In the month that I’ve been using iOS 27 (launching in public beta today) and the new Siri AI, I’ve come to a few conclusions: Siri AI is a much better Siri and will (probably) be a massive success; the newfound chatbot capabilities of Siri will pose a serious threat to OpenAI and the vast majority of free ChatGPT users they have; and the new Siri is (again, probably) not for me at the moment. At the very least, it can’t be right now given its lack of support for third-party apps and technical issues I’ve encountered during beta testing.
It took me a while to accept the fact that Siri AI can’t be the kind of AI assistant I’d spend hours working with every day. But after testing iOS 27’s new Siri experience every day (and breaking it often in the process), I think that’s okay – and, arguably, what Apple is shooting for at the moment.
The new Siri AI is not designed for people who have grown accustomed to working with frontier models and agents such as Claude Code and Codex. The first version of Siri AI can’t be considered an “agent”, nor can it be compared to products from Anthropic, OpenAI, or Google that are targeting power users living at the bleeding edge of AI. If you go into Siri AI thinking that it’s Apple’s answer to ChatGPT Work or Claude Cowork for long-running tasks or deep research queries, you’re going to be disappointed – like I initially was.
Instead, Siri AI carries all the typical traits of a new Apple product: it’s a user-friendly experience designed for the masses, without any of the complexities that define a power-user tool, for better or worse. This is how Apple rolls: they don’t start from a high power-user ceiling and let products trickle down to consumers; they always start from the consumer level and refine, iterate, and extend until products trickle up to power users. This perspective isn’t meant to excuse the (many) current flaws of Siri AI. (More on them below.) It’s just the necessary lens for understanding how Apple is addressing their AI shortcomings in a way that doesn’t betray the company’s soul and design ethos.
There will be plenty more to say about iOS 27, the improved Shortcuts app, Liquid Glass tweaks, and other system enhancements later this year. After all, I have a review to write. Today’s column is merely an opportunity for me to reason through the obstacles I’ve faced with Siri AI and the way I’ve had to re-learn how to think about Siri.
Siri AI: The Good Stuff
You see, I believe my issue is that I’m too agent-pilled and accustomed to products like Claude Code and Codex at the moment. Desktop agents have fundamentally changed what I do as a creator who writes and talks on podcasts but also releases software products for my team and audience. There is no denying that Apple’s new Foundation models powering Siri are a far cry from Fable and Sol, or that they feel like models from two years ago. The AI frontier from the two big labs (and – we have to be honest with the numbers here – probably SpaceXAI and Meta now, too) is in a completely different league at the moment. I spent my first couple of weeks with Siri AI trying to convince myself that I could replace Codex with Siri AI, and that was the wrong approach. There is a potential future in which Siri AI can become a more proactive and capable agent, but that’s not what Apple is shipping this year.
If you, like me, are a heavy Claude or ChatGPT user but are curious about Siri AI, you need to reset your expectations and understand that Apple is going after something else entirely. For starters, the new Siri AI is a dramatically better Siri for typical Siri stuff. The new Siri understands your commands and nuanced requests better because of the LLMs behind it; it can often perform multiple requests in one go (such as setting multiple timers with one command); the new expressive (and customizable!) voices sound great, and they’re terrific at reading and summarizing notifications. Apple’s first advantage compared to other chatbots is right here: only Siri can integrate with the iPhone and iPad to this extent, so even if the Foundation models aren’t as smart as the competition, Siri can do a lot more for most people on their devices because neither OpenAI nor Anthropic have OSes they can control. Claude and ChatGPT are extremely intelligent inside their own apps; Siri AI is intelligent enough for routine tasks that can span an entire operating system.
The other key advantage of Siri AI is its system-wide persistence. In addition to voice mode, there’s now a full-blown Siri app that behaves like a traditional chatbot app, allowing you to revisit threads and pin specific ones at the top; but most importantly, you can now finally invoke the new hybrid Spotlight/Siri AI search UI from anywhere on iOS by swiping down on the Dynamic Island.
Spotlight and Siri have been unified in the same UI, so you can still quickly launch apps and documents via search in addition to asking questions.
The lack of system-wide access to Spotlight on iOS bothered me for years, ever since I started reviewing iOS on an annual basis. Now, search is only a swipe away no matter the app I’m using, and the search box itself is smart enough to understand whether I’m looking for an app to launch or formulating a longer request for Siri AI.
It’s been challenging for me to “undo” advanced habits I’ve developed with agents like OpenClaw and assistants like Codex; I think MacStories readers who fall on the power-user end of the AI spectrum will probably face the same hurdles with Siri AI. However, I’ve been able to identify a variety of areas where Siri AI was faster, nicer, and more comfortable than ChatGPT or Codex Remote for practical, everyday questions.
I recently spent a few days in Gaeta, and as we were walking to dinner one night, we spotted this huge vessel docked in front of the restaurant. Typically, I would have taken a picture, started a new ChatGPT thread, uploaded the image, and asked a question about it. This time, I simply held down the Camera Control button (which now defaults to Siri AI mode in the Camera app) and captured a photo. A few seconds later, Siri AI told me I was looking at the Palinuro, a three-masted barquentine that serves as a training vessel for the Italian Navy – which was spot-on. An interaction that would have taken 20-30 seconds with ChatGPT was reduced to a five-second affair with Siri AI. Even nicer, I was able to ask follow-up questions from Siri AI’s floating overlay as well as find the chat in the Siri app later, where I continued asking questions about the ship’s history and usual locations.
The ability to go from Siri in the Camera to a longer conversation in the dedicated Siri app is one of my favorite aspects of Siri AI.
Improved on-screen awareness and integration with Apple Maps has been another highlight. On our way to Gaeta, Google Maps had us drive through narrow mountain roads that we really didn’t like, even though they arguably saved us some time. For the return trip, I decided to use Apple Maps, but I noticed that it also recommended the same mountain roads. So without leaving the Maps app, I swiped down to invoke Siri and typed:
I wanna go back home (from Gaeta to Rome) but I don’t like this route. It goes through too many mountains. I wanna do the Autostrada as much as possible. Is there any way to maybe add some time to the trip and go slightly further down south to find another Autostrada entrance?
To which Siri responded:
To avoid the mountainous routes and stay on the Autostrada A1 longer, you can head slightly south from Gaeta toward the Cassino entrance or even further south toward Capua before heading north to Rome. This will add some time to your trip but provides a flatter, more straightforward drive on the highway.
Again, spot-on: the Cassino toll booth proved to be the way to go for a more comfortable trip.
A couple more things worth noting here:
- Siri AI didn’t mind my mix of Italian and English in the same request. Even though it’s only officially launching with English support, Siri AI is backed by a large language model – and LLMs are inherently good at multiple languages.
- Siri AI assembled a multi-step route for me, which I opened in Maps, and it was perfect.
After some hiccups in the first two developer betas of iOS 27, Siri AI has also become an efficient way to work with the Reminders app, which I started using as my primary task manager several months ago when I began working on my RemCTL CLI for it. In addition to the usual stuff that Siri could already do in Reminders before, such as creating tasks and fetching items due on the current day, Siri AI – thanks to the new and improved App Intents Apple added to Reminders – can now handle more advanced questions. For instance, I can ask Siri to get tasks belonging to two specific sections of a list in Reminders, and it’ll do it. Claude can also integrate with Reminders on iOS, but since its integration is powered by the old and limited EventKit framework, it can’t be as flexible as the exclusive App Intents integration now available for all apps in Siri AI.
Siri AI can finally show me tasks from sections of lists…too bad it also included a task from another section.
I’ll have plenty more examples to share and analyze in my review of iOS and iPadOS 27 later this year. As things stand right now, my thoughts on Siri AI are converging around this idea: with system-wide access, an exclusive app ecosystem, and good enough performance, Siri AI doesn’t need to be a frontier-level model to be useful to millions of people.
Siri AI: The Bad Stuff
All of this, however, is not to say that Siri AI is perfect. Far from it.
This is beta software, of course, and Apple has time to improve the experience. But I’m afraid that some design choices and intrinsic limitations of Siri AI will remain in place for the next year, leaving us with a product that, despite a two-year delay, still feels very early compared to the likes of ChatGPT, Claude, or Gemini, even in their plain “chatbot” modes.
The biggest issue I’ve encountered is the inconsistency of it all. Very often, the new Siri AI still replies with a generic “Uh oh, something went wrong” error that doesn’t explain what the error was or why it happened. Sometimes, I ask a question via voice, and it errors out, but then a few seconds later, I type the same question in the app, and it’s fine.
Anecdotally speaking, these issues seem to occur more frequently when Siri “thinks” longer for a request, which perhaps suggests Apple needs to optimize the performance of their larger model on Private Cloud Compute. However, the fact that Apple wants to keep things simple compared to their competition isn’t doing them any favors here: in ChatGPT or Gemini, I can know when the model is reasoning for longer, but Siri AI’s interface is a black box. There are no reasoning selectors or hints in the UI at all. That is a fine, Apple-y approach when everything works well; but as soon as something breaks (as often happens with chatbots), the lack of clarity and controls stings.
The entire Siri app is, in fact, a bit of a mess. Its performance is subpar: I’ve noticed frequent stutters when scrolling threads, delays when typing (letters wouldn’t appear on-screen and autocorrect wouldn’t work), and broken ‘Sources’ popups displaying no actual sources for a query.
The results of this query were stale (I was on a trip last week), and the Sources panel for linked emails came up empty.
The app lets you rename and pin threads, which is nice, but it doesn’t offer basic controls such as the ability to select text in a Siri response or create folders for chats. Although the grid view looks good in marketing screenshots, in practice, I had to disable it immediately because I couldn’t quickly parse my threads and find what I was looking for.
Which brings me to indexing. As I noted above, Apple’s advantage compared to other chatbots will be Siri’s access to an on-device index that draws from the user’s apps and personal context. The problem is that I’ve yet to see an example of personal context “enhancing” any of Siri’s answers, and performing actions in or retrieving data from apps has been half broken for me since the very first beta of iOS 27.
I can’t speak about personal context because it has literally never worked in my examples. For apps, my understanding is that third-party ones will need to be specifically updated for iOS 27 in order to work with Siri AI – although some of them seem to work already, but others don’t? Apple requires developers to implement new features of the App Intents framework for Siri AI, and I’m optimistic that those who do will have their apps appear in Siri AI by September. Greg Pierce, the developer of Drafts, has added early support for Siri AI in his app, and I’ve been able to successfully create a note within the app from Siri, which presented a custom UI snippet for Drafts and completed the request in seconds. That was neat.
My problem is that, right now with Apple’s own apps, both the index and Siri’s ability to perform actions are very inconsistent. The assistant hallucinates abilities it doesn’t have, and it frequently just doesn’t work. In the examples below, I wanted to get notes from a specific folder, songs from a playlist, and a link from a note. Siri AI responded with an empty list of notes, said it couldn’t get songs from a playlist, and told me that my note didn’t have any links, respectively. (It did.)
Reminders integration started working for me in iOS 27 beta 3, but it still isn’t perfect. When I ask for tasks due today, Siri AI insists on presenting the same tasks twice, my only fault being that I enabled the integration between Reminders and Calendar:
At one point, I asked Siri to show me my overdue reminders. Siri AI struggled with that: it cut the list of overdue items short, apologized when I pushed back, then did it again anyways. I know that Siri AI is not based on a Gemini model but is rather a Gemini distillation, but I think that if you’ve ever used a Gemini model before, this kind of behavior with tool-calling should be awfully familiar.
Siri AI isn’t a replacement for agentic workflows with other LLMs that can perform multiple actions in one chain of events. Here, for instance, I asked Siri to get my latest screenshot from the Photos app and frame it with my Apple Frames shortcut. Not only did Siri AI not get the most recent screenshot from my library, but the assistant couldn’t perform two actions sequentially. At least, however, it told me; when I repeated a similar question but asked to copy the screenshot to the clipboard instead, Siri first asked me to confirm my action and then changed its mind and said it couldn’t do it.
Searching for content hasn’t been ideal on my end, either. When I asked Siri to find me the latest single by Phoebe Bridgers, its default text response was an EP from two years ago; when I asked via voice, the response was correct. (…Why?) I similarly haven’t been impressed with Siri’s ability to search for messages and emails. Siri AI can reliably find recent texts from the Messages app, but the moment I start going a little further back in time, the system seems to struggle. I wanted to know when we took some time off at MacStories last summer, which I know was mentioned in a MacStories Weekly email that I have in the Mail app. Siri AI could only find a generic mention of John recharging after some time off, but it couldn’t give me an exact date because it did not find the correct email. ChatGPT Work did it in one minute and gave me a full breakdown of the weeks we took off.
All of this begs the question:
Is Apple’s on-device index a solid technological foundation or not? Is this system actually going to work at scale, for users with dozens of apps installed, each donating their data to the index, perhaps spanning multiple years of content? And can the cloud models – which are not using MCP but appear to be based on a plain JSON schema for structured data – make sense of it all?
My early tests haven’t been encouraging, but we have until September to find out.
The Trickle-Up
A trickle-up strategy cuts both ways: it gives Apple an opportunity to start simple and refine over time, but it also means that you, the user, are never given any more control than what the product allows for. As a result, Siri AI can be magical when it works; when it doesn’t, it feels like a mystery.
I can’t say whether I’m optimistic that Apple will get all of this to work in time for the fall or not because they don’t have the greatest track record in AI. I’m willing to give them the benefit of the doubt since the product itself is genuinely interesting and different from any other chatbot on the market. I want Siri AI to work, and if Apple can deliver on their vision, I’m convinced that it’ll spell trouble for OpenAI and ChatGPT. (Let’s face it: it’s the product to beat here, both in and outside of court.)
Siri AI permeates iOS 27, and that’s a threat to OpenAI and the hundreds of millions of users they have using ChatGPT for free with GPT-5.5 Instant. I don’t think Apple Foundation Models are as good as GPT-5.5 Instant, but Siri AI is the more ergonomic and integrated product. When the underlying chatbot and its world knowledge capabilities are good enough, and they can also be invoked via voice, text, the Camera app, context menus, or keyboard shortcuts, why would I open a siloed chatbot when I can use Siri AI and get a comparable answer more comfortably? If you’re a casual user of ChatGPT and do not pay for it, I think Siri AI can be a very compelling product that provides similar answers and, unlike OpenAI’s chatbot, integrates with the iPhone apps you already use. I don’t think it’s a coincidence that OpenAI is now following in Anthropic’s footsteps to monetize the business and enterprise markets rather than the consumer one.
At the same time, my concern is that we may be collectively assuming that “normal people” won’t see the differences between the capabilities of ChatGPT and Siri AI. In this industry, we have a tendency to sell “normal people” short and paint them as some perplexed bunch of occasional smartphone users who somehow passively accept any technology that is thrown at them. I strongly disagree with that. Maybe those people don’t care about ChatGPT Work, Codex, or Fable (yet?), but they can tell when an AI assistant is useful and when it’s not. People will compare the utility of ChatGPT to Siri AI, and I’m concerned that Apple’s 1.0 product will feel like it’s too little, too late – especially since Siri AI will be launching in select regions and in English only.
In the AI scene, companies move fast and break things. Apple needs to move fast without breaking anything, anymore. That’s a tough challenge, but here we are.
