OpenAI’s Dots: A First Look

Source: OpenAI.

Source: OpenAI.

Earlier this week, I was at OpenAI’s annual DevDay conference where it launched Dots, a personal agent that lives inside the ChatGPT app. I set up my Dot and named it Puck after the mischievous sprite in Shakespeare’s A Midsummer Night’s Dream. In the days since then, I’ve found myself using Puck more and more. There are still rough edges, but I thought I’d share what’s working and what’s not, and how Dots are different from what’s already available in ChatGPT and Codex.

Dots are persistent, cloud-based agents that use the plugins and other tools you’ve connected to ChatGPT, after you allow them to do so. Your Dot has its own virtual Linux computer to assist you with your work. And at first, your Dot, which is depicted by a colorful character you can customize, doesn’t have access to anything else. However, as you give your Dot tasks that need access to other tools, it will ask for your permission to access other tools. The pacing of this initial interaction with your Dot is really well done. The requests felt natural and allowed me to get comfortable with expanding what I let Puck do without feeling like annoying interruptions.

Customizing my Dot.

Customizing my Dot.

Dots are available on mobile and desktop devices, and because they are cloud-based, your Dot’s chat is always synced between devices. But being a cloud-based agent has its downsides, too. Out of the box, your Dot can’t access your computer’s files and apps. That’s easily fixed by clicking or tapping on your Dot and granting it access to your Mac, so it can use the Mac alongside its own VM. As with Codex’s Remote feature, using a remote Mac with your Dot requires the ChatGPT app to be open on that Mac, too.

Read more



How I Used Notion, Agents, and Local AI to Research and Organize My iOS 27 Review

My Notion setup (left) and Desk, my custom system for the iOS and iPadOS review.

My Notion setup (left) and Desk, my custom system for the iOS and iPadOS review.

The process for this year’s iOS and iPadOS review was, on the surface, similar to last year’s: I researched, wrote, and edited the entire story in Notion, then used a custom tool to export it to Markdown for MacStories. Structurally, it was also a mirror of last year’s setup: I had separate databases for notes...

Read more


Frames CLI 1.5.0, Now with iPhone 18 Pro and (Experimental) iPhone Duo Support

The updated Frames CLI also supports proportional scaling for iPhone Duo.

The updated Frames CLI also supports proportional scaling for iPhone Duo.

The Frames CLI – the companion command line interface to my Apple Frames shortcut I released earlier this year – received a 1.5.0 update earlier today with two notable additions: iPhone 18 Pro frames, and experimental support for iPhone Duo screenshots in all poses.

As always, my shortcut and CLI are based on Apple’s official product bezels, which is why, as of today, there is no support for Apple Watch Series 12 and Ultra 4 yet (those frames haven’t been published by Apple). iPhone 18 Pro is the new default frame family for the two Pro and Pro Max screen sizes, and the CLI supports all the new device colors this year (Burgundy, Glacier, Silver, and Black).

iPhone 18 Pro in Burgundy.

iPhone 18 Pro in Burgundy.

iPhone Duo support is experimental. I obviously don’t have an iPhone Duo yet, but thanks to Opus 5.5, I was able to grab screenshots from the Xcode 27.1 Device Hub, verify them against Apple’s official assets, and test everything in the Frames CLI. It should work! The CLI – and, thanks to its skill, your agent of choice – supports framing screenshots taken on the inner and outer display, different poses, different rotation settings, as well as screen recordings.

If you’re a developer working on iPhone Duo apps, I think the updated Frames CLI should come in handy to automate the process of framing multiple screenshots and screen recordings. As before, you can take advantage of CLI features such as proportional scaling, merge mode, and batch mode, which should help you with your upcoming App Store submissions for the iPhone Duo.

The Frames CLI is free and open source, works with any agent, and is highly customizable. I’ll release an updated version of the Apple Frames shortcut once I can get my hands on an actual iPhone Duo next month (hopefully). Fingers crossed.



Our Favorite Indie Apps for iOS 27, Vol. 2

It’s time to get back to our favorite indie apps that take advantage of Apple’s latest OS features. Today, we’re highlighting: Bear, Gentler Streak, The Outsiders, DoMarks, and Cheatsheet Notes.

Bear

Bear, the note-taking app for iPhone, iPad, Mac, and Apple Watch, just released version 2.10 with several Siri AI features, including actions to:

  • Create a new note
  • Append text to an existing note
  • Append files to a note
  • Pin notes

The app also includes onscreen awareness so Siri knows the content of the note you’re looking at without you telling it.

Bear’s new actions make it a compelling way to dictate notes on the go. Simply invoke Siri and start talking. With the ability to start a new note or append to existing notes, you can get quite a lot done with only your voice. One of my favorite uses is annotating screenshots. I take a screenshot, invoke Siri, and in one go, I can ask it to add a new note with my last photo (the screenshot), give it a title, and add a quick note about it. It’s far easier than walking through those steps manually.

Gentler Streak

Gentler Streak

Gentler Streak

Our iPhones and the Apple Watch can collect and process a lot of health and fitness data for us. My favorite way of making sense of it all is Gentler Streak, which works on the iPhone, iPad, and Apple Watch, making sense of all that data.

One of Gentler Streak’s greatest strengths is its delightful illustrations and clear, meaningful presentation of fitness data. I love browsing my workouts and other fitness data in Gentler Streak, but with the latest release, I’ve come to appreciate the snippets it offers thanks to App Intents, too.

The update lets you access bite-sized snippets of data without opening Gentler Streak, accessing data like today’s workout, your activity status, and suggested activities all from Spotlight or Siri. It’s handy when you’re in a hurry and just want a quick update on something like how well you slept last night. The app also supports onscreen awareness, allowing Siri to explain features of Gentler Streak to you or interpret onscreen data.

The Outsiders

The Outsiders

The Outsiders

The Outsiders, from the same team as Gentler Streak, is a great complement to it, trading Gentler Streak’s relaxed approach to workouts for a more intense, performance-driven perspective. I’m a big fan of the iPhone app’s colorful design, which, like Gentler Streak, lets you access data like your training readiness, latest workout, body metrics, and sleep data simply by asking for the data “in The Outsiders.” Onscreen awareness allows Siri to explain metrics to you, too.

If you choose to edit a workout’s title, Apple Intelligence kicks in with a suggestion changing something generic like “Evening Workout” into “Evening Commute Through Davidson College,” which sounds much nicer and adds a little hint about where you were and what you did for that workout.

Cheatsheet Notes

I love how Cheatsheet Notes has evolved over the years from a very basic scratchpad to a beautifully designed and focused note-taking app that adopts all of Apple’s latest technologies. The recent update, which is available for the iPhone, iPad, Apple Watch, and Mac (sold separately) is no exception, incorporating all sorts of Siri AI features, as well as new widgets.

Thanks to Siri AI’s onscreen awareness, you can ask Siri questions about information visible in your notes. You can also append text and images to notes with Siri’s help. The append functionality is especially useful because Cheatsheet is intended for quick notes about things you want to remember, like a parking spot at the airport. Take a quick photo of your parking spot, ask Siri to add it to your Airport Parking note and that’s it.

Cheatsheet has also added extra-large widgets that can display a list of notes, a set of notes tied to action buttons, a shuffling of notes from any folder, or a single note. Of course, the app also supports an extensive list of Shortcuts actions, too.

If you’re looking for a great place to store the sort of information you might otherwise scribble on scraps of paper, check out Cheatsheet Notes. It’s an excellent app and scraps of paper is no way to live.

DoMarks

With the release of Apple’s OS updates, DoMarks reached version 4.0. The app is based on the simple idea that people save links to do something with them later. DoMarks makes that easy by helping you assign an action category to each URL you save whether it’s to buy, read, watch, or do something else with the URL. The app fills a role that’s similar to a read-later app and can be used for reading, but the beauty of it is that what you do with the links you save for later is only limited by your own imagination.

With DoMarks’ Siri AI integration, you can save a webpage from Safari simply by asking Siri to save it to DoMarks. You can also ask Siri to open a link by its name or delete it. DoMarks supports onscreen awareness, allowing you to ask questions about a bookmark, too.

Other actions available via Siri, include keyword searches and opening a bookmark. However my favorite action is “Surprise Me in DoMarks,” which will open one of your saved bookmarks at random in Safari. It’s a great way to rediscover interesting spots on the web that I came across long ago, but didn’t have the time to look at. The app has also added a long list of Shortcuts actions that makes powerful automations possible too.

I’m a link hoarder (shocking, I know), and I’ve always found it hard to know what to do with links for things I want to check out later that aren’t reading material. DoMarks is the perfect way to handle those sorts of links, and now, it’s easier than ever to build your collection of bookmarks with Siri’s help.


Apple Music Hall Opens in Battersea Power Station

Source: Apple.

Source: Apple.

Today, Apple announced the opening of Apple Music Hall, a state-of-the-art live venue in London’s Battersea Power Station. The intimate concert space will offer a unique experience for both artists and fans alike. According to Apple’s press release:

The 600-capacity venue is designed intentionally to close the gap between intimacy and production value and allow for an unprecedented level of creative control. Every seat feels close to the performer, yet the infrastructure offers what an artist requires for an arena tour, with a 38-foot-wide stage that can be reconfigured for traditional front-facing sets or more in-the-round experiences. Additionally, the venue is equipped with a 48-speaker spatial sound system positioned all around the audience. When an artist performs in spatial, it will enable fans to hear that performance in an immersive environment.

In addition, Apple Music Hall will support both traditional video broadcast cameras and iPhone video capture of events.

Source: Apple.

Source: Apple.

The new venue looks amazing. I’d love to see a show there myself someday. Fortunately, Apple will also be livestreaming performances from the hall worldwide, so whether you can get into a Battersea show or not, you’ll have a chance to enjoy the performances. I’d love to see Apple Music Hall become a modern version of MTV Unplugged.


M5 Ultra Mac Studio Review: The Dream Mac for Local AI Agents

The M5 Ultra Mac Studio.

The M5 Ultra Mac Studio.

For the past few days, I’ve been testing the (currently) top-of-the-line M5 Ultra Mac Studio with 256 GB of RAM.

I’ll cut to the chase: the M5 Ultra Mac Studio is a dream machine for local AI agents. This computer makes it possible to run personal assistants powered by local models with great performance and no additional cloud costs. If you’ve been skeptical of testing OpenClaw or Hermes Agent with local models because they’d never be even remotely near the intelligence and speed of cloud ones, this Mac will change your mind about that.

Since last Thursday, I’ve been comparing this Mac Studio to its predecessor, the M3 Ultra with 512 GB of RAM, as well as my own desktop gaming PC with an RTX 5090 inside. For its size, price, thermal performance – not to mention Apple’s approach to unified memory – the M5 Ultra Mac Studio has fundamentally changed how I think about models running locally and what they can enable now. A 5090, of course, still has an edge over the M5 Ultra thanks to its higher memory bandwidth. But considering the sheer size of my PC build, as well as its heat and noise, I would prefer an M5 Ultra Mac Studio any day. It also happens to be a Mac, with an operating system that looks nice and doesn’t suck, plus a vibrant app ecosystem. (Windows fans, I’m sorry, but Microsoft software will never get my sympathy.)

As I’ll explore in this article, running the latest Qwen3.8-Flash-Next model on the M5 Ultra Mac Studio has been so nice and fast, I’ve made it my default in both Open Minis for iOS and Hermes Agent. That’s right: the personal assistants I use the most – more than Siri AI, in fact – are now entirely powered by a model running locally on a Mac Studio. Furthermore, thanks to the M5 Ultra’s faster GPU and higher memory bandwidth, these agents start responding more quickly, stay fast at larger context windows, and can run long, multi-turn loops without slowing to a crawl as the session grows. Because of this, I’ve also been using local models in the Codex app on my Mac – either as main threads or subagents orchestrated by GPT-6 Astra – and I’ve had a great experience doing so.

Local subagents running in Codex on the M5 Ultra Mac Studio.

Local subagents running in Codex on the M5 Ultra Mac Studio.

I should note upfront that I’m not an AI developer by trade: I do not train or fine-tune models. I’m a tinkerer at heart, and I’ve been playing around with local AI models for over a year at this point. This summer, I went all-in on local AI usage for a big project I was working on, which I will explain in the following section.

My goal with this article is to provide you with a mix of two things: numbers and visualizations based on the (many) tests I’ve run over the course of four days, and an explanation of my practical use cases for local AI applied to my workflow and how I get things done for MacStories.

Let’s dive in.

Read more