and save the image to my Temp Files folder.

A few seconds and Apple CLI calls later, Minis saved the resulting framed image to a folder of my choosing. The ability to work in any folder in the Files app outside of Minis’ sandbox is another official iOS API that the app is leveraging; we first saw the ability to “mount” specific folders from the Files app in Working Copy years ago, and the feature was later adopted by the likes of Ulysses, iA Writer, MWeb, and other document-based apps. In Open Minis, you can bookmark any folder from any file provider location in the Files app and tell your agent to save files to or read them from there.

Minis can’t write images to the iOS clipboard, but it can save files in any (previously bookmarked) location of the Files app.

Minis’ settings for managing mounted folders.

This feels magical to me, but it’s merely one of the many examples of what is possible when you combine large, powerful models with the more-open-than-you-think, secure nature of iOS and iPadOS.

Working with Open Minis on iOS

All of this a lot to wrap your head around at first, and there’s no denying that Open Minis is a power-user tool designed for people who, like me, enjoy using frontier models and living at the bleeding edge of AI. What’s different in this case, though, is the fact that Open Minis – unlike other apps – embraces its Apple-first nature by fully supporting technologies that are made by Apple, released to third-party developers, and not being used by Siri AI at all at the moment.

It’s impossible to “review” an AI chatbot app since everyone’s use cases are so different, but I’m going to nevertheless describe a few scenarios that should give you an idea – and hopefully reset your expectations, too – of what can be accomplished with an AI that has deep hooks into iOS.

For starters, you can use any model you want in Open Minis, including the latest GPT-5.6 models, Claude Fable, anything from OpenRouter, and more. (I even asked Open Minis to create our own proxy for the OpenAI API, running on my Mac Studio, so I could use Sol in Fast mode; it works!) You can press the / button above the keyboard to trigger reasoning levels, compaction, memories, and skills; you can also create model groups, model defaults, and subagents from the app’s settings, then ask the model to use a specific set of subagents for a particular task, and it’ll do it.

Managing model providers, groups, and subagents in Minis.

Approach this app with this concept in mind: nearly everything about it is open and configurable by just talking to it. Short of rewriting the app’s code itself, you can ask Open Minis to tweak all sorts of things about itself and its own settings, and the agent will do it. Personally, I find this to be a more effective, elegant, and stable harness than OpenClaw for these kinds of things. Even though the app’s UI could use some polish (I don’t like the reasoning picker, and I wish I could collapse thinking steps by default), it is incredibly fun to tune Minis’ workspace to your liking by talking to a model. You can, in fact, just do things.

A few days ago, I was curious about the state of the temperature and humidity in our apartment. So I asked Minis:

Get me a concise report of the state of the temperature and humidity in my house, present it as a nice table.

A native HomeKit permission prompt and a couple minutes later, Sol in Minis parsed a raw dump of temperature and humidity readings from each sensor, reviewed each room configured in HomeKit, and presented the results. Siri AI, for comparison, presented…something:

I also figured it’d be cool to compare the Photos integration in Open Minis to Siri AI’s photo library access. In theory, they’re both using the same framework, with the same metadata for each photo, but Siri AI also has access to “personal context”, right? So, I asked:

Based on my Photos, would you say I was recently on vacation?

I will let the results speak for themselves:

How about HealthKit? Again, keep in mind that Open Minis isn’t employing any “hacks” or workarounds here; it’s simply accessing the same native Apple APIs and frameworks that all developers can use. I asked:

Find the photo of when I was on vacation recently and took a picture of a large ship. How much did I walk that night?

Minis started thinking about this request in a different way: it checked its memory first, and it realized that we recently discussed my recent vacations, so it could immediately short-circuit the process of finding out about those dates. Then, it started filtering my photos by those dates, found the original photo of the Palinuro vessel, and…yeah:

Inspecting the thinking steps in the request is also a fun exercise in seeing how a frontier model driven by an exceptional iOS harness can reason through a problem like this. The model – using the ‘Minis Computer’ (i.e., the aforementioned Linux shell) – fetched memories as Markdown files from the Files app, called the Apple Photos CLI, assembled a contact sheet with a grid of photos, picked two candidates, selected the best photo, isolated the date, called HealthKit for that date, and only then built an answer. And since all of this is based on deterministic code that was executed on-device, the response was fast and did not contain any hallucinations.

How the agent reasoned through my question and data returned by iOS.

I then decided to go a step further: I asked Minis to take photo highlights from my recent vacations, put them on a map powered by Apple’s MapKit JS, and create a nice, interactive HTML artifact with photos on a map. I used Kimi K3 for this. Minis first asked me to securely store my MapKit developer token, then got to work. It collected photos and parsed metadata returned by the Photos app, and a couple of minutes later, there it was:

The Maps artifact built in HTML by Minis with a combination of Photos and MapKit.

Notice how the HTML artifact itself is presented with WKWebView – another native Apple framework that lets Minis’ agent display webpages with the same WebKit rendering engine used by other web apps on iOS. I also combined web views with Apple NLP, the Natural Language Processing framework that’s available to Minis as another CLI. I asked the app to fetch my most recent iPad article from MacStories, scrape it as Markdown via Firecrawl, tag its different parts of speech with Apple NLP, and present it nicely. Not a problem:

Parts of speech tagged with Apple’s native NLP framework.

Music is also a first-class citizen in Open Minis: by integrating with the Apple Media framework, agents can see what’s in your music library and find information about the albums, songs, and artists you’ve saved. Which means that if I ask Minis…

What Oasis singles and b-sides do I have in my library?

…Minis can inspect my library, cross-reference results with the web, de-duplicate matches, and present results in a way that Siri AI just can’t do right now since its capabilities are limited and the model can’t reason for longer on any specific query:

I can go on. Open Minis can access the native Bluetooth framework, scan nearby Bluetooth LE devices, and find out details about them:

Working with the Bluetooth CLI in Minis.

It can send you real notifications when it’s done with a task, and you can even program those notifications to have a custom title and body text:

The app can also access your current location, extract locations from calendar events, and use the native Apple Weather APIs to give you detailed weather forecasts:

I think you get the idea.

By combining intelligent reasoning models with extensive integration on Apple platforms, Open Minis can deliver an agentic experience with no equal on iOS right now, which also serves as a fascinating preview of Siri AI’s potential future for power users. As a result of all this, while I still enjoy Siri AI as a basic voice assistant more capable than it was before, I’ve completely replaced its text-based chatbot functionalities with Open Minis powered by either GPT-5.6 Sol or Kimi K3.

iOS Agents Are Coming

Minis, Siri AI, and the upcoming Halo agent for iOS.

It is ironic that, on the cusp of Siri AI launching to millions of users in English only in a few months, here we have a single indie developer who is shipping an app that puts Siri AI to shame when it comes to getting work done with LLMs on iPhone and iPad today – with any model you want, in any language or region.

Over the next few months, I expect more developers to ship products comparable to (and perhaps even exceeding) Open Minis, based on the same idea of an on-device agentic harness that combines LLMs with iOS-specific integrations. One worth keeping an eye on is Halo, an upcoming iOS agent from Tanmay Sonawane that aims to combine LLMs, iOS integrations, memory, and proactive features based on Andrew Karpathy’s pioneering work on AutoResearch in an elegant, iPhone-native experience. I’m in the early testing group for Halo, and it’s a very promising product that, unlike Minis, runs in a loop on-device (displayed via Live Activities) to gather insights about your conversations, upcoming tasks and events, and more.

As I wrote months ago, I’m surprised that none of the big AI labs are exploring this space more in depth. As Open Minis proves, now that models have grown incredibly capable at long-running tasks and tool calling, there’s a real case to be made for agents that can tap into the iOS filesystem, apps such as Photos and Calendar, and technologies like Vision OCR, location, and speech-to-text at virtually no cost. Can you imagine what a “real” Codex or ChatGPT Work for iPhone and iPad could be with a similar system to Open Minis’ and the agentic loop and harness that drive OpenAI’s models? What could Anthropic do with a Claude Cowork powered by Fable that could access the Files app, run CLIs, and sync your workspace files across devices?

With Siri AI, Apple is finally shipping a pretty good chatbot with world knowledge and personal context. Open Minis feels like the beginning of a whole new category of agentic apps for iPhone, which power users like myself can start relying on and fitting into their workflows today.

The new Siri AI in iOS 27.

In the month that I’ve been using iOS 27 (launching in public beta today) and the new Siri AI, I’ve come to a few conclusions: Siri AI is a much better Siri and will (probably) be a massive success; the newfound chatbot capabilities of Siri will pose a serious threat to OpenAI and the vast majority of free ChatGPT users they have; and the new Siri is (again, probably) not for me at the moment. At the very least, it can’t be right now given its lack of support for third-party apps and technical issues I’ve encountered during beta testing.

It took me a while to accept the fact that Siri AI can’t be the kind of AI assistant I’d spend hours working with every day. But after testing iOS 27’s new Siri experience every day (and breaking it often in the process), I think that’s okay – and, arguably, what Apple is shooting for at the moment.

The new Siri AI is not designed for people who have grown accustomed to working with frontier models and agents such as Claude Code and Codex. The first version of Siri AI can’t be considered an “agent”, nor can it be compared to products from Anthropic, OpenAI, or Google that are targeting power users living at the bleeding edge of AI. If you go into Siri AI thinking that it’s Apple’s answer to ChatGPT Work or Claude Cowork for long-running tasks or deep research queries, you’re going to be disappointed – like I initially was.

Instead, Siri AI carries all the typical traits of a new Apple product: it’s a user-friendly experience designed for the masses, without any of the complexities that define a power-user tool, for better or worse. This is how Apple rolls: they don’t start from a high power-user ceiling and let products trickle down to consumers; they always start from the consumer level and refine, iterate, and extend until products trickle up to power users. This perspective isn’t meant to excuse the (many) current flaws of Siri AI. (More on them below.) It’s just the necessary lens for understanding how Apple is addressing their AI shortcomings in a way that doesn’t betray the company’s soul and design ethos.

There will be plenty more to say about iOS 27, the improved Shortcuts app, Liquid Glass tweaks, and other system enhancements later this year. After all, I have a review to write. Today’s column is merely an opportunity for me to reason through the obstacles I’ve faced with Siri AI and the way I’ve had to re-learn how to think about Siri.

Siri AI: The Good Stuff

You see, I believe my issue is that I’m too agent-pilled and accustomed to products like Claude Code and Codex at the moment. Desktop agents have fundamentally changed what I do as a creator who writes and talks on podcasts but also releases software products for my team and audience. There is no denying that Apple’s new Foundation models powering Siri are a far cry from Fable and Sol, or that they feel like models from two years ago. The AI frontier from the two big labs (and – we have to be honest with the numbers here – probably SpaceXAI and Meta now, too) is in a completely different league at the moment. I spent my first couple of weeks with Siri AI trying to convince myself that I could replace Codex with Siri AI, and that was the wrong approach. There is a potential future in which Siri AI can become a more proactive and capable agent, but that’s not what Apple is shipping this year.

If you, like me, are a heavy Claude or ChatGPT user but are curious about Siri AI, you need to reset your expectations and understand that Apple is going after something else entirely. For starters, the new Siri AI is a dramatically better Siri for typical Siri stuff. The new Siri understands your commands and nuanced requests better because of the LLMs behind it; it can often perform multiple requests in one go (such as setting multiple timers with one command); the new expressive (and customizable!) voices sound great, and they’re terrific at reading and summarizing notifications. Apple’s first advantage compared to other chatbots is right here: only Siri can integrate with the iPhone and iPad to this extent, so even if the Foundation models aren’t as smart as the competition, Siri can do a lot more for most people on their devices because neither OpenAI nor Anthropic have OSes they can control. Claude and ChatGPT are extremely intelligent inside their own apps; Siri AI is intelligent enough for routine tasks that can span an entire operating system.

The new expressive voices (right) sound great.

The other key advantage of Siri AI is its system-wide persistence. In addition to voice mode, there’s now a full-blown Siri app that behaves like a traditional chatbot app, allowing you to revisit threads and pin specific ones at the top; but most importantly, you can now finally invoke the new hybrid Spotlight/Siri AI search UI from anywhere on iOS by swiping down on the Dynamic Island.

Spotlight and Siri have been unified in the same UI, so you can still quickly launch apps and documents via search in addition to asking questions.

The lack of system-wide access to Spotlight on iOS bothered me for years, ever since I started reviewing iOS on an annual basis. Now, search is only a swipe away no matter the app I’m using, and the search box itself is smart enough to understand whether I’m looking for an app to launch or formulating a longer request for Siri AI.

It’s been challenging for me to “undo” advanced habits I’ve developed with agents like OpenClaw and assistants like Codex; I think MacStories readers who fall on the power-user end of the AI spectrum will probably face the same hurdles with Siri AI. However, I’ve been able to identify a variety of areas where Siri AI was faster, nicer, and more comfortable than ChatGPT or Codex Remote for practical, everyday questions.

I recently spent a few days in Gaeta, and as we were walking to dinner one night, we spotted this huge vessel docked in front of the restaurant. Typically, I would have taken a picture, started a new ChatGPT thread, uploaded the image, and asked a question about it. This time, I simply held down the Camera Control button (which now defaults to Siri AI mode in the Camera app) and captured a photo. A few seconds later, Siri AI told me I was looking at the Palinuro, a three-masted barquentine that serves as a training vessel for the Italian Navy – which was spot-on. An interaction that would have taken 20-30 seconds with ChatGPT was reduced to a five-second affair with Siri AI. Even nicer, I was able to ask follow-up questions from Siri AI’s floating overlay as well as find the chat in the Siri app later, where I continued asking questions about the ship’s history and usual locations.

The ability to go from Siri in the Camera to a longer conversation in the dedicated Siri app is one of my favorite aspects of Siri AI.

Improved on-screen awareness and integration with Apple Maps has been another highlight. On our way to Gaeta, Google Maps had us drive through narrow mountain roads that we really didn’t like, even though they arguably saved us some time. For the return trip, I decided to use Apple Maps, but I noticed that it also recommended the same mountain roads. So without leaving the Maps app, I swiped down to invoke Siri and typed:

I wanna go back home (from Gaeta to Rome) but I don’t like this route. It goes through too many mountains. I wanna do the Autostrada as much as possible. Is there any way to maybe add some time to the trip and go slightly further down south to find another Autostrada entrance?

To which Siri responded:

To avoid the mountainous routes and stay on the Autostrada A1 longer, you can head slightly south from Gaeta toward the Cassino entrance or even further south toward Capua before heading north to Rome. This will add some time to your trip but provides a flatter, more straightforward drive on the highway.

Again, spot-on: the Cassino toll booth proved to be the way to go for a more comfortable trip.

These Maps-related suggestions were perfect.

A couple more things worth noting here:

• Siri AI didn’t mind my mix of Italian and English in the same request. Even though it’s only officially launching with English support, Siri AI is backed by a large language model – and LLMs are inherently good at multiple languages.
• Siri AI assembled a multi-step route for me, which I opened in Maps, and it was perfect.

After some hiccups in the first two developer betas of iOS 27, Siri AI has also become an efficient way to work with the Reminders app, which I started using as my primary task manager several months ago when I began working on my RemCTL CLI for it. In addition to the usual stuff that Siri could already do in Reminders before, such as creating tasks and fetching items due on the current day, Siri AI – thanks to the new and improved App Intents Apple added to Reminders – can now handle more advanced questions. For instance, I can ask Siri to get tasks belonging to two specific sections of a list in Reminders, and it’ll do it. Claude can also integrate with Reminders on iOS, but since its integration is powered by the old and limited EventKit framework, it can’t be as flexible as the exclusive App Intents integration now available for all apps in Siri AI.

Siri AI can finally show me tasks from sections of lists…too bad it also included a task from another section.

I’ll have plenty more examples to share and analyze in my review of iOS and iPadOS 27 later this year. As things stand right now, my thoughts on Siri AI are converging around this idea: with system-wide access, an exclusive app ecosystem, and good enough performance, Siri AI doesn’t need to be a frontier-level model to be useful to millions of people.

Siri AI: The Bad Stuff

All of this, however, is not to say that Siri AI is perfect. Far from it.

This is beta software, of course, and Apple has time to improve the experience. But I’m afraid that some design choices and intrinsic limitations of Siri AI will remain in place for the next year, leaving us with a product that, despite a two-year delay, still feels very early compared to the likes of ChatGPT, Claude, or Gemini, even in their plain “chatbot” modes.

The biggest issue I’ve encountered is the inconsistency of it all. Very often, the new Siri AI still replies with a generic “Uh oh, something went wrong” error that doesn’t explain what the error was or why it happened. Sometimes, I ask a question via voice, and it errors out, but then a few seconds later, I type the same question in the app, and it’s fine.

Anecdotally speaking, these issues seem to occur more frequently when Siri “thinks” longer for a request, which perhaps suggests Apple needs to optimize the performance of their larger model on Private Cloud Compute. However, the fact that Apple wants to keep things simple compared to their competition isn’t doing them any favors here: in ChatGPT or Gemini, I can know when the model is reasoning for longer, but Siri AI’s interface is a black box. There are no reasoning selectors or hints in the UI at all. That is a fine, Apple-y approach when everything works well; but as soon as something breaks (as often happens with chatbots), the lack of clarity and controls stings.

The entire Siri app is, in fact, a bit of a mess. Its performance is subpar: I’ve noticed frequent stutters when scrolling threads, delays when typing (letters wouldn’t appear on-screen and autocorrect wouldn’t work), and broken ‘Sources’ popups displaying no actual sources for a query.

The results of this query were stale (I was on a trip last week), and the Sources panel for linked emails came up empty.

The app lets you rename and pin threads, which is nice, but it doesn’t offer basic controls such as the ability to select text in a Siri response or create folders for chats. Although the grid view looks good in marketing screenshots, in practice, I had to disable it immediately because I couldn’t quickly parse my threads and find what I was looking for.

I really don’t like Siri’s grid layout.

Which brings me to indexing. As I noted above, Apple’s advantage compared to other chatbots will be Siri’s access to an on-device index that draws from the user’s apps and personal context. The problem is that I’ve yet to see an example of personal context “enhancing” any of Siri’s answers, and performing actions in or retrieving data from apps has been half broken for me since the very first beta of iOS 27.

I can’t speak about personal context because it has literally never worked in my examples. For apps, my understanding is that third-party ones will need to be specifically updated for iOS 27 in order to work with Siri AI – although some of them seem to work already, but others don’t? Apple requires developers to implement new features of the App Intents framework for Siri AI, and I’m optimistic that those who do will have their apps appear in Siri AI by September. Greg Pierce, the developer of Drafts, has added early support for Siri AI in his app, and I’ve been able to successfully create a note within the app from Siri, which presented a custom UI snippet for Drafts and completed the request in seconds. That was neat.

My problem is that, right now with Apple’s own apps, both the index and Siri’s ability to perform actions are very inconsistent. The assistant hallucinates abilities it doesn’t have, and it frequently just doesn’t work. In the examples below, I wanted to get notes from a specific folder, songs from a playlist, and a link from a note. Siri AI responded with an empty list of notes, said it couldn’t get songs from a playlist, and told me that my note didn’t have any links, respectively. (It did.)

Reminders integration started working for me in iOS 27 beta 3, but it still isn’t perfect. When I ask for tasks due today, Siri AI insists on presenting the same tasks twice, my only fault being that I enabled the integration between Reminders and Calendar:

At one point, I asked Siri to show me my overdue reminders. Siri AI struggled with that: it cut the list of overdue items short, apologized when I pushed back, then did it again anyways. I know that Siri AI is not based on a Gemini model but is rather a Gemini distillation, but I think that if you’ve ever used a Gemini model before, this kind of behavior with tool-calling should be awfully familiar.

Siri AI isn’t a replacement for agentic workflows with other LLMs that can perform multiple actions in one chain of events. Here, for instance, I asked Siri to get my latest screenshot from the Photos app and frame it with my Apple Frames shortcut. Not only did Siri AI not get the most recent screenshot from my library, but the assistant couldn’t perform two actions sequentially. At least, however, it told me; when I repeated a similar question but asked to copy the screenshot to the clipboard instead, Siri first asked me to confirm my action and then changed its mind and said it couldn’t do it.

Why ask for clipboard confirmation if you can’t do it?

Searching for content hasn’t been ideal on my end, either. When I asked Siri to find me the latest single by Phoebe Bridgers, its default text response was an EP from two years ago; when I asked via voice, the response was correct. (…Why?) I similarly haven’t been impressed with Siri’s ability to search for messages and emails. Siri AI can reliably find recent texts from the Messages app, but the moment I start going a little further back in time, the system seems to struggle. I wanted to know when we took some time off at MacStories last summer, which I know was mentioned in a MacStories Weekly email that I have in the Mail app. Siri AI could only find a generic mention of John recharging after some time off, but it couldn’t give me an exact date because it did not find the correct email. ChatGPT Work did it in one minute and gave me a full breakdown of the weeks we took off.

Left: ChatGPT Work. Right: Siri AI.

All of this begs the question:

Is Apple’s on-device index a solid technological foundation or not? Is this system actually going to work at scale, for users with dozens of apps installed, each donating their data to the index, perhaps spanning multiple years of content? And can the cloud models – which are not using MCP but appear to be based on a plain JSON schema for structured data – make sense of it all?

My early tests haven’t been encouraging, but we have until September to find out.

The Trickle-Up

A trickle-up strategy cuts both ways: it gives Apple an opportunity to start simple and refine over time, but it also means that you, the user, are never given any more control than what the product allows for. As a result, Siri AI can be magical when it works; when it doesn’t, it feels like a mystery.

I can’t say whether I’m optimistic that Apple will get all of this to work in time for the fall or not because they don’t have the greatest track record in AI. I’m willing to give them the benefit of the doubt since the product itself is genuinely interesting and different from any other chatbot on the market. I want Siri AI to work, and if Apple can deliver on their vision, I’m convinced that it’ll spell trouble for OpenAI and ChatGPT. (Let’s face it: it’s the product to beat here, both in and outside of court.)

Siri AI permeates iOS 27, and that’s a threat to OpenAI and the hundreds of millions of users they have using ChatGPT for free with GPT-5.5 Instant. I don’t think Apple Foundation Models are as good as GPT-5.5 Instant, but Siri AI is the more ergonomic and integrated product. When the underlying chatbot and its world knowledge capabilities are good enough, and they can also be invoked via voice, text, the Camera app, context menus, or keyboard shortcuts, why would I open a siloed chatbot when I can use Siri AI and get a comparable answer more comfortably? If you’re a casual user of ChatGPT and do not pay for it, I think Siri AI can be a very compelling product that provides similar answers and, unlike OpenAI’s chatbot, integrates with the iPhone apps you already use. I don’t think it’s a coincidence that OpenAI is now following in Anthropic’s footsteps to monetize the business and enterprise markets rather than the consumer one.

At the same time, my concern is that we may be collectively assuming that “normal people” won’t see the differences between the capabilities of ChatGPT and Siri AI. In this industry, we have a tendency to sell “normal people” short and paint them as some perplexed bunch of occasional smartphone users who somehow passively accept any technology that is thrown at them. I strongly disagree with that. Maybe those people don’t care about ChatGPT Work, Codex, or Fable (yet?), but they can tell when an AI assistant is useful and when it’s not. People will compare the utility of ChatGPT to Siri AI, and I’m concerned that Apple’s 1.0 product will feel like it’s too little, too late – especially since Siri AI will be launching in select regions and in English only.

In the AI scene, companies move fast and break things. Apple needs to move fast without breaking anything, anymore. That’s a tough challenge, but here we are.

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.

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.

My Codex setup.

In the current era of coding agents becoming productivity assistants, iPadOS’ limitations are no longer defined by the lack of desktop-class multitasking or access to external peripherals. A new class of iPadOS shortcomings looms large on the horizon: the iPad’s app sandboxing and the absence of an open filesystem have relegated it to acting as a remote control for agents.

I’ve been ruminating on this thought for some time. I, of course, am very satisfied with the improvements Apple brought to the iPadOS platform throughout the 26 cycle: between new windowing, local capture, a menu bar, and the improved Files app, I can get most of my old-school work done on the iPad Pro without begrudging the experience like I used to a few years ago. What I’ve noticed this year, however, is that iPadOS 26 was an update designed to address the pre-existing low-hanging fruit of quasi-desktop efficiency; by design – and we have Craig Federighi on the record saying as much – it wasn’t intended to reinvent the wheel in any meaningful way.

That would have been fine a few years ago. The problem is that the productivity wheel is literally being reinvented by other companies as we speak. And in an unsurprising turn of events, the Mac is at the forefront of that reinvention, while the iPad is being left behind once again.

I’m writing this as someone who likes to be on the bleeding edge of AI tools. Since the release of Claude Code in early 2025, I (and, realistically, millions of other nerds whose taste aligns with mine) have increasingly moved a lot of my research, automation, coding, and other tasks considered “productivity” to desktop agents. These are powered by the same underlying technology as chatbots, but they’re considerably more powerful: Claude Code and Cowork, Codex, Perplexity’s Personal Computer, and self-hosted agents like OpenClaw and Hermes can understand intent and perform long-running tasks on your computer. They can write code, stay on a task for hours (or even days) at a time, analyze the contents of your screen, and even use a computer on their own. To believe that these AI tools are still a fad and chatbots are useless is misinformation at this point.

As of June 2026, I spend most of my days with two apps constantly open on my M4 Pro MacBook Pro: Codex and Notion. I’m a huge fan of what OpenAI has accomplished with Codex for Mac; their all-in-one package that combines thread-based chats with skills, plugins, connectors, computer use, memories, and system-wide filesystem access has genuinely allowed me to produce content for my audience that I wouldn’t have even dreamed of years ago. Since I started working with Codex, I’ve released a major update to Apple Frames, two CLIs (with two more coming soon), Shortcuts Playground, and a brand new MacStories Shortcuts Archive. These are actual products that are used by thousands of people and are generating real revenue for MacStories. I’ve also created an entire suite of MacStories-only internal apps (now used by our whole team) and am currently in the process of researching my iOS 27 review, creating an app for Shortcuts Playground, and brainstorming a different product altogether for MCP.

I’m doing all of this on a Mac because the true Codex experience isn’t even “desktop-only”: it’s Mac-only.

Let me give you some examples. To make the original version of Shortcuts Playground, I had Codex with Computer Use scrape my entire library on the old MacStories Shortcuts Archive, download over 300 shortcuts, and learn my coding style. Once I had a plugin, I also had Codex create over 1,000 shortcuts on its own, install them in the Shortcuts app for Mac, and debug them visually to find issues. For the new Shortcuts Playground plugin and app, I’m going even further: Codex created over 3,500 shortcuts spanning the entire library of Shortcuts actions while simultaneously coordinating with other Codex threads – some of which are running on my Mac Studio – to build an app, train a local model for Core AI, and constantly iterate on the new harness behind the app. Meanwhile, I’m also spending time in Codex organizing sources for my iOS 27 review, managing my tasks with Reminders and my own RemCTL, and performing general research on any topic I think of. The net result of all this is that I’m shipping more things, making more money for MacStories, saving money thanks to our new internal tools, and – most importantly – learning a lot and having fun.

Working with Codex for Mac.

Some of the CLIs I’ve built. Two of them are coming soon.

In all of this, the iPad’s role is to be, once again, an accessory to the Mac – and a rather expensive one at that. I wrote last year about iPadOS’ third-party app problem, and I still think all of it applies today. What’s different in 2026 is that these powerful agentic tools that are redefining coding and knowledge work, and which are centralizing productivity inside so-called “super apps”, aren’t coming to the iPad, but not for political or financial reasons: they’re Mac-only because only macOS is mature and open enough to support them.

In a funny twist of fate, Apple spent years trying to make iPadOS catch up to macOS on the surface, only for macOS’ underlying nature to unlock a new generation of apps that are rewriting the rules of modern software. No amount of windowing and menu bars can change the fact that neither Claude Cowork nor Codex will ever be possible on the current version of iPadOS. From an open filesystem that lets agents poke around anywhere to powerful Accessibility and Screen Recording APIs for developers to features like system-wide hotkeys, dictation, and true background processes, Apple’s oldest operating system is the one that feels the freshest (and the most powerful) in the AI industry today.

In fact, the Mac is so powerful and well-equipped for this new wave of desktop agents, it even yields an amazing experience when used in a “headless” setup with no display attached to it. This may have started as a trend because of OpenClaw, but six months later, I believe that a Mac mini with Codex running on it is the best bang for your buck if you’re building an always-on agentic setup based on a frontier model that can do just about anything you throw at it.

Which brings me to the iPad’s only silver lining in this space right now.

Most of my Codex tasks are running on my Mac Studio server, but I also use Codex on my MacBook Pro. Thanks to Codex’s support for remote connections, I can chat with threads running on the Mac Studio from the Codex app on a different machine, which is a fantastic feature. Alternatively, I can use Apple’s excellent (and, again, Mac-only) Screen Sharing app to log into my headless Mac and interact with macOS with superior performance and image quality to VNC. (I also use this HDMI 2.1 dummy plug to unlock 4K resolution when headless.) Coordinating Codex threads across different projects and machines feels like the sort of thing that shouldn’t be possible, yet here we are.

If the iPad is still relevant to me in this specific new way of working, it’s entirely because of the ChatGPT app and the fact that OpenAI cared enough to design a good remote experience for iPhone and iPad users. The Codex section inside ChatGPT is a solid product and getting better every week; it’s also the only app of this kind that lets you connect to multiple computers at once and manage threads across all of them. With Codex remote on iPad, I can continue my projects from the MacBook Pro or Mac Studio, pin specific threads, and keep an eye on all my agents working in the background. In general, it’s also a way to bridge functionalities that are missing from iPadOS. Without Codex remote, I wouldn’t be able to ask my agent to reschedule my reminders and turn some emails into tasks in the same workflow; I wouldn’t be able to tell my agent to go to the Apple Newsroom, find me a specific press release, extract all images from it, and upload them to our CDN.

Codex remote on iPad.

Perhaps Siri AI will unlock similar capabilities (although I doubt to the degree of a frontier desktop agent), but it’ll still be limited to apps made by companies that decide to support App Intents. When I’m not using my Mac and I think of something I can’t do on the iPad these days, I instantly reach for Codex inside ChatGPT. I suspect this trend will only grow as more AI companies release similar remote experiences for iOS and iPadOS.

Here’s the issue, though: these are remote companion experiences. It’s great that they exist and that OpenAI cared enough to make them great, but they’re still no substitutes for the real Codex experience on a Mac. It’s ironic if you think about it, isn’t it? A headless Mac is still more flexible and powerful than an iPad hamstrung by the closed nature of its own OS and software gatekeeping.

My headless Mac Studio in Mirage for iPad.

Mirage for iPad’s app launcher.

If you’re among the five million people using Codex on a weekly basis and will be planning your next laptop purchase in a few months, perhaps these considerations will change the calculus for you. Especially in the face of price increases and RAM uncertainty, would you be better served by spending $1,499 on a hybrid laptop that gets work done the old way with 256 GB of storage, or $1,499 on a computer where AI is a first-class citizen with 24 GB of RAM and double the storage? If we accept that power users’ priorities and workflows will be dramatically changing in the near future (if they haven’t already!), all prices being equal, which OS is best positioned for the future?

Of course, I like using both an iPad Pro and a Mac for different tasks. But let’s face it; in this day and age – and especially after last week – not everybody has the budget for two computers that have some overlap between them. Sure, I could argue that an iPad Pro + a headless Mac mini is an insane combo to get the best of both worlds these days: the nimble and delightful nature of iPadOS and the freedom to experiment with AI on a Mac. You can install apps like the latest Jump Desktop beta or the great new screen sharing app Mirage on the iPad and use your Mac mini almost as if it were connected to the iPad’s display. Set up Tailscale on your network, and the Mac’s power can be with you at all times. But that’s a lot of money, and a lot of setup, to achieve an approximation of what a single MacBook Air can handle with more memory, more storage, and a couple of Mac apps.

I’m sure that Apple is aware of the changing nature of this landscape, but in a similar vein to chatbots and Siri, perhaps they were unprepared for the tide of agents to accelerate so quickly. If the idea of putting macOS on an iPad Pro continues to be a non-starter at Apple, and assuming agent-based coding and knowledge work are here to stay, what should the company do to make sure the iPad doesn’t get left behind again? Is a sandboxed Terminal for iPad backed by a dedicated “Agent Framework” the solution? Is working with other companies to build more “remote companion” apps the way forward?

Or, perhaps more obviously: how long until Siri AI can also become a capable agent, connected to App Intents, on par with competing frontier agents?

Until, and if, that happens, the iPad will once again play the role of sidekick to macOS.

When it comes to the bleeding edge of AI and pushing the frontier of agents forward, there’s nothing like the Mac.

MultiSwitcher for iPadOS.

Update: An earlier version of this article referred to this feature as having been introduced in iPadOS 27, but it was actually introduced in the iPadOS 26 cycle. I missed it. My apologies.

In iPadOS’ Shortcuts app, the existing ‘Open App’ action was recently updated with the ability to launch an app with a specific window placement parameter. This means you can now automate window positions on iPad by opening a bunch of apps and programmatically selecting where their windows be placed.

To find this feature, use the ‘Open App’ action in Shortcuts and expand it to reveal the new ‘Window Location & Size’ field. Here, you can click the default ‘Full Screen’ value to reveal a host of options:

• Full Screen
• Left
• Right
• Top Bottom
• Top Leading
• Top Trailing
• Bottom Leading
• Bottom Trailing
• Left Third
• Middle Third
• Right Third

You can play around with these options to open any app and resize any window by choosing from the same presets that are otherwise shown by iPadOS when right-clicking the traffic light controls:

Some of the options supported by the ‘Open App’ action.

That was a neat discovery, but as I was playing around with the action, I realized that its practical utility would be impacted by the fact that you have to manually pre-select the app you want to open as well as its window layout. Wouldn’t it be better if you could turn this Shortcuts action into a reusable technique to programmatically get whichever app is in the foreground with no manual selection upfront, then also give it a pre-selected window preset? As it turns out, you absolutely can.

This is why I created MultiSwitcher, a simple proof-of-concept shortcut for iPadOS users that lets you resize any foreground window to a preset of your choice – no manual input necessary. The idea is fairly straightforward: you can use the ‘Get Current App’ action to get the name of the foreground app, pass it to the ‘Open App’ action, and also pre-configure that action to accept a layout variable.

This new parameter of the ‘Open App’ action supports configurable options.

MultiSwitcher is best used as a shortcut added to your iPad’s dock, so you can click it at any time and instantly resize the foreground window. For MultiSwitcher, I designed a visual menu (with some ASCII characters) that lets you preview window layouts, pick one, and resize the currently frontmost window. It doesn’t have to be this way, though: if you’d rather add multiple variations of MultiSwitcher to your dock, each with a specific window size already selected, you can also do that and skip the menu. The choice is up to you.

While these newfound window-control capabilities for iPadOS are still a far cry from the Mac’s breadth of window managers and multitasking tweaks, I find this implementation in Shortcuts to be quite elegant and intuitive for most users to grasp with no need for a third-party app.

You can download MultiSwitcher for iPadOS below.

MultiSwitcher

Control iPadOS window placement by selecting from a list of preset window sizes. The shortcut will resize the currently frontmost window.

Get the shortcut here.