When Fable 5 returned last week, I knew exactly what to throw at it. In February, I started a project out of frustration that likewise ended in frustration, so I put it on the shelf and waited. Five months later, Fable 5 was released, and I knew it was time to finish Editor, a single-view diffing tool for writers rather than developers.
Posts tagged with "AI"
Finishing with Fable 5
Safari’s New MCP Server Is Great for Agents→
Saron Yitbarek, writing on the WebKit blog:
In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more powerful. We know agents are increasingly integral to the coding process and the Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window.
Any MCP-compatible client can connect to the Safari MCP server. By connecting your agent to a Safari browser window, your agent can emulate what your users experience, giving it the information it needs to debug more autonomously, like access to the DOM, network requests, screenshots, and console output.
Importantly:
The Safari MCP server runs entirely on your local machine and makes no network calls of its own. It also does not have access to your personal information in Safari (e.g. AutoFill or other browser activity). When it captures page content, screenshots, or console logs, that data goes directly to the agent you’re running — not to Apple. What happens to that data from there depends on the agent and model you’re using. As with any agent you give access to your browser, only use ones you trust.
For the past few months, I’ve been using Google Chrome on my MacBook Pro and Mac Studio not because I like the browser (in fact, I really dislike Chrome’s text rendering and UI), but simply because it was the best option for agents. In Codex specifically, between Playwright, Chrome Dev Tools, and OpenAI’s own Chrome extension, I could kick off research tasks (such as vacation planning and booking a hotel) that involved a browser directly from my iPhone, letting Codex drive the research on my remote Mac.
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.
Headless Macs and Hamstrung iPads
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.
Three Features Coming to Photos This Fall via Apple Intelligence→
Photo editing is getting some of the most interesting Apple Intelligence features this fall. At WWDC, Tyler Stalman interviewed Jon McCormack, Apple’s Vice President of Camera and Photos Software Engineering, and Della Huff, the company’s Senior Manager of Camera and Photos Product Marketing, in a video that covers Spatial Reframing, Extend, and an improved Clean Up tool, along with demos of each:
The interview goes into depth on each feature and how they’re enhanced by the integration with Apple’s improved Private Cloud Compute models, sharing nuggets like the fact that Spatial Reframing of photos is possible even if an image is taken with a single-lens iPhone and the fact that Apple includes metadata in generatively edited photos identifying the use of AI and will add SynthID watermarking, a technology developed by Google, to AI-edited photos later this year.
I’m not a fan of wholesale image generation, which is why I appreciate the thoughtful approach Apple is taking with these photo editing features. The changes are at the margins of the photo and identified as edited using AI.
The Third Generation of Apple’s Foundation Models and AFM Core Advanced→
I just came back to my hotel room after a long day at Apple Park (I documented most of it in my Instagram stories, including a very cool shot), and, like everyone else here in Cupertino, I’m still processing the information overload from the past 12 hours. The MacStories team already covered iOS and iPadOS 27, plus Siri AI and Apple Intelligence, and we have more coming tomorrow.
Before I call it a day though, I wanted to link the first thing I read on my way back: Apple’s latest article on the Machine Learning blog about the new Apple Foundation Models that were announced today – three cloud-based models, and two on-device ones.
Siri AI and the Latest in Apple Intelligence: The MacStories Overview
The big question coming into today’s WWDC keynote was what Apple would have to offer in terms of AI – or, as the company refers to it, Apple Intelligence. Given Apple’s behind-the-scenes struggles, delayed features, and partnership with Google to re-architect its Foundation Models based on Gemini, expectations were high, and the company delivered with the announcement of a whole new Siri and a slew of Apple Intelligence features baked into its upcoming operating systems.
Siri AI, the all-new version of Apple’s virtual assistant, was the star of the show and got plenty of time in the spotlight, including several real-time demos on the iPhone and Mac. But the company also announced updates to Visual Intelligence, new photo editing tools, a Shortcuts builder, and additional Apple Intelligence features.
It all starts with the latest Foundation Models based on a new architecture developed by Apple in collaboration with Google’s Gemini models. Coming in both local and Private Cloud Compute variations, these models work across Apple devices using a combination of user input (via text, voice, or images), personal context, on-screen awareness, app actions, and world knowledge in conjunction with the new system orchestrator to power conversations and actions taken by Siri AI as well as Apple Intelligence features baked into each OS. Of course, Apple touts that these features are secure and protect user privacy whether they are run on-device or in Private Cloud Compute.
Apple Frames CLI, Now with Support for Framing Screen Recordings
I’m on my way to California for WWDC, and with the conference kicking off tomorrow, I thought I’d take advantage of my 12 hours on this airplane by sharing the latest addition to the Apple Frames CLI: support for video framing.
RemCTL 1.0.5, Now with Support for All-Day Reminders and Task Assignments→
I wanted to share a quick update to RemCTL, my CLI for Reminders that I released last week, which brings almost every Reminders feature to your agent or terminal of choice.
As it turns out, I forgot to support two more Reminders-exclusive (i.e. not available to third-party clients) functionalities in the initial version: all-day reminders and the ability to assign a reminder to another person in a shared list. The former is the feature that lets you enter a task with a due date such as “Tuesday” but without a due time;. those tasks can now be properly read and written by RemCTL.
Additionally, while RemCTL cannot share lists with iCloud (it requires a private Apple entitlement – same reason why the CLI cannot share a template via iCloud), it can now read and create task assignments from an already-shared Reminders list. In a nice touch, you can even lookup assignees by name, email address, or phone number.
You can find a detailed changelog of the latest release here. As always, the best way to update the CLI is to simply ask your agent to pull the latest version and update its installed skill to match the most recent version from the repo.
Introducing RemCTL: The Power-User Reminders CLI for macOS and AI Agents
Today, I’m pleased to release my latest free and open source project: RemCTL, a power-user Reminders CLI that, unlike others, exposes all the latest Reminders features as of iOS and macOS 26. RemCTL supports reading and writing subtasks, tags, sections, rich links, image attachments, grocery lists, and even templates.
It’s available on GitHub here, and it comes bundled with a skill for desktop agents.