This Week's Sponsor:

Textastic

The Powerful Code Editor for iPad and iPhone — Now Free to Try

Search results for "866"

Using Simon Willison’s LLM CLI to Process YouTube Transcripts in Shortcuts with Claude and Gemini

Video Processor.

Video Processor.

I’ve been experimenting with different automations and command line utilities to handle audio and video transcripts lately. In particular, I’ve been working with Simon Willison’s LLM command line utility as a way to interact with cloud-based large language models (primarily Claude and Gemini) directly from the macOS terminal.

For those unfamiliar, Willison’s LLM CLI tool is a command line utility that lets you communicate with services like ChatGPT, Gemini, and Claude using shell commands and dedicated plugins. The llm command is extremely flexible when it comes to input and output; it supports multiple modalities like audio and video attachments for certain models, and it offers custom schemas to return structured output from an API. Even for someone like me – not exactly a Terminal power user – the different llm commands and options are easy to understand and tweak.

Today, I want to share a shortcut I created on my Mac that takes long transcripts of YouTube videos and:

  1. reformats them for clarity with proper paragraphs and punctuation, without altering the original text,
  2. extracts key points and highlights from the transcript, and
  3. organizes highlights by theme or idea.

I created this shortcut because I wanted a better system for linking to YouTube videos, along with interesting passages from them, on MacStories. Initially, I thought I could use an app I recently mentioned on AppStories and Connected to handle this sort of task: AI Actions by Sindre Sorhus. However, when I started experimenting with long transcripts (such as this one with 8,000 words from Theo about Electron), I immediately ran into limitations with native Shortcuts actions. Those actions were running out of memory and randomly stopping the shortcut.

I figured that invoking a shell script using macOS’ built-in ‘Run Shell Script’ action would be more reliable. Typically, Apple’s built-in system actions (especially on macOS) aren’t bound to the same memory constraints as third-party ones. My early tests indicated that I was right, which is why I decided to build the shortcut around Willison’s llm tool.

Read more

Recording Video and Gaming: A Setup Update→

It’s been a couple of months since I updated my desk setup. In that time, I’ve concentrated on two areas: video recording and handheld gaming.

I wasn’t happy with the Elgato Facecam Pro 4K camera, so I switched to the iPhone 16e. The Facecam Pro is a great webcam, but the footage it shot for our podcasts was mediocre. In the few weeks that I’ve moved to the 16e, I’ve been very happy with it. My office is well lit, and the video I’ve shot with the 16e is clear, detailed, and vibrant.

The iPhone 16e sits behind an Elgato Prompter, a desktop teleprompter that can act as a second Mac display. That display can be used to read scripts, which I haven’t done much of yet, or for apps. I typically put my Zoom window on the Prompter’s display, so when I look at my co-hosts on Zoom, I am also looking into the camera.

The final piece of my video setup that I added since the beginning of the year is the Tourbox Elite Plus. It’s a funny looking contraption with lots of buttons and dials that fits comfortably in your hand. It’s a lot like a Stream Deck or Logitech MX Creative Console, but the many shapes and sizes of its buttons, dials, and knobs set it apart and make it easier to associate each with a certain action. Like similar devices, everything can be tied to keyboard shortcuts, macros, and automations, making it an excellent companion for audio and video editing.

On the gaming side of things, my biggest investment has been in a TP-Link Wi-Fi 7 Mesh System. Living in a three-story condo makes setting up good Wi-Fi coverage hard. With my previous system I decided to skip putting a router on the third floor, which was fine unless I wanted to play games in bed in the evening. With a new three-router system that supports Wi-Fi 7 I have better coverage and speed, which has already made game streaming noticeably better.

Ayn Odin 2 Portal Pro. Source: Ayn.

Ayn Odin 2 Portal Pro. Source: Ayn.

The other changes are the addition of the Ayn Odin 2 Portal Pro, which we’ve covered on NPC: Next Portable Console. I love its OLED screen and the fact that it runs Android, which makes streaming games and setting up emulators a breeze. It supports Wi-Fi 7, too, so it pairs nicely with my new Wi-Fi setup.

A few weeks ago, I realized that I often sit on my couch with a pillow in my lap to prop up my laptop or iPad Pro. That convinced me to add Mechanism’s Gaming Pillow to my setup, which I use in the evening from my couch or later in bed. Mechanism makes a bunch of brackets and other accessories to connect various devices to the pillow’s arm, which I plan to explore more in the coming weeks.

The 8BitDo Ultimate 2 Controller. Source: 8BitDo.

The 8BitDo Ultimate 2 Controller. Source: 8BitDo.

There are a handful of other changes that I’ve made to my setup that you can find along with everything else I’m currently using on our Setups page, but there are two other items I wanted to shout out here. The first is the JSAUX 16” FlipGo Pro Dual Monitor, which I recently reviewed. It’s two 16” stacked matte screens joined by a hinge. It’s a wonderfully weird and incredibly useful way to get a lot of screen real estate in a relatively small package. The second item is 8BitDo’s new Ultimate 2 Wireless Controller that works with Windows and Android. I was a fan of the original version of this controller, but this update preserves the original’s build quality and adds new features like L4 and R4 buttons, TMR joysticks that use less energy than Hall Effect joysticks, and 2.4G via a USB-C dongle and Bluetooth connection options.

That’s it for now. In the coming months, I hope to redo parts of my smart home setup, so stay tuned for another update later this summer or in the fall.

Permalink

iOS and iPadOS 18.3 Tweak Apple Intelligence and Add a Few Features

Starting them young. Source: Apple.

Starting them young. Source: Apple.

The drip, drip, drip of Apple Intelligence continues with iOS and iPadOS 18.3. There are still some big-ticket features announced at WWDC 2024 that are yet to come, but with today’s release, Apple keeps ticking items off its list.

The biggest change is one that is largely hidden from view. Starting with iOS and iPadOS 18.3, Apple Intelligence is turned on by default. That should result in greater adoption of the features, and it’s a good indicator that Apple is confident LLM hallucinations won’t come back to bite the company in its reputation. We’ll see about that last bit, but given the size of the iPhone market, Apple’s guardrails have held up reasonably well so far.

That said, Apple is walking back one feature a little. Notification summaries will no longer be applied to news apps, after some high-profile confabulations. Given that news apps typically send headlines, which are inherently summary in nature, I don’t think that’s a great loss, although the change is reportedly temporary. However, one change to notifications is not temporary: starting with iOS and iPadOS 18.3, summarized notifications appear in italics to help distinguish them from other notifications.

Visual Intelligence has been updated in iOS 18.3 as well. Accessed by pressing and holding the iPhone’s Camera Control, Visual Intelligence can now add events to your calendar, identify animals and plants, and get information about places around you, such as a store or restaurant’s hours.

The latest update also adds back a Calculator feature. When you tap the equals sign repeatedly, the Calculator app will apply the last-used operation each time.

Finally, Apple introduced its latest Black Unity Collection earlier today. The iPhone and iPad wallpapers are part of iOS and iPadOS 18.3, and the new Unity Rhythm watch face is included with watchOS 11.3.

Apple Reveals the Top App Store App and Game Downloads of 2024

Apple’s App Store has published its year-end list of the top free and paid apps and games, along with its top Apple Arcade games.

The top free apps are about what you’d expect. There are social networks, shopping apps, a few streaming music and video apps, Google, Gmail, McDonald’s, and ChatGPT. Among the top paid apps are several we’ve covered here and on Club MacStories, including AutoSleep, Paprika, Procreate Pocket, Forest, RadarScope, µBrowser, and long-time favorite Streaks. Strangely, the paid app list also includes a game – Suika Game clone called ‘Merge Watermelon for watch’ for the Apple Watch.

Among the free and paid games, highlights include Subway Surfers, NYT Games, Minecraft, Geometry Dash, Stardew Valley, and Balatro. If you’re an Arcade subscriber, top games include NBA 2K24, Sneaky Sasquatch, Sonic Dream Team, NFL Retro Bowl ‘25, Angry Birds Reloaded, Retro Bowl+, Stardew Valley+, stitch, and Tomb of the Mask.

Each of the three lists includes 40 free and paid apps or games for 120 total. The vast majority of apps are the sort of everyday apps people download to shop, search the web, browse social media, and entertain themselves. There is more variety among the paid apps, with categories like health, self-improvement, productivity, and creative apps leading the apps for which users are willing to pay.

On the games lists, what struck me more than anything else is how many games on the lists aren’t new. That’s less true of Arcade, but it seems as though the hits of the past continue to rule the regular App Store game list. I’d like to see more variety in 2025, but it’s also good to see some truly great apps among the more everyday apps that will undoubtedly continue to get lots of downloads.

Apple Intelligence in iOS 18.2: A Deep Dive into Working with Siri and ChatGPT, Together

The ChatGPT integration in iOS 18.2.

The ChatGPT integration in iOS 18.2.

Apple is releasing iOS and iPadOS 18.2 today, and with those software updates, the company is rolling out the second wave of Apple Intelligence features as part of their previously announced roadmap that will culminate with the arrival of deeper integration between Siri and third-party apps next year.

In today’s release, users will find native integration between Siri and ChatGPT, more options in Writing Tools, a smarter Mail app with automatic message categorization, generative image creation in Image Playground, Genmoji, Visual Intelligence, and more. It’s certainly a more ambitious rollout than the somewhat disjointed debut of Apple Intelligence with iOS 18.1, and one that will garner more attention if only by virtue of Siri’s native access to OpenAI’s ChatGPT.

And yet, despite the long list of AI features in these software updates, I find myself mostly underwhelmed – if not downright annoyed – by the majority of the Apple Intelligence changes, but not for the reasons you may expect coming from me.

Some context is necessary here. As I explained in a recent episode of AppStories, I’ve embarked on a bit of a journey lately in terms of understanding the role of AI products and features in modern software. I’ve been doing a lot of research, testing, and reading about the different flavors of AI tools that we see pop up on almost a daily basis now in a rapidly changing landscape. As I discussed on the show, I’ve landed on two takeaways, at least for now:

  • I’m completely uninterested in generative products that aim to produce images, video, or text to replace human creativity and input. I find products that create fake “art” sloppy, distasteful, and objectively harmful for humankind because they aim to replace the creative process with a thoughtless approximation of what it means to be creative and express one’s feelings, culture, and craft through genuine, meaningful creative work.
  • I’m deeply interested in the idea of assistive and agentic AI as a means to remove busywork from people’s lives and, well, assist people in the creative process. In my opinion, this is where the more intriguing parts of the modern AI industry lie:
    • agents that can perform boring tasks for humans with a higher degree of precision and faster output;
    • coding assistants to put software in the hands of more people and allow programmers to tackle higher-level tasks;
    • RAG-infused assistive tools that can help academics and researchers; and
    • protocols that can map an LLM to external data sources such as Claude’s Model Context Protocol.

I see these tools as a natural evolution of automation and, as you can guess, that has inevitably caught my interest. The implications for the Accessibility community in this field are also something we should keep in mind.

To put it more simply, I think empowering LLMs to be “creative” with the goal of displacing artists is a mistake, and also a distraction – a glossy facade largely amounting to a party trick that gets boring fast and misses the bigger picture of how these AI tools may practically help us in the workplace, healthcare, biology, and other industries.

This is how I approached my tests with Apple Intelligence in iOS and iPadOS 18.2. For the past month, I’ve extensively used Claude to assist me with the making of advanced shortcuts, used ChatGPT’s search feature as a Google replacement, indexed the archive of my iOS reviews with NotebookLM, relied on Zapier’s Copilot to more quickly spin up web automations, and used both Sonnet 3.5 and GPT-4o to rethink my Obsidian templating system and note-taking workflow. I’ve used AI tools for real, meaningful work that revolved around me – the creative person – doing the actual work and letting software assist me. And at the same time, I tried to add Apple’s new AI features to the mix.

Perhaps it’s not “fair” to compare Apple’s newfangled efforts to products by companies that have been iterating on their LLMs and related services for the past five years, but when the biggest tech company in the world makes bold claims about their entrance into the AI space, we have to take them at face value.

It’s been an interesting exercise to see how far behind Apple is compared to OpenAI and Anthropic in terms of the sheer capabilities of their respective assistants; at the same time, I believe Apple has some serious advantages in the long term as the platform owner, with untapped potential for integrating AI more deeply within the OS and apps in a way that other AI companies won’t be able to. There are parts of Apple Intelligence in 18.2 that hint at much bigger things to come in the future that I find exciting, as well as features available today that I’ve found useful and, occasionally, even surprising.

With this context in mind, in this story you won’t see any coverage of Image Playground and Image Wand, which I believe are ridiculously primitive and perfect examples of why Apple may think they’re two years behind their competitors. Image Playground in particular produces “illustrations” that you’d be kind to call abominations; they remind me of the worst Midjourney creations from 2022. Instead, I will focus on the more assistive aspects of AI and share my experience with trying to get work done using Apple Intelligence on my iPhone and iPad alongside its integration with ChatGPT, which is the marquee addition of this release.

Let’s dive in.

Read more

The Latest from Comfort Zone, Magic Rays of Light, and MacStories Unwind

Enjoy the latest episodes from MacStories’ family of podcasts:

Comfort Zone

“The gang has so much to be thankful for, including you, dear listeners. ❤️

Oh yeah, and they find new ways to listen to music before being revealing their absolute favorite Apple app.”

Magic Rays of Light

Sigmund and Devon discuss Steve McQueen’s Blitz, new Apple Original documentary Bread & Roses, and the first episode of Concert for One featuring an immersive performance by RAYE.

MacStories Unwind

This week, a Thanksgiving guessing game, neighborly pies, NotebookLM, the Infamous Cousin Dave’s emoji habits, and getting started with retro gaming.

Read more

The MacStories Holiday Gift Guide for the Apple Nerd in Your Life

With Black Friday sales in full swing and the holidays around the corner, we here at MacStories thought we’d each share gift ideas for the Apple nerd in your life. Some of these items are currently on sale, so be sure to get your shopping started and check them out soon.

Federico

UGREEN 300W 48,000mAh Battery

I love this big, chunky battery with a handle.

As I recently mentioned on Unwind and NPC, I’ve been really into the idea of gadgets that are “portable, but for the home” this year. These are accessories that are portable in the sense that they can be moved around, but you wouldn’t commute or travel with them. In this case, I was looking for a powerful battery I could place on my living room table to charge multiple devices at once, such as Silvia’s MacBook Pro and my iPad Pro, or my Legion Go and iPhone. The internal capacity of this battery ensures it can stay on for hours when charging a single device like a Steam Deck, too.

The battery comes with a front-facing display with details about its charge and in/out wattages, and it even offers an LED light on the side for illuminating your environment. Plus, if you have a 140W USB-C charger, filling it up completely doesn’t take too long. This has to be one of my favorite tech purchases this year, and I can’t recommend it enough.

UGREEN Nexode Pro 100W Charger

Speaking of UGREEN, I also like their latest 100W GaN charger. Part of the company’s Nexode line, this is a compact USB-C wall charger that can output up to 100W via its first USB-C port when used by itself. This one is actually bag- and travel-friendly, and it’s become my new default for fast-charging the iPhone and iPad Pro.

Read more

A Peek into the Past Through the Lens of the Early iPhone’s Camera→

Riley Walz has created a marvelous couch potato project that peeks into a different era of the iPhone and YouTube. The idea behind Walz’s project, which I stumbled upon thanks to a story written by Umar Shakir at The Verge, is simple. The project is called ‘IMG_0001,’ because, as Walz explains:

Between 2009 and 2012, iPhones had a built-in “Send to YouTube” button in the Photos app. Many of these uploads kept their default IMG_XXXX filenames, creating a time capsule of raw, unedited moments from random lives.

Walz was inspired by Ben Wallace to build a website around the videos after Wallace wrote about discovering these videos. Walz found over 5 million videos with the IMG_XXX title on YouTube, which now feed into the IMG_XXXX website where they can be randomly played.

When you need a break, visit Walz’s site and watch a few videos. Filmed with early iPhones and iPod Touches, the quality isn’t great, but there’s something about these snippets of everyday life that someone decided to upload that is mesmerizing to watch. Projects like this are what make the open web great.

Permalink