Month: June 2025

Dan Moren ended his “Stay Foolish” column at Macworld with a tremendous essay about what it means to be a “fan” of Apple or its products in 2025:

Over the years, those in the Apple community have long been called everything from the liturgical “Apple faithful” to the insipid “iSheep”, dating back to the days when the prevailing wisdom was that to hitch your fortunes to this weird company must imply a cult-like devotion. The simple truth was that most customers were simply fans of the products themselves: they liked the way they worked and looked.

That hasn’t changed for me: I continue to be a fan of Apple’s products. But as Apple started becoming more and more successful, I’ve become increasingly skeptical that one should ever really consider oneself a “fan” of a company.

On the eve of WWDC and, with it, the kicking-off of Apple’s coming year, I found myself thinking about this column published in April.

There was a time when rooting for Apple and calling oneself a “fan” seemed to make sense. The things it designed and sold had a clear ethos that gave me an impression of the kind of effortless confidence that only comes from a massive amount of effort. The business model felt like a simple exchange — as Steve Jobs said at D8, “we want to make the best products in the world for our customers. If we succeed they’ll buy them, and if we don’t they won’t”.

That era — the Jobs era, the simplistic worldview era, and the clear ethos era — is behind us. I am not saying Apple now takes everything for granted; I am sure it has teams of people working hard all day long to make improvements. But it is a corporate behemoth that cannot move quickly. Regardless of how cool its rumoured “Liquid Glass” visual refresh may be, I have a difficult time believing it will radically alter the way we use our devices. There are 2.35 billion devices on users’ wrists, in their hands and bags, and on their desks. At least a billion of them are iPhones. So, even though it is a bit exciting to be on the verge of something new and different, I do not think it will be that new and different, lest Apple alienate a huge number of people. It will look different enough, and that looks like progress — and maybe it will actually represent progress, too.

Visual interface changes aside, the expectations for this year’s WWDC do not seem to be high. We are still waiting on last year’s most impressive Apple Intelligence features, and the Vision Pro is a nascent device in the hands of few. The ideas factory is sputtering a little. But the money factory remains strong.

I am enmeshed in the Apple ecosystem so, in some ways, it should be exciting the company has to try a little harder. I am not. I do not think anyone expects Apple will sell dramatically fewer iPhones this year, nor will it lose subscribers to services, its increasingly important recurring revenue printer. Apple was a more interesting company when it could not be certain its customers would buy more stuff. I hope, after the Vision Pro’s release, it is also understanding it cannot take its developer base for granted, either.

Every time I use the Windows 11 computer on my desk at work, I am reminded of why I use MacOS. I still prefer it. But the post-P.C. device era has encouraged some nasty habits at Apple that have, consequently, made it one of the world’s most valuable businesses.

Apple has all the money it could ever want. It sells some very good products. But its size has smothered the fire it seemed to have, and dulled its edge. There are still risky bets it could make, but all of them are necessarily softened by its critical position in the world’s economy and in retirement plans. I see no reason to be a fan of that kind of company, even if you — as I — still appreciate many of the products and services it delivers. I am, as ever, looking forward to seeing what is being announced tomorrow, albeit with the understanding I will be watching a slick infomercial possibly containing concept videos. It is hard to see how one could be a fan of a multi-trillion-dollar company. I am just a customer, like a billion-plus others.

Speaking of the Analysis Group, here is a press release from 2022:

Analysis Group was acknowledged at the GCR [Global Competition Review] awards ceremony for its work on Epic Games v. Apple, which was awarded “Matter of the Year” and “Litigation of the Year – non-cartel defence.” The litigation involved allegations that anti-steering provisions contained in Apple’s App Store policies for developers stifled competition.

And here is an article by Tripp Mickle, New York Times, from last month:

Judge Gonzalez Rogers questioned whether Apple was telling the truth and asked the company to provide documents about its plans. It produced 89,000 documents but claimed a third of them were confidential. The court said those claims were “unsubstantiated” and forced Apple to turn over more than half of the documents.

The documents made clear that Mr. Roman had lied under oath, that the Analysis Group report was a “sham” and that Apple had “willfully” disregarded a court order, Judge Gonzalez Rogers said. She called it a “cover-up.”

I wonder if the Analysis Group is giving back that award. I also wonder if that matters in the eyes of industry groups like the Global Competition Review.

Apple:

Apple today announced the global App Store ecosystem facilitated $1.3 trillion in developer billings and sales in 2024, according to a new study by economists Professor Andrey Fradkin from Boston University Questrom School of Business and Dr. Jessica Burley from Analysis Group. For more than 90 percent of the billings and sales facilitated by the App Store ecosystem, developers did not pay any commission to Apple.

The purpose of this study — also produced in 2020, 2021, and 2023, though not last year — is two-fold. First, it indicates to lawmakers the footprint of the App Store and suggests any further regulatory action would seriously compromise the economy as a whole. The second reason it exists is to soften the impression of Apple’s commission on digital purchases, hence this part of the study and press release, emphasis mine:

The new study by Professor Fradkin and Dr. Burley highlights how developers on the App Store have more ways than ever to monetize their apps. The study found that in 2024, developer billings and sales for digital goods and services totalled $131 billion, driven by games, photo and video editing apps, and enterprise tools. Sales of physical goods and services exceeded $1 trillion, fuelled by rising demand for online food delivery and pickup, as well as grocery orders. In-app advertising revenue from ads placed by developers in their apps was $150 billion.

A big amount, but measured against the total estimated economy of $1.3 trillion, it is supposed to be seen as a small fraction — “less than 10%”. This number is, the study’s authors write, not an estimate of payments made through In-App Purchases:

Sales from digital goods and services purchased elsewhere but used on apps on Apple devices are included, while billings from in-app purchases made via the App Store but used elsewhere are excluded.

I do not understand why this definition was chosen. Surely the excluded sales are actually a better example of transactions “facilitated by the App Store ecosystem”, even if the purchase is ultimately consumed elsewhere. But, then again, I cannot think of many things I can buy with In-App Purchases which I ultimately use outside the app, so perhaps it does not make much difference if they had been included. It may be the result of a methodological gap in the study.

The study’s authors still conclude Apple takes a commission on “less than 10%” of $1.295 trillion. If this number was closer to 1%, the report would probably say that. It is perhaps a touch unfair, but let us assume it is about 10%, which happens to be just shy of the $131 in total digital billings. Apple’s commission is not as straightforward as the flat 30% rate it used to charge. But, at its minimum 15% rate, this suggests Apple made at least $19.4 billion in 2024 in App Store commissions alone — from what the Analysis Group says is less than 10% of an economic ecosystem facilitated by the App Store.

Jeff Johnson:

I’ve always been baffled about why a small minority of developers, including small indie developers like me, are required to finance the App Store ecosystem for every developer, including the developers of “free” apps that nonetheless generate billions of dollars per year from billings and sales. Why is Apple’s IAP not required for all purchases in all App Store apps? It’s difficult for me to see a principled distinction between the apps that have to use Apple IAP and the apps that don’t. It seems completely arbitrary. Apple made a big deal about Spotify not making “contributions to that marketplace,” yet Apple also openly (and hypocritically) admits that most of the financial transactions that occur in App Store apps are not contributing to that marketplace either. There are a lot of “free riders” in the App Store.

The thing about the Analysis Group’s report is that it is very broad. While it does not include transactions made through Safari on iOS, things like shopping in Amazon’s app or buying airfare in Kayak’s app are factored in. Whether these purchases were actually facilitated by the App Store ecosystem is questionable to me — would someone have not bought that flight if not for their iPhone?

Where this gets especially murky is with the whole economic world that is dependent on smartphones. The classic example of this is Uber. Taxis have existed for a long time, and so have pirate taxis, and you could always ask your friend to carpool, and you can take a bus. But the structure of Uber, which relies on an app each for customers and drivers, would not exist without the App Store. Yet Uber is not required to use In-App Purchases, nor does Apple collect any commission on its business. A similar argument could be made about social apps like Instagram and TikTok, which are also smartphone-dependent, yet are funded by ads Apple does not get a cut of — mostly.

Apple has argued in court this commission is for App Store upkeep, developer relations, API development, and for intellectual property licensing. These are things common to all apps. Yet only those facilitating transactions for digital services are expected to pay? How is Uber — with its half-gigabyte client app updated once or twice weekly for tens of millions of users — not paying for App Store hosting and bandwidth, but indie developers are?

Do you want to block all YouTube ads in Safari on your iPhone, iPad, and Mac?

Then download Magic Lasso Adblock — the ad blocker designed for you.

Magic Lasso Adblock: YouTube Ad Blocker for Safari

As an efficient, high performance, and native Safari ad blocker, Magic Lasso blocks all intrusive ads, trackers, and annoyances — delivering a faster, cleaner, and more secure web browsing experience.

Magic Lasso Adblock is easy to set up, doubles the speed at which Safari loads, and also blocks all YouTube ads; including all:

  • video ads

  • pop up banner ads

  • search ads

  • plus many more

With over 5,000 five star reviews, it’s simply the best ad blocker for your iPhone, iPad, and Mac.

And unlike some other ad blockers, Magic Lasso Adblock respects your privacy, doesn’t accept payment from advertisers and is 100% supported by its community of users.

So, join over 350,000 users and download Magic Lasso Adblock today.

With just a few days to go until WWDC, Stephen Hackett chronicled the history of the mythical 3 GHz Power Mac G5, previewed at the conference over twenty years ago:

The heat generated by the G5 would become an issue later on, but first we need to talk about Steve Jobs broke a fundamental rule of Apple:

We don’t comment on future products.

The Power Mac G5 was before my time as a Mac user, but I remember the otherworldly impression it made on me. I am no Mac historian, but it still feels to me like it began a distinct era of flagship Macs that were both powerful and relatively accessible — the inflation-adjusted price of the best G5 spec, without build-to-order upgrades, is nearly $2,000 less than the base price of today’s Mac Pro.

I, like millions of people, spend a good chunk of my Mondays through Fridays in Microsoft 365 (formerly Office) applications, many of which I partly or wholly access through a browser. For years, I could just type portal.office.com in my browser and get links to Word, Excel, Outlook — all the classics — plus some organization-specific applications.

Microsoft being Microsoft, it has decided to bury all that. We are in the artificial intelligence era now, baby. Instead of seeing the applications millions of people rely on, Microsoft has decided the default view should be a Copilot chat. The familiar suite of apps is in another page accessible from the sidebar; each app can, at least, be pinned to that same sidebar. This was barely announced and seems to have taken many by surprise.

But, hey, Copilot should at least make me more productive, right? It is Microsoft’s own service — albeit backed by OpenAI’s work — and integrated, in theory, with our organization’s applications and files. Maybe it could function as an application launcher. So I told Copilot to “launch Word”. Copilot:

I can’t directly launch Microsoft Word from here, but I can help you open it on your device. Here’s how you can do it:

On Windows:

  1. Press the Windows key on your keyboard or click the Start menu.

  2. Type “Word” in the search bar.

  3. Click on Microsoft Word from the search results.

On macOS:

  1. Open Finder or press Command + Space to open Spotlight Search.

  2. Type “Word” and press Enter when Microsoft Word appears.

Truly embarrassing stuff to interrupt users’ learned workflow for something worse because it is important for Microsoft to be seen as a cutting-edge innovator. It has made Copilot part of its branding — so much so that it will advertise Copilot even where it is not available, for “consistency”.

Richard Lawler, the Verge:

Texas moved closer to becoming the next state with a right to repair law on the books, as the state Senate unanimously voted 31 – 0 to finalize HB 2963 this weekend. It would require manufacturers to make spare parts, manuals, and necessary tools available for equipment sold or used in the country’s second most populated state.

Maddie Stone, Grist:

That [if Ohio’s bill becomes law] would mark an important political inflection point for the right-to-repair movement. While most of the states that have passed repair laws so far are Democratic strongholds, bills have been introduced in all 50 as of February. The adoption of a right-to-repair law in deep red Ohio — where Republicans control the state House, Senate, and the governor’s office, and Donald Trump won the last presidential election by more than 10 percentage points — would further underscore the broad, bipartisan popularity of being allowed to fix the stuff you own.

Karl Bode, TechDirt:

This is definite progress, and I hate to be a buzzkill, but it’s worth reiterating that of the 8 states that have passed right to repair reforms so far, not a single one has actually enforced them in any meaningful way. This despite no shortage of bad corporate actors working overtime to kill independent repair shops, make manuals and parts hard to find, use obnoxious DRM, or claim that repairing your own stuff violates warranty.

The problem with corporations insisting upon the safety and reliability that only comes from staying within their own ecosystem of parts and accessories is that they are frequently lying or, at least, exaggerating about the dangers. At least lawmakers across the political spectrum and around the world are beginning to call them on their tall tales.

Michael Geist:

The government yesterday introduced the Strong Border Act (Bill C-2), legislation that was promoted as establishing new border measure provisions presumably designed to address U.S. concerns regarding the border. Yet buried toward the end of the bill are lawful access provisions that have nothing to do with the border. Those provisions, which raise the prospect of warrantless access to information about Internet subscribers, establish new global production orders of subscriber information, and envision new levels of access to data held by electronic service providers, mark the latest attempt in a longstanding campaign by Canadian law enforcement for lawful access legislation. Stymied by the Supreme Court of Canada (which has ruled that there is a reasonable expectation of privacy in subscriber data) and by repeated failures to present a compelling evidentiary case for warrantless access, law enforcement has instead tried to frame lawful access as essential to address everything from organized crime to cyber-bullying to (now) border safety. […]

As has become frustratingly typical for laws of this type, there are secrecy requirements and warrant workarounds based on urgency. But it is tucked into an unrelated bill that only exists because of provocations from our southern neighbour. This is a completely dishonest runaround to legislate long-desired capabilities.

Update: Jeremy Appel, the Orchard:

I have a Liberal campaign flyer pinned to my office wall, where I place election campaign literature I accumulate from various elections, which reads: Making life more affordable, protecting your rights and standing up to Trump.

This legislation doesn’t do any of these things, and in fact does the opposite of two of the three.

Profound weakness masquerading as strength and confidence.

Dan Sinker:

Hanif Abdurraqib, in one of his excellent Instagram mini-essays the other week, wrote about the rise of content that’s designed to be consumed while doing something else. In Hanif’s case, he was writing about Time Machine, his incredible 90 minute deep dive into The Fugees’ seminal album The Score. Released in 2021, Hanif marveled at the budget, time, and effort that went into crafting the two-part 90 minute podcast and how, today, there’s no way it would have happened.

He’s right. Nobody’s funding that kind of work right now, because nobody cares.

(It’s worth pointing out that Hanif wrote this using Stories, a system that erased it 24 hours later. Another victim of the Who Cares Era.)

This does not seem like it is a brand new feeling. It is plausible that one could create a Paul Fairie-esque collection of similar complaints throughout history — of art created only for commerce’s sake; of shallow media intended for brief consumption instead of a lasting impression.

I think it is more useful to de-emphasize the “era” part of Sinker’s criticism, and to instead consider how carelessness creeps in. Sarah Wynn-Williams published “Careless People” earlier this year. I wrote in April about Perplexity’s carelessness of ethics and privacy. Perhaps both of these examples are better described as corrosion or corruption. What Sinker is describing is more like cultural and societal ennui.

Les Orchard:

The user isn’t the customer. And they’re not the product either. The real product is behavioral optimization — metrics on a dashboard. The paying customer is somewhere else entirely, and the “content” is just a means to nudge behavior and juice KPIs.

There have always been measures for success, but the ability to relentlessly optimize for them is a fairly new phenomenon. Plenty of films and plays are created by reverse-engineering the tropes favoured by award committees, but they still need to be good in order to draw an audience.

Update: A lack of care is, in part, downstream of other forces (previously linked).

I am a daily user of a V60, so this new James Hoffmann video scratched an itch I did not know I had. Not to spoil it, but the V60 does not make a significant appearance until the last four minutes, but the journey is worth the wait.

The discussion of the mid-2000s specialty coffee movement in Canada brought back some memories, too. Vancouver was the most significant place in the country and perhaps one of a few places in the world where this attitude toward coffee was taking over, and Calgary luckily received some of the reflected glory. There are shots of menus from 2006 with by-the-cup brewing for two or three dollars, around the same time Phil & Sebastian was getting started here. There is a note at the bottom of one of the menus from Elysian advertising advance purchases of a forthcoming award-winning coffee at the then-devastating price of ten dollars per cup.

Turns out twenty years is a long time.

Aniketh Girish, et al.:

We disclose a novel tracking method by Meta and Yandex potentially affecting billions of Android users. We found that native Android apps — including Facebook, Instagram, and several Yandex apps including Maps and Browser — silently listen on fixed local ports for tracking purposes.

Dan Goodin, Ars Technica:

The covert tracking — implemented in the Meta Pixel and Yandex Metrica trackers — allows Meta and Yandex to bypass core security and privacy protections provided by both the Android operating system and browsers that run on it. Android sandboxing, for instance, isolates processes to prevent them from interacting with the OS and any other app installed on the device, cutting off access to sensitive data or privileged system resources. Defenses such as state partitioning and storage partitioning, which are built into all major browsers, store site cookies and other data associated with a website in containers that are unique to every top-level website domain to ensure they’re off-limits for every other site.

The difference between targeted advertising and spyware is there is no difference.

After Girish, et al., disclosed this behaviour, Meta’s apps ceased tracking users with this method, and Goodin said Yandex will also stop. Meta is still under a consent decree struck in 2019 with a $5 billion penalty after violating a 2012 agreement. Executives at Meta do not care about privacy, rules, laws, or common sense. They will keep doing stuff like this. Ad tech is an indefensible industry run by megalomaniacs who would better serve society if they were made to live in a cave under an ice sheet, though I do not care which one.

This, from Adam Newbold, is a perfect encapsulation of a bunch of ethical problems related to artificial intelligence. The prompt:

Generate an image for a Calvin & Hobbes strip. Four panels. Calvin and Hobbes are walking through the woods, talking to each other, both holding smart phones and looking at them intently the entire time.

Panel 1: Calvin says to Hobbes, “This strip was made entirely with ChatGPT, which should be impossible given the strict intellectual property rights restrictions on Calvin & Hobbes content.”

Panel 2: Hobbes responds to Calvin, “Oh? Then how did it make it?”

Panel 3: Calvin responds to Hobbes, “Some guy just typed this into a box and clicked a button. That’s all it took.”

Panel 4: Hobbes responds to Calvin, “That’s so fucked up.”

This is entirely doable without generative artificial intelligence, but it requires far more skill. The ease of this duplication is maddening. I find this offensive in exactly the way Newbold intended it to be.

More important, I think, is the control exercised over the likenesses of Calvin and Hobbes by the strip’s creator Bill Watterson, as Newbold noted in the strip. Watterson famously rejected all but a handful of licensed merchandising ideas. But the mechanism for how he might protect this is the same as the one used by Disney when it fights parody and reinterpretation of its vast intellectual property, even though the motivations are different. Watterson’s protective quality is admirable, driven by artistic integrity to the extent he has left many millions of dollars’ worth of tchotchkes on the table to retain the spirit of the strips. Disney’s is entirely business motivated, evidenced by the tens of billions of dollars in licensed tchotchkes sold last year alone.

This is not the first “Calvin & Hobbes” strip made with generative A.I., nor does generative A.I. begin and end at self-referential prompts like these. Some assholes have created plugins — more-or-less — to badly emulate Watterson’s unique style in generative A.I. programs. It is awful.

I want to live in a world where we can differentiate between the necessary reinterpretation of intellectual property while respecting the wishes of artists. This is a tricky line, I know. It requires us — individually, but also the organizations responsible for generative A.I. stuff — to think about who is making such a request in good faith, and decide whether we are going to honour that.

One more thing: Watterson is a pretty private person, rarely giving interviews. But, right above this paragraph, I think we can get a sense of how he might feel about this.

Adam Engst, TidBits:

To distinguish these tools [Perplexity and ChatGPT’s web search] from traditional search engines like Google and Bing, I’m calling them “answer engines.” Although they are performing live Web searches for you, the focus is on answering your question rather than displaying the results of the search. I see answer engines as the next step in networked knowledge acquisition because they fundamentally change how we find and absorb information online:

[…]

The key benefit of answer engines is that they typically provide you with exactly the information you want, with no additional effort required. They’re a bit like Wikipedia in this way—you could fact-check statements with the listed sources in a Wikipedia article, and you can often learn more by following links to related topics, but most of the time, you’re happy to read the article and move on.

I think Engst is, in an ideal world, correct — A.I. search is positioned as a way to get straight to the answer. It, theoretically, cuts through a web poisoned by bait for search engines, marketing copy disguised as information, and thin articles suffocated by ads.

So far, I have rarely been satisfied by the results I have received. It has never been satisfactory for someone to say “according to Google” when asked how they know a piece of information, and the deadpan way answer engines frame their responses gives them an unearned authority. I have found it necessary to double check everything. I recently documented ChatGPT’s answer with an invented report with an invented quote that led me to the results I was looking for after some web searches. I have also posted screenshots from Google’s A.I. answer engine on Mastodon. It made up an Excel option and cited it to Microsoft’s documentation; it claimed Noah Wyle co-starred with Alex Horne in “The Pitt”. In fairness, I would like to see that.

Even so, these answer engines have been helpful for me as starting points. It can sometimes be difficult to know what search terms to use, even if you can formulate in your head the question or type of answer you are hoping to receive. I have found this particularly helpful with web development questions. They are tools that can support someone on a research journey. But we should remain skeptical that some trained black box of mystery is able to directly answer questions accurately. We must check, and re-check. Our ability to use these products depends on a well-developed skill for research.

Online privacy isn’t just something you should be hoping for – it’s something you should expect. You should ensure your browsing history stays private and is not harvested by ad networks.

Magic Lasso Adblock: No ads, no trackers, no annoyances, no worries

By blocking ad trackers, Magic Lasso Adblock stops you being followed by ads around the web.

As an efficient, high performance and native Safari ad blocker, Magic Lasso blocks all intrusive ads, trackers, and annoyances on your iPhone, iPad, and Mac. And it’s been designed from the ground up to protect your privacy.

Users rely on Magic Lasso Adblock to:

  • Remove ad trackers, annoyances, and background crypto-mining scripts

  • Browse common websites 2.0× faster

  • Block all YouTube ads, including pre-roll video ads

  • Double battery life during heavy web browsing

  • Lower data usage when on the go

With over 5,000 five star reviews; it’s simply the best ad blocker for your iPhone, iPad, and Mac.

And unlike some other ad blockers, Magic Lasso Adblock respects your privacy, doesn’t accept payment from advertisers and is 100% supported by its community of users.

So, join over 350,000 users and download Magic Lasso Adblock today.