2026-03-26 06:18:02
I’m pretty skeptical that Apple’s new Siri-wrapped Gemini will be able to accurately and reliably assist with automation. Gemini will be the foundation to Apple’s foundation models, but there’s no there there. Apple has no well-documented, debuggable, inspectable system to execute automation with, unless you count ancient and inscrutable AppleScript, and you shouldn’t.
Sure, LLM chatbots will spit out code (even AppleScript!) if you ask them to, but it might not work. It gets substantially worse when you’re asking LLMs questions about Shortcuts.
Go ahead and ask any chatbot to describe how to make a Shortcut to perform some automation that you’ve been wanting to do and then try to assemble what it suggests. It’s extremely tedious, prone to user error, and isn’t in any way guaranteed to work even when it’s all put together.
Agents that hook into development environments are much better than a bare chatbot because they can inspect, run, and debug the code they are generating. They aren’t perfect, but if you have an agent like Claude Code hooked up to an development tool like VS Code and start describing some Python script you want, it’ll execute and iterate until the output is what you asked for.
If humans don’t have access to documentation, to actionable debug output, logging, the ability to bypass/ignore actions as part of testing, and the ability to copy and paste snippets of code, then how can the new Siri do it?
Right now, Shortcuts works with AI models by passing some input and then receiving the output. When something goes to the model, the model transforms the data, and delivers a result back to Shortcuts. That’s a non-deterministic workflow, so any change to the model, or even just randomness in general, can produce different output. This means you can’t reliably troubleshoot or adjust it without introducing uncertainty in what new outputs you’ll get.
When working with an agent to assemble automation in an IDE, the code it builds is deterministic, so it will keep working even if the model changes. Not everything you want to automate requires LLM functionality when it runs, but not everything you automate should require hours of labor to fabricate the deterministic workflow version of it.
I really hope that the magic of new Siri isn’t going to be that it will just do things with bare actions and App Intents, magically, without any user-accessible process, or as a blob inside of a Shortcut you need to make. If I ask Siri to reorder a list, and it doesn’t do it correctly, I want to be able to access the scaffolding it created to see what went wrong, not just keep asking Siri to do it again in slightly different ways until I get output I like.
If Siri doesn’t produce anything inspectable, or it produces a Shortcut, then there’s not much work humans or AI can do to fix things.
The problem the Shortcuts app is supposed to solve has never been solved, because no one really knows how to use Shortcuts unless they become a Shortcuts expert. Shortcuts is user-friendly in appearance, but not in practice. It’s meant to welcome people who don’t know anything about programming with its friendly drag-and-drop interface, and searchable actions panel.
Unfortunately, the names for actions don’t always say what they do, and the documentation is often a vague piece of filler that’s frequently reused for more than one Shortcut action. Even experienced programmers can get flummoxed when they try to search the available actions for seemingly standard functions, like reversing a list.
Magic connections are magic, until your script gets any longer than the length of your screen and you need to start dragging actions around, inevitably breaking connections and making unintended ones. With a text-based script you’d have to keep track of the names and spelling of your variables, but they don’t change out from under you if you add more lines of code above or below them.
You can’t do one of the most simple, and useful things in scripting, which is commenting out (ignoring/bypassing) something to test or evaluate alternatives.
A lot of the time, when people are using Shortcuts, they’re relying heavily on the run shell script action to do actual programming that lets them write normal, vanilla code, or ssh’ing into a server from iOS to do the same thing. It’s nice that Shortcuts can do that, but shell scripts aren’t cross platform, and ssh’ing into a server is in no way accomplishing Shortcuts’ mission.
Without logging, you can’t ask Siri why your automation that was supposed to run in the middle of the night didn’t run. Maybe it was a permissions issue that was never raised when the shortcut was created. You, and Siri, just don’t know.
Again, Apple doesn’t have to do these things just for humans, or just for Siri. They are in no way mutually exclusive.
If the concern is that Shortcuts shouldn’t be like a programming language, with tracebacks, and logs which would put off “normal people” then just remember that “normal people” don’t really use Shortcuts. They ask a chatbot to just do it, and Siri, as Apple’s chatbot, could take advantage of those fiddly, programming bits and perform its role better, in a way that was auditable.
I have seen people make frantic posts on Mastodon about how AI is deskilling programmers, but the beauty of Shortcuts is that Apple already applies the deskilling at the factory.
2026-03-26 06:04:53
Our latest personal tech projects, twenty-five years of macOS, our networking setups, and where we turn for up-to-date information.
2026-03-26 05:49:50
The Verge’s Sean Hollister with just an excellent article breaking down the administration’s total nonsensical ban on consumer level routers made outside of the country. The article’s structured as a Q&A, and here are just a couple of my favorite excerpts:
Sounds bad. But if they’re not recalling the routers, and they’re not fixing them… what the heck is the government actually doing?
It’s banning future routers that haven’t been made yet.
You’re not making a lot of sense.
I warned you this was a story about Brendan Carr, known dummy and anti-consumer FCC chairperson! Specifically, the FCC is keeping new, previously unannounced, foreign-made consumer routers out of the US… unless it decides to exempt them. For reasons. We’ll get to those.
Hollister classifies this as a shakedown to somehow force more manufacturing jobs back to the U.S. Gee, I wonder if there could possibly be any…let’s say exploitable…loopholes to this brilliantly concocted plan:
What if I buy one of those newer routers in Canada and bring it back home?
The FCC’s magic 8 ball says, “no,” but good luck enforcing that, Brendan.
2026-03-25 22:00:00
Moltz goes on and on about games, Dan makes a vicarious purchase and Lex has a new app!
2026-03-24 23:35:11
Apple today announced Apple Business, a new all-in-one platform that includes key services companies need to effortlessly manage devices, reach more customers, equip team members with essential apps and tools, and get support from experts to run and grow efficiently and securely. Apple Business features built-in mobile device management, helping businesses easily configure employee groups, device settings, security, and apps with Blueprints to quickly get started. In addition, customers can now set up business email, calendar, and directory services with their own domain name for seamless and elevated communication and collaboration.
This new offering actually consolidates three existing Apple products, Apple Business Manager, Apple Business Essentials, and Apple Business Connect, and offers mobile device management for free, which will save some existing customers money. There are also some new API functions for larger organizations, and Apple is offering businesses access to Apple-hosted email and calendaring for the first time. The new Blueprints feature will make it easier for administrators to assign configurations and apps.
Also announced today is something that has been widely expected: ads in Maps in the U.S. and Canada. We now know those will arrive this summer. Apple provides additional details further on:
Ads on Maps will appear when users search in Maps, and can appear at the top of a user’s search results based on relevance, as well as at the top of a new Suggested Places experience in Maps, which will display recommendations based on what’s trending nearby, the user’s recent searches, and more. Ads will be clearly marked to ensure transparency for Maps users.
Again, it’s not a huge surprise to see this—Apple has been working on bolstering its ad business in the past few months. But it does mean that once this feature is enabled, you’ll have to scroll past an add to see results when you search for stuff in Apple Maps.
Ads or no, companies that use Apple Business will also be able to edit their metadata and upload pictures directly into Apple Maps.
It’ll take some time to digest these changes, but it seems like this is a simplification of Apple’s business offering, and making MDM free will be a win for smaller organizations. Unfortunately, Apple’s still only offering 5GB of free iCloud data on managed accounts, and it’s hard to think that any business should rely on Apple’s notoriously unreliable email platform.
2026-03-24 22:15:01
From Eric Berger at Ars Technica, the first of a three-part series about orbital data centers. This first part focuses largely on economics, but also touches upon issues of the environment, the obliteration of the night sky, and more. It’s a really fascinating read.
“This is not physically impossible; it’s only a question of whether this is a rational thing to scale up economically,” [engineer Andrew] McCalip said. “The answer is it’s really close. And if you own both sides of the equation, SpaceX and xAI, it’s not a terrible place to be. I wouldn’t bet against Elon.”
Yet betting on Elon also requires a giant leap of faith.
The third part of this series will dive deeper into detailed cost estimates, but in terms of round numbers, the bare-bones cost of deploying 1 million satellites is more than a trillion dollars. SpaceX’s two biggest previous projects to date, the hyper-ambitious Starlink and Starship programs, each required on the order of $10 billion up front. So in terms of scope and cost, orbital data centers are two orders of magnitude larger.
The part that has me curious, but isn’t really addressed in the story, is future-proofing. Companies like Nvidia are kicking out new chips at such a rate that the processors you send in to orbit will almost certainly be outdated by the time they’re operational. Will that be enough to offset the perceived gains? Are we constantly going to be launching new satellites? What happens to the old one? What if the AI bubble bursts? All fertile ground for a near-future sci-fi story, methinks, if not near-future non-fiction.
