Apple’s Too Conservative Approach to Text Intelligence

Apple is, understandably, taking a conservative approach to artificial intelligence. Nowhere is this more obvious and product-crippling than its text intelligence features. I am a fan of using AI for an edit pass on my words. Specifically, I’ve come to rely on Grammarly and its ability to sniff out overused adverbs and otherwise general sloppiness in my writing.

I’ve been around long enough to recall when grammar checkers first started appearing in applications like Microsoft Word. They were useless. It was comical how often their recommendations went against the grammar rules and made your writing worse. It wasn’t until the arrival of Grammarly that I got back on board with the idea of a grammar checker, and it’s been quite helpful. Note that I’m not using artificial intelligence to write for me; I’m using it to check my work and act as a first-pass editor. The problem I’ve always had with Grammarly is that it sends my words to the cloud whenever I want them checked.

Ideally, I’d like that done privately and locally. That’s why I was so excited about Apple Intelligence and text intelligence. It would presumably all happen on the device or Apple’s Private Cloud Compute servers. Unfortunately, at least in beta, Apple Intelligence isn’t up to the task. That conservative approach makes Apple’s Text Intelligence useless to me in this editor role. While Apple’s tools can identify obvious grammatical errors, they fall short in the more nuanced aspects of writing assistance.

A telling example: As a test, I recently gave Apple Intelligence a paragraph where the word “very” appeared in three consecutive sentences — a clear style issue that any modern writing tool would flag. However, Apple’s text intelligence didn’t notice this repetition. That’s very, very, very bad.

This limitation reflects a broader pattern in Apple’s approach to AI tools. While the foundation is solid, the current implementation may be too restrained to compete with existing writing assistance tools that offer more comprehensive feedback on style and readability. The challenge for Apple will be finding the sweet spot between maintaining their caution and delivering genuinely useful writing assistance. I get the big picture here. I know they’re not trying to make a Grammarly competitor, but they need to take several steps away from that conservative benchmark if this is going to be useful.

Another problem with the text tools is the implementation of recommended changes. You can have it either replace your text entirely (without any indicator of what exactly was changed) or give you a list of suggested edits, which you must implement manually. Other players in this space, like Grammarly, highlight recommended changes and make it easy to implement or ignore them with a button.

Apple is famous for its ability to create excellent user interfaces, and I suspect they could do something similar but probably better if they put their minds to it. Unfortunately, the current version of the text intelligence tools in Apple Intelligence isn’t even close.

The Lab Report for November 29, 2024

The Opal C1 Webcam is meant to be the webcam everybody actually wants to use. It\’s got tons of software features and a better lens system than anything you\’d find in most (all?) other webcams. It\’s time for me to kick the tires…

This is a post for MacSparky Labs Tier 2 (Backstage) and Tier 3 (Early Access) Members only. Care to join? Or perhaps do you need to sign in?

Happy Thanksgiving

Happy Thanksgiving, gang. Let’s hope that next year at this time, Apple Intelligence can actually draw a picture of a turkey on a farm wearing sunglasses.

A New Pro Display

I’m often asked about future Apple displays. Many people are now switching over to the desktop-computer-plus-screen model as the big iMac seems less likely to show up, and the Mac mini got so damn cute. So folks want to know if Apple has any new displays in the works. I’m sure the Apple Studio Display and Pro Display XDR will get successors, but I’ve got no clue when. Apple can sometimes go a long time between updating monitors and has, in the past, abandoned making them altogether.

The latest rumor is that the Pro Display XDR will be improved using Quantum Dot technology. This makes a lot of sense. The Pro Display XDR is really expensive and has a low-volume screen. The current MacBook Pro displays are, by most measures, better. Bringing new tech to the Pro Display would give Apple a low-volume platform to iron it all out before bringing it to the more popular displays. The rumor is that it won’t get released until late 2025 or 2026.

One question in my mind is if they do create a successor to the Pro Display XDR, is it going to use the same mounting system as the existing one? Will people who dropped $1,000 for one of those stands be able to use it with the next iteration? Place your bets.

Yoink for Improved Drag-and-Drop

This week MacSparky is sponsored by Yoink (Website) (for Mac) (for iOS). Dragging and dropping files from one place to another is a common task, but it’s not that easy.

You have to click on the file you want to move, drag it over to the destination of your choice, and drop it there. This can be done if you’re lucky enough to land in the right spot and have just the right windows open next to each other. You also have to do this while looking at your monitor, which means that every time you drag something around, you are distracted from what else might be happening in front of your eyes. Moving files shouldn’t feel like defusing a bomb.

Yoink allows users to easily drag & drop items, getting files exactly where they belong and without having to have everything set “just right” in advance. They have a version for Mac, iPhone, and iPad and I use it daily. Everybody needs a shelf. Make your technology shelf Yoink.

There are several reasons I chose Yoink over its competitors. First, I like the design. It looks nice but also gets out of the way when I’m not using it. Second, Yoink has been around for a while, and it has both stability and a rich set of features. Get Yoink if you need a shelf app that won’t let you down.

Yoink’s developer also has two other useful apps, ScreenFloat (a screenshot utility) and Transloader (a download utility). You can get a bundle with all three apps in the App Store.

Passkey Adoption is Too Slow

We recently hit a milestone in the world of digital security: 200 companies are now using passkeys instead of traditional password systems. It’s progress, sure, but to me, it’s not exactly fireworks-worthy. Frankly, it feels like we should be much further along.

I’ve heard from many in my audience — a group of smart, tech-savvy folks — and yet, there’s hesitation. People are leery about passkeys. The idea of leaving behind the trusty (if flawed) username and password combo still feels risky to some. That’s understandable; we’re in a strange transitional phase where trust in the new system is still being earned, and the old system isn’t quite dead yet.

Right now, a lot of companies are hedging their bets. They implement passkeys but keep the traditional username and password system alive “just in case.” While that might sound like a good compromise, it actually introduces new risks. Let me explain.

When a site offers both options, it creates a tempting target for bad actors. Imagine this: You try to log in with your shiny new passkey, and a fake prompt tells you it failed. Next thing you know, you’re asked to log in with your password instead. Guess what? You just handed over your credentials to the bad guys.

By maintaining the old system alongside the new one, we’re essentially giving attackers two doors to try. It’s like installing a state-of-the-art security system but leaving the back door unlocked “just in case.”

Then there’s the trend of bypassing passwords entirely in favor of email-based authentication. At first glance, it seems simple and clever: “Just click the link we emailed you.” But email isn’t exactly a fortress of security. If someone compromises your email account, they’ve got the keys to the kingdom.

This trend feels like a half-step solution. It’s better than nothing, but it’s not the robust answer we need in the long term.

Passkeys, when implemented correctly, are a huge leap forward. They’re designed to be more secure and easier to use. They’re phishing-resistant, for one thing. A hacker can’t trick you into handing over a passkey the way they can a password. And they take advantage of the biometric and secure enclave tech built into our devices, which is vastly more secure than anything we’ve relied on before.

We’re in this awkward adolescence of digital security. But getting to the point where passkeys are the norm will take a concerted effort. Companies need to be all-in, not straddling the line. Users need better education about how passkeys work and why they’re safer. And the tech industry as a whole needs to push forward faster.

Right now, everything about passwords and passkeys feels a little brittle. The sooner we can move to a world where passkeys are ubiquitous and properly implemented, the better off we’ll all be. Until then, stay vigilant, stay informed, and don’t forget to lock the back door.

Apple Claps Back