CarPlay apps have grown far beyond maps, music and basic messaging. More than 120 popular iPhone apps now offer some form of support for Apple’s in-car platform, giving drivers access to navigation, podcasts, audiobooks, sports, communication, electric vehicle charging, parking, food ordering and newer AI assistants.

Not every compatible app places its full iPhone interface on the dashboard. CarPlay uses simplified layouts, voice controls and restricted features designed to reduce distractions. Some apps show lists and buttons, while others operate mainly through Siri or audio playback.

The larger catalog nevertheless changes what CarPlay can do. It is becoming a controlled extension of the iPhone rather than a small collection of driving utilities.

CarPlay Apps Cover More of the Journey

The first generations of CarPlay concentrated on a small set of familiar activities: choosing a route, making a call, sending a message and playing audio. Those functions remain central, but Apple has gradually opened additional categories to developers.

CarPlay apps can now help drivers find parking, locate fuel, identify EV charging stations, order food for collection and complete certain driving-related tasks. Automakers can also build apps that control supported vehicle features without forcing the driver to leave the CarPlay interface.

Apple continues to limit which app categories qualify. A social network, game or ordinary shopping app cannot simply reproduce its iPhone screen on the dashboard. Developers must use Apple’s CarPlay frameworks and present only functions considered suitable for the car.

The approach explains why the available catalog can feel both extensive and restrained. More than 120 apps may be compatible, but the dashboard does not become a crowded copy of the App Store.

Navigation Remains the Starting Point

Apple Maps is built directly into CarPlay and provides turn-by-turn guidance, traffic information, estimated arrival times and destination suggestions based on information from the iPhone.

Drivers can also choose popular alternatives including Google Maps and Waze. Each service brings a different combination of traffic data, route preferences, incident reporting and familiar saved locations.

Other navigation and travel options include HERE WeGo, TomTom GO Navigation, Sygic GPS Navigation, Gaia GPS and specialist apps designed for trucks, motorcycles or outdoor routes.

The strongest choice usually comes down to habit and regional coverage. A driver already using Google Maps or Waze on iPhone can continue using saved destinations and preferences inside the car. Apple Maps benefits from tighter system integration, including Siri requests, Calendar suggestions and Apple Watch directions.

CarPlay allows several navigation apps to appear in the Dashboard layout, where mapping can share the screen with media controls and other useful information.

Music, Radio and Podcasts Dominate the Catalog

Audio remains the largest CarPlay app category because it suits an environment where users should spend as little time as possible looking at the screen.

Apple Music, Spotify, YouTube Music, Amazon Music, Deezer, Tidal and Pandora provide access to large music libraries. Radio services such as TuneIn, iHeartRadio and SiriusXM add live stations, news, sports and talk programming.

Podcast listeners can use Apple Podcasts, Overcast, Pocket Casts, Castro and Spotify. Audiobook options include Apple Books, Audible, Audiobooks.com and Bookmate.

The CarPlay versions usually emphasize large buttons, recent listening, saved libraries and voice search. More detailed account management remains on the iPhone.

Siri can start playback without requiring users to browse through several menus. The experience is safer and often faster when the request includes the service and content, such as asking Siri to play a specific playlist through Apple Music or Spotify.

Messaging Is Becoming More Visual

Messages has long allowed CarPlay users to hear incoming texts and dictate replies through Siri. Third-party messaging services have expanded the same general idea.

WhatsApp now offers a fuller CarPlay experience that can display recent chats, calls and favorite contacts while keeping message composition centered on voice. Other supported communication apps include Telegram and selected business messaging services, depending on region and app version.

CarPlay does not display long text conversations like an iPhone. Siri reads messages aloud, and users can dictate a response. Visual elements remain limited so the dashboard does not become a scrolling chat screen.

Phone and supported calling apps also provide simplified access to contacts, recent calls and favorites. Meeting services can support audio participation, but video remains unavailable while driving.

AI Assistants Enter CarPlay

AI assistants represent one of the newest CarPlay app categories. ChatGPT, Perplexity and Grok have introduced CarPlay support, allowing drivers to interact through voice without handling the iPhone.

These apps can answer general questions, explain subjects, brainstorm ideas or continue voice conversations. Their usefulness in a car is different from navigation or music. They provide a hands-free knowledge interface during a commute or long trip.

Google Meet and other communication apps have also expanded their in-car presence, emphasizing audio conversations rather than video.

AI responses should not replace directions, emergency information or vehicle warnings. They can also produce inaccurate answers, particularly when asked about rapidly changing road conditions. Apple Maps, official traffic services and the vehicle’s own systems remain the appropriate sources for driving decisions.

The arrival of AI assistants still marks a meaningful expansion. CarPlay is no longer limited to commands with predefined outcomes. Drivers can now hold longer spoken interactions through supported services.

Parking, Fuel and EV Charging Become Easier

Practical travel apps can reduce the need to handle an iPhone after arriving near a destination.

Parking services can help locate garages, compare availability or start a parking session. Availability varies by city, but apps from services such as SpotHero, EasyPark and ParkWhiz may offer CarPlay functions in supported markets.

Fueling apps can guide drivers to compatible stations and, in some cases, prepare or authorize payments. EV charging apps can locate chargers, show connector availability and begin navigation to a selected station.

ChargePoint, PlugShare, Electrify America and other charging networks provide different levels of CarPlay integration. Drivers should confirm that their preferred service supports the platform in their country and app version.

Food-ordering support is more restricted. Compatible apps are designed around quick pickup tasks rather than browsing complete menus while the vehicle is moving.

Sports and Driving Information Join the Dashboard

Sports apps are also finding a place in the car. Apple Sports and selected third-party services can provide scores or spoken updates without requiring drivers to follow a live visual feed.

Audio broadcasters already make sports a major part of CarPlay through radio and podcast services. Dedicated sports support makes it easier to reach a favorite team or competition directly.

Driving-task apps can handle functions such as recording mileage, managing road trips or communicating with fleet systems. These experiences are generally built for narrow purposes and use simplified controls.

Automaker apps form another category. Depending on the vehicle, they can expose controls for radio stations, climate functions, drive modes or other systems through CarPlay. Support is determined by the manufacturer and may differ between models.

How to Find CarPlay Apps on an iPhone

Compatible apps installed on the iPhone normally appear in CarPlay automatically. Users can decide which ones remain visible and change their order.

To organize CarPlay apps:

Settings > General > CarPlay > select the vehicle > Customize

Apps can be added, removed or rearranged from this screen. Removing an app from the CarPlay layout does not uninstall it from the iPhone.

An app may not appear when its developer has not enabled CarPlay support, the feature is unavailable in the region or the app needs to be updated. Some services also require an active subscription or account.

The safest layout keeps frequently used navigation and audio apps near the first page. Less essential services can remain farther back or be removed to reduce dashboard clutter.

More Apps Do Not Mean More Screen Time

The value of 120 CarPlay apps is not having 120 icons inside the car. It is having a useful service available when a particular trip requires it.

A daily commute may involve only Maps, Music and Messages. A road trip may add charging, parking, audiobooks and weather information. A workday could involve audio meetings and mileage tracking.

CarPlay’s restrictions remain part of its appeal. Apps are expected to simplify their interfaces, support voice interaction and limit detailed visual tasks. The system should reduce the temptation to use the iPhone rather than reproduce every distraction on a larger screen.

As iOS 27 expands capabilities for audio, communication, navigation and driving-task apps, the catalog is likely to keep growing. The more useful evolution will be deeper integration with the Dashboard, Siri and vehicle controls—not simply another row of icons.

The post CarPlay Apps: 120 Popular Options for Your Car appeared first on AppleMagazine.

ARK augmented reality describes a form of spatial interaction in which artificial intelligence does more than place digital objects in the physical world. It uses knowledge from foundation models to understand unfamiliar scenes, generate useful information and adapt its response to the person, task and environment.

The concept comes from a 2023 research paper titled “ArK: Augmented Reality with Knowledge Interactive Emergent Ability.” Its authors proposed a system that transfers knowledge from large foundation models into new physical and virtual environments. Instead of training an AI agent separately for every room, object or activity, ArK uses existing knowledge memory to interpret what it sees and generate appropriate 2D or 3D content.

Traditional augmented reality places information over reality. ARK augmented reality tries to understand reality before deciding what should appear.

That distinction creates a compelling direction for Apple. Vision Pro already blends digital content with physical space. Apple Intelligence adds language, image understanding and personal context. Visual Intelligence lets users look at objects, text and scenes before asking for information. Siri AI adds a conversational layer. ARKit, RealityKit and visionOS provide the spatial foundation.

Apple now has many of the components required to build a knowledge layer over the physical world.

ARK Augmented Reality Goes Beyond Digital Overlays

Most familiar augmented reality experiences are relatively fixed. A furniture app places a digital sofa in a room. A navigation app displays arrows over a street. A museum app identifies an artwork. A repair app shows where a component belongs.

These experiences can be useful, but they usually depend on predefined content and rules. The system recognizes a known object or location, then presents prepared information.

ARK augmented reality proposes something more adaptive. A knowledge-enabled system could enter an unfamiliar environment, interpret what is present and generate assistance based on a broader understanding of objects, relationships and possible actions.

A user looking at a complicated electrical panel would not only see labels. The system could identify the panel type, explain the purpose of each section, compare the arrangement with standard configurations and warn the user not to touch dangerous components.

A student examining a machine could ask how it works and receive a spatial explanation attached to its real parts. A surgeon could review anatomical information positioned around a medical model. A technician could receive repair guidance even when the exact equipment had not been included in a previous training dataset.

The display becomes less like a floating screen and more like an informed interpretation of the environment.

Why Apple Is Positioned to Build It

Apple’s advantage would not come from inventing every part of ARK augmented reality. It would come from combining hardware, software, artificial intelligence and personal context into one controlled ecosystem.

Vision Pro already understands rooms, surfaces, hands, eyes and objects well enough to place digital content convincingly in physical space. Its cameras and sensors continuously map the environment while visionOS manages windows, volumes and immersive experiences.

Apple Intelligence provides another layer. Foundation models can interpret language, summarize information, generate content and connect requests with app actions. Visual Intelligence can identify text, images and real-world objects. Siri AI can act as the conversational interface.

The Apple ecosystem also provides personal context that a generic AR platform may not have. Calendar knows the user’s schedule. Maps understands location. Photos contains visual history. Notes and Mail hold project information. Health contains personal trends. Home understands rooms, accessories and automations.

An Apple-built knowledge layer could combine the environment in front of the user with the information already available across trusted devices and apps.

A person preparing for a meeting could look at a conference room and see the agenda, participant names and relevant documents arranged around the table. A traveler could look across a train station and receive directions connected to the correct platform, departure time and digital ticket. A homeowner could examine a room and see live information from temperature, air-quality and energy sensors.

The physical environment becomes the interface.

Vision Pro Is the Laboratory

Vision Pro is the obvious development platform for this idea because it already offers the cameras, displays, sensors and processing required for advanced spatial understanding. Its size and price limit broad adoption, but those same characteristics allow Apple and developers to test experiences that would be harder to build first on lightweight glasses.

ARK augmented reality on Vision Pro could become especially useful in enterprise environments. Apple already promotes the headset for employee training, product design, field service, collaboration and specialized visualization.

A worker could enter an unfamiliar facility and receive contextual instructions attached to real equipment. An engineer could inspect a physical prototype while design changes, performance data and maintenance history appear around it. A new employee could learn a workflow through spatial guidance generated from company manuals and operational knowledge.

The system would not need to display every available fact. It would need to understand which information fits the current task.

That is where AI knowledge becomes more valuable than a traditional AR overlay. Too much information can be as disruptive as too little. A strong system should filter, prioritize and explain rather than cover the room with floating labels.

The iPhone Could Bring ARK to More People

Vision Pro may be the development environment, but iPhone could provide the scale. The iPhone already combines cameras, LiDAR on Pro models, location, motion sensing, Visual Intelligence and Apple Intelligence.

An iPhone-based ARK experience would be less continuous because users would need to hold up the device. It could still deliver useful knowledge interaction without requiring a headset.

A user could point the camera at a plant and receive care guidance based on its species, visible condition, local weather and placement in the room. Someone assembling furniture could receive generated guidance positioned over the actual parts. A shopper could compare products by looking at them rather than manually searching for each model.

The difference from ordinary visual search would be interaction. The user could ask follow-up questions, change the goal and let the system update the visual guidance.

Future glasses could eventually make the experience persistent. The iPhone would help Apple develop the intelligence, privacy controls and app ecosystem before lightweight eyewear becomes ready.

A World That Explains Itself

The most ambitious version of ARK augmented reality is a world in which information is attached to objects, places and situations only when requested or needed.

A city could become understandable without searching through maps, review sites and separate transit apps. Buildings could reveal history. Streets could explain temporary closures. Restaurants could surface reservations, dietary options and accessibility details. Public transport could show the correct entrance and platform.

Inside a home, Apple’s knowledge layer could explain energy use, identify maintenance problems and guide repairs. In a classroom, physical models could become interactive lessons. In healthcare, patients could receive visual instructions for approved home procedures or medication devices.

The experience would depend on context rather than menus. The user looks, asks and receives information positioned where it belongs.

This is the transition from augmented reality as decoration to augmented reality as understanding.

Privacy Will Decide Whether It Works

A knowledge layer capable of understanding the physical world also creates serious privacy questions. The system may see homes, workplaces, documents, faces, screens and private conversations. The more context it receives, the more useful it becomes. The same access can also make it invasive.

Apple’s privacy architecture could become one of its strongest advantages. On-device processing would allow some scene understanding without sending continuous camera feeds to external servers. Private Cloud Compute could handle more complex requests while preserving stricter controls than an ordinary cloud AI service.

Apple would also need visible controls over what is analyzed, remembered and shared. A user should know when the system is interpreting the environment and whether information is temporary or retained. Workplaces and public spaces would need rules for recording, identification and sensitive data.

ARK augmented reality cannot become socially acceptable if people feel that nearby devices are constantly cataloging them.

The successful version would behave less like surveillance and more like intentional assistance. The user asks for understanding. The system processes only what is needed. The knowledge disappears when the task ends unless the user chooses to save it.

Developers Could Build Knowledge Worlds

Apple would not need to create every knowledge experience itself. visionOS, ARKit, RealityKit and App Intents could let developers connect specialized knowledge with physical environments.

A medical company could build guidance for approved equipment. A manufacturer could create spatial maintenance systems. A university could attach interactive explanations to laboratories and museums. A retailer could create product comparisons based on inventory and customer preferences.

Apple could provide the shared intelligence layer: scene understanding, object recognition, language interaction, privacy permissions and spatial presentation. Developers would provide the trusted domain knowledge.

This division would be essential. General AI can explain many things, but professional environments require verified information. A generated answer about a historical building has different consequences from an answer about industrial machinery or medical treatment.

Apple’s platform could distinguish between general knowledge and certified domain sources, allowing users to see where information comes from before acting.

From Spatial Computing to Contextual Computing

Apple describes Vision Pro as a spatial computer because digital content can occupy physical space. ARK augmented reality suggests the next progression: contextual computing.

A spatial computer knows where digital content is placed. A contextual computer understands why the content is useful in that location, what the user is trying to accomplish and which knowledge should appear.

That would connect several Apple strategies that currently look separate. Vision Pro supplies spatial awareness. Apple Intelligence supplies reasoning and generation. Siri AI supplies conversation. Visual Intelligence supplies real-world understanding. The ecosystem supplies personal context.

Together, they could create a system that does not wait for users to open the correct app and search through the correct menu. The environment itself becomes the starting point.

Apple’s opportunity is to make that interaction restrained rather than overwhelming. The company does not need to cover reality with digital noise. It can use design, privacy and contextual intelligence to make information appear only when it improves the moment.

ARK augmented reality offers a useful description of that future. Reality remains visible. Knowledge becomes interactive. The computer begins to understand the world in front of the user instead of asking the user to translate everything into a search box.

The post ARK Augmented Reality Could Build Apple’s Knowledge Layer appeared first on AppleMagazine.

PrismML AI compression could give Apple a way to place far more capable artificial intelligence directly inside the iPhone. The Caltech spinout says it reduced a 27-billion-parameter model from approximately 54GB to less than 4GB, small enough to run locally on an iPhone 17 Pro.

That represents a reduction of about 93%, but the more useful number may be memory efficiency. PrismML says its technology can use up to 15 times less memory than conventional versions of the same model. Apple has reportedly held early discussions with the startup about possible uses for the technology.

Neither company has announced a partnership, acquisition or product plan. PrismML’s claims also need to be judged through independent testing, sustained performance and the compromises introduced by heavy compression. Even so, the demonstration points directly at one of Apple’s largest AI challenges: fitting stronger models inside devices without destroying battery life, consuming too much memory or sending every complex request to the cloud.

PrismML AI Compression Changes the Size Problem

Large AI models are difficult to run on phones because their parameters require substantial storage and working memory. A standard model may perform well in a data center equipped with powerful accelerators, large memory pools and constant electricity, then become impractical inside a device designed to last all day on one battery.

PrismML approaches that problem by representing model weights with far fewer bits. The startup has developed what it calls Bonsai models, including 1-bit versions designed to preserve much of the original model’s capability while sharply reducing size and energy use.

The reported iPhone demonstration used a compressed version of Alibaba’s Qwen model with 27 billion parameters. That is far larger than the compact language models normally associated with smartphones. Running it locally suggests that model size may no longer be controlled only by the number of parameters. How efficiently those parameters are represented becomes just as relevant.

Compression is not new. Developers already use quantization, pruning and other methods to make models smaller. PrismML’s claim is that its approach pushes that process much further while retaining useful reasoning and language performance.

That claim is exactly why Apple would be interested.

Why Siri AI Needs Smaller Models

Apple’s AI strategy depends on dividing work between the device and the cloud. Simpler Apple Intelligence requests can run locally, while more demanding tasks may move to Private Cloud Compute. That hybrid structure allows Apple to offer stronger capabilities without forcing the iPhone to carry every model it may ever need.

The cloud layer, however, introduces cost, latency and availability requirements. A request must leave the device, reach a server, be processed and return. Apple has designed Private Cloud Compute around strong privacy protections, but local processing remains faster and easier to explain.

A larger on-device model could improve Siri AI’s language understanding, reasoning and ability to complete multi-step tasks without a network connection. It could also reduce the number of requests sent to Apple’s servers.

That does not mean cloud processing would disappear. Server models can remain larger and support especially demanding requests. PrismML AI compression could instead move the dividing line. Tasks that currently need Private Cloud Compute might become possible directly on a future iPhone.

The benefits could include quicker responses, stronger offline operation and less server demand as Apple Intelligence reaches more users.

Privacy Fits Apple’s Preferred Direction

On-device processing has always been central to Apple’s AI positioning. Personal information can remain on the iPhone rather than moving through a conventional cloud service. The device can interpret a request, use local context and produce an answer without exposing the underlying data beyond the hardware.

A model capable of handling more work locally would reinforce that approach. Siri AI could potentially understand messages, notes, schedules or onscreen content while reducing the need to transfer information elsewhere.

Apple already uses Private Cloud Compute when local processing is insufficient, and the company has built significant safeguards around that system. Yet every task completed on the iPhone removes one additional processing step.

Privacy is not the only advantage. Local models can continue operating when connectivity is poor or unavailable. That could help Siri AI during flights, rural travel, crowded events or other situations where cloud access becomes unreliable.

A capable offline assistant would also feel more like part of the operating system and less like a remote service accessed through an interface.

The iPhone Still Has Physical Limits

Shrinking a model to less than 4GB does not automatically make it ideal for everyday iPhone use. The model must also run quickly enough, avoid excessive heat and leave enough memory for iOS and active apps.

A technical demonstration may complete tasks successfully while consuming more energy or time than users would accept from Siri. Apple would need to optimize the model for its Neural Engine, memory architecture and software frameworks rather than simply loading PrismML’s existing build onto every supported device.

Storage is another consideration. A model occupying several gigabytes would compete with apps, photos, offline media and system files. Apple could reserve more storage for intelligence features, deliver models selectively or use several specialized models instead of one large general system.

Battery use may create the hardest constraint. An AI model can fit in memory and still require too much sustained computation for frequent mobile use. The ideal system needs to be small, fast and efficient enough to disappear into normal iPhone behavior.

Apple’s chip design gives it an advantage here. The company controls the processor, Neural Engine, operating system and AI software stack. PrismML could provide the compression technique while Apple handles the deeper hardware integration.

Better AI Without Replacing the Cloud

The strongest use of PrismML’s technology may not be putting one enormous model on every iPhone. Apple could use compression across a family of models designed for different devices and tasks.

A smaller model could handle routine language requests. A more capable local model could be downloaded only to recent Pro devices with sufficient memory. Specialized models could support writing, image generation, app actions or Visual Intelligence. Private Cloud Compute could remain available when the request exceeds local capability.

That would give Apple more flexibility than an all-local or all-cloud design. Each device could carry the intelligence appropriate for its chip, memory and battery capacity.

The approach could also help Macs, iPads and future home products. A compressed model may run more comfortably on a MacBook Air, HomePod or smart home hub without requiring constant server access. Apple could scale the same intelligence foundation across products while adjusting model size to the hardware.

This is especially relevant as Siri AI moves beyond answering questions. App actions, personal context and ambient smart home control require intelligence that remains available throughout the day. Lower memory and energy requirements could make those experiences more practical.

Compression Always Includes Trade-Offs

A 93% reduction is a striking headline, but compression can affect output quality. A smaller representation may lose precision, weaken reasoning or struggle with uncommon information. The real test is not whether the model runs. It is whether it performs well enough across the tasks Apple expects Siri AI to handle.

PrismML says its technology preserves strong performance compared with full-precision models. Apple would still need extensive evaluation across languages, safety categories, tool use and personal-assistant scenarios.

Reliability is especially sensitive for an operating-system assistant. A model used for casual brainstorming can tolerate occasional weakness. A model handling messages, appointments, directions or app actions needs a higher level of consistency.

Apple may therefore use aggressive compression selectively. Some tasks can accept a smaller model, while others may remain on a higher-quality server model. The user would not need to know which model is active as long as the response remains fast and dependable.

Apple Wants the Technology, Not Necessarily the Company

Reports indicate Apple has spoken with PrismML, but early conversations can lead in several directions. Apple could license the startup’s technology, work on a technical integration, hire members of the team or explore an acquisition.

The company has a long history of purchasing smaller firms for specialized technology and engineering talent. Model compression would fit that pattern because it supports Apple’s existing AI strategy rather than creating a separate consumer product.

PrismML could also remain independent and provide its tools to multiple hardware companies. Its technology has potential uses across phones, computers, robotics, vehicles and industrial equipment where cloud access is expensive or unreliable.

Apple’s interest alone gives the startup attention. The larger significance is that efficient models are becoming as valuable as larger ones. The AI industry spent years treating scale as the primary route to improvement. Mobile computing forces a different question: how much intelligence can fit inside the power and memory limits of one personal device?

A Smaller Model Could Make Siri Feel Larger

Apple does not need to place the biggest available model on an iPhone. It needs a model capable enough to improve the interactions users repeat every day.

PrismML AI compression could help Siri understand more context, complete more requests locally and respond without waiting for a server. It could strengthen Apple’s privacy argument while reducing the infrastructure load created by millions of AI-enabled devices.

The technology remains early, and a startup demonstration is not the same as a shipping Apple feature. The 93% figure will mean little if quality, battery life or speed suffer under daily use.

But the direction fits Apple unusually well. The company has spent years designing smaller, more efficient hardware systems that perform beyond their apparent limits. PrismML is proposing a similar strategy for AI models.

If the startup’s claims hold up, the next major Siri improvement may not come from sending a larger model into the cloud. It may come from fitting one into the iPhone without making the iPhone feel the weight.

The post PrismML AI 93% Compression Could Give Siri a Major Boost appeared first on AppleMagazine.

Siri Wolfram helped define the original promise of Apple’s voice assistant. When Siri debuted on the iPhone 4S in 2011, it could answer factual and computational questions without sending users through a list of search results. Ask about a mathematical calculation, scientific quantity, historical statistic or unit conversion, and Wolfram Alpha could provide a structured answer.

That partnership gave early Siri something many modern AI assistants still struggle to guarantee: a source designed to compute answers rather than produce plausible sentences. Wolfram Alpha was not a chatbot. It was a computational knowledge engine built around curated data, symbolic mathematics and algorithms.

Siri AI enters a far more ambitious era. Apple now wants its assistant to hold natural conversations, understand personal context, interpret images, find information across apps and complete actions. Yet the old Siri Wolfram relationship remains useful for understanding what Apple gained, what was lost as assistants became more conversational and why verified computation may become even more valuable in the generative AI age.

Siri Wolfram Was Built Around Answers

The original Siri Wolfram integration reflected a straightforward idea: users wanted direct answers without manually searching, opening websites and comparing sources.

Wolfram Alpha was particularly effective for questions with a computable result. It could solve equations, compare financial data, convert measurements, retrieve astronomical information, calculate dates and present structured scientific facts. Siri provided the voice interface, while Wolfram supplied the knowledge engine behind selected responses.

A user could ask how many days remained until a date, calculate a percentage, compare populations or request information about a mathematical concept. Siri translated the spoken request and delivered the result in a format suitable for the iPhone.

The experience was narrow compared with modern generative AI, but it had a valuable discipline. Wolfram Alpha attempted to determine an answer from structured information. It did not need to improvise an explanation every time.

That made Siri Wolfram especially useful for mathematics, science, education and quick factual calculations. The assistant could sound intelligent because it was connected to a system built to compute.

What Siri Wolfram Alpha Could Do Well

Siri Wolfram Alpha worked best when the request had a definable structure. Arithmetic, percentages, conversions, equations and statistics were natural categories. The system could also retrieve information about weather history, geography, nutrition, astronomy, transportation and other data-rich subjects.

The integration helped make Siri feel different from ordinary web search. Instead of showing several links, the assistant could present one answer with supporting figures or charts.

That approach had limitations. Wolfram Alpha could only respond effectively when it understood the request and had the relevant data or computational method. It was not designed for open-ended conversation, personal writing, emotional nuance or the countless informal questions users ask assistants.

Siri also relied on several external services, with Wolfram Alpha handling only certain knowledge categories. The experience could therefore feel inconsistent. One request produced a polished computational response, while another returned a web search or a limited canned answer.

Still, the partnership demonstrated a principle Apple has never fully abandoned: the best assistant does not need to create every answer itself. It needs to route each request to the system most qualified to handle it.

Generative AI Changed the Definition of an Assistant

Modern AI assistants are expected to do far more than retrieve facts. Users want them to explain ideas, write messages, summarize documents, analyze images, brainstorm projects and remember the direction of a conversation.

Siri AI is Apple’s response to that expanded expectation. Powered by Apple Intelligence and Apple Foundation Models, the new assistant can handle open-ended requests and continue natural conversations. It can use personal context from supported apps, understand onscreen content and connect requests with app actions.

This is a dramatic expansion from the Siri Wolfram era. The old model was largely transactional: ask a question, receive an answer. Siri AI is intended to interpret intent, understand relationships between information and help complete a larger task.

A user may ask Siri AI to find a restaurant recommendation buried in Messages, locate a hotel confirmation in Mail and add the details to a travel note. That request involves personal context and several system services rather than one public factual answer.

The assistant becomes less like a talking search box and more like an operating-system layer.

Conversation Creates a Reliability Problem

Generative AI makes assistants more flexible, but it also introduces uncertainty. A language model can produce an elegant response even when the underlying information is incomplete or wrong. The same fluency that makes the assistant enjoyable can make an inaccurate answer sound convincing.

The old Siri Wolfram model avoided much of that risk within its strongest categories. A mathematical calculation came from a computational engine. A unit conversion followed a defined relationship. A data query could be tied to structured information.

Siri AI needs both capabilities. It needs conversational intelligence for requests that cannot be reduced to a formula, while retaining access to reliable tools for tasks that demand precision.

Apple can use specialized systems for calculations, calendars, maps, weather, app actions and personal information rather than asking one generative model to invent every result. Foundation models can understand the request, then direct the work to an appropriate source.

That structure would preserve the strongest lesson from Siri Wolfram: intelligence also means knowing when not to guess.

Personal Context Is the New Knowledge Engine

Wolfram Alpha gave Siri access to public computational knowledge. Siri AI adds a second knowledge source: the user’s own information.

Apple says Siri AI can understand personal context across messages, emails, photos, notes and other supported content. It can help retrieve a detail without requiring the user to remember which app contains it.

This changes the assistant’s value. Wolfram Alpha could explain the distance between two cities. Siri AI could find the hotel reservation, identify the arrival time and retrieve the message where a friend recommended a nearby restaurant.

That personal layer also requires stricter privacy. Apple uses on-device processing for many requests and Private Cloud Compute when more processing power is required. The company has designed the system so personal data does not become part of an ordinary cloud AI profile.

Siri Wolfram answered questions about the world. Siri AI is being designed to answer questions about the user’s place within it.

Apps Complete the Transition

Siri AI also moves beyond knowledge by connecting directly with apps through App Intents. Developers can expose content and actions so the assistant can help users complete tasks instead of only describing how to do them.

That could include editing a photo, retrieving a document, starting a workout, updating a task or sending information through a supported app. Onscreen awareness adds another route, allowing users to ask about content already visible without explaining every detail again.

Wolfram Alpha remains valuable because some questions require specialized computation. App Intents extend the same routing philosophy into actions. Siri does not need to contain every capability internally. It needs to understand the request and connect it with the correct tool.

This may become the defining structure of Siri AI: one conversational interface backed by models, apps, services, personal context and specialized knowledge engines.

The Old Siri Still Has a Lesson for the New One

Siri Wolfram belonged to a more limited assistant era, but its underlying approach was disciplined. The system used a specialized source for questions that demanded structured knowledge and computation.

Siri AI has a wider assignment. It must converse naturally, interpret images, understand personal information and complete actions across Apple devices. That breadth can make Siri far more useful, but only if Apple preserves dependable pathways for calculations and factual tasks.

The future assistant should not choose between Wolfram-style precision and generative flexibility. It should combine them. A conversational model can understand what the user wants. A computational engine can provide the numerical answer. Personal context can supply relevant details. App Intents can complete the task.

The old Siri Wolfram integration showed that a voice assistant could make expert knowledge accessible through one spoken request. Siri AI now aims to place conversation, personal context and action around that foundation.

The assistant has become larger, more personal and more capable. Its credibility will still depend on something the 2011 version understood well: when a question has a correct answer, intelligence should calculate before it speaks

The post Siri Wolfram Built a Powerful Foundation for Siri AI appeared first on AppleMagazine.

Roblox’s new AI game creation tool Build lets iPhone users turn a text prompt into a playable game. Give it a try!

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Skip manual billing with this lifetime deal on AI Invoice Maker. It creates pro invoices in seconds and manages billing across Apple devices.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

A new report says OpenAI wants to produce a super-smart, "humanlike" portable speaker that gets to know you (and actually moves).

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Apple’s trade-secrets lawsuit against OpenAI carefully avoids naming Jony Ive, but discovery dosen’t care what Cupertino wants to keep quiet.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Anyone can download the iOS 27 public beta, which brings new Apple Intelligence tools. Grab it now and sign up for the Siri AI waitlist.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Get an AI tool that brings top AI models like ChatGPT, Mistral AI and more together in one interface. Enter 1minAI, the all-in-one AI tool.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Apple sued OpenAI, alleging the AI company stole trade secrets from former employees to accelerate its push into AI-powered hardware.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

Apple is reportedly talking to a startup that claims it squeezed a massive AI language model onto an iPhone.

(via Cult of Mac - Your source for the latest Apple news, rumors, analysis, reviews, how-tos and deals.)

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.

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.

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.

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 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.

When Fable 5 returned last week, I knew exactly what to throw at it. In February, I started a project out of frustration that likewise ended in frustration, so I put it on the shelf and waited. Five months later, Fable 5 was released, and I knew it was time to finish Editor, a single-view diffing tool for writers rather than developers.

At MacStories, we all write in Markdown, and we’ve used GitHub to share and sync changes among team members since 2015. GitHub is primarily a developer tool, but it’s a fast, reliable way to share our Markdown-formatted article files, too.

We use GitHub the most for the Club MacStories newsletters. Every week, Federico, Devon, Jonathan, and I work on sections for MacStories Weekly and save them to a GitHub repo. That allows any of us to sync the sections locally for reading, editing, and assembling the issue.

The trouble is that as great as Markdown text editors are to write and GitHub is for versioning and syncing, there isn’t a good way to view the changes someone has made to a document. I know because I’ve been looking for a solution for a long time. Some Markdown apps like iA Writer and Bear support versioning or backups, but I’ve yet to find a text editor that can visualize changes made by someone else based on a document’s Git history.

Of course, developers have many ways to track changes to code, including GitHub Desktop, Kaleidoscope, and Git Tower. Code is just text, so those apps can be used by writers, too. However, the process of writing and editing prose is fundamentally different from code. I’ve tried the apps above and others, and it’s just too hard to track changes in the formats development tools use.

We wouldn’t have stuck with GitHub as long as we have if it didn’t work, but that hasn’t made the friction of reviewing changes any less frustrating, especially on Fridays when we send MacStories Weekly. That’s when I had the idea for Editor. I was trying to parse some changes Devon had made to one of my stories with GitHub Desktop, and the friction finally got to me.

One obvious problem was the side-by-side document view many code diffing tools use. I wanted more detail than most diffing tools offer, but in a single, readable view, so I could skim through changes quickly.

Most agent-assisted projects benefit from some up-front research and planning. I knew what I wanted would sink or swim on the design, not the app’s underlying Markdown viewer, so I spent time researching systems for visualizing document edits.

That’s when I came across Upwelling, a multi-author project from Ink & Switch that describes itself as “an independent research lab exploring the future of tools for thought.” In their research paper, the authors described my exact problem:

Unfortunately, version control tools like Git, which are designed for software development, do not suit the needs of writers. Git cannot compare or merge files from WYSIWYG editors such as Microsoft Word… and graphical user interfaces for Git are cluttered with complex concepts such as commit hashes and visualizations of non-linear branching and merging histories.

Ink & Switch’s solution, a prototype collaborative text editor, wasn’t what I wanted to build, but the research behind it was full of interesting ideas that helped me settle on several principles for what would become Editor:

• Document changes needed to be visible in a single view that carefully balanced highlighting changes with readability;
• A writer should be able to instantly switch from the marked-up version of their document to the clean original and edited final version;
• Changes needed to be categorized by filterable types like punctuation, word choice, capitalization, insertions, and deletions to reduce clutter in heavily edited documents;
• Change types would be color coded using a side rail system inspired by maps of London’s tube system;
• Navigating among individual edits needed to be done by simple j/k keyboard input; and
• Global document navigation should employ a mini-map of a document’s edit regions (a feature borrowed from developer IDEs like Xcode) to make it easy to jump from one area of a document to another.

With those choices made, I got busy in Claude Code and came up with a proof of concept quickly, but sadly, these were the days of Claude Opus 4.6, which wasn’t nearly as good at design as today’s models. What I wanted was possible, but what I had was a mess.

As it turns out, designing track changes that are accurate but readable is hard. For example, does changing “day” to “date” replace one word with the other or substitute one character (the “y”) for two others (“te”)? Despite putting clear parameters around what Editor should look like, I could tell Claude was stuck, so I called it quits and moved on.

However, I’d wanted something like Editor for far too long to simply give up. So I saved what I had to a GitHub repo and figured I’d take another run at it later.

Later turned out to be last week when Claude Fable 5 was re-released after a U.S. government shutdown of the model. Anthropic made the model available to its subscribers, with some restrictions, through July 7, which I made good use of.

A lot has changed in the six months since I put Editor on ice. Notably, Claude Opus 4.8 and Claude Design were released, and Claude became better at using a browser, all of which fit nicely with Editor’s relatively complex design.

Between Opus 4.8 and Claude Design, I expect I could have finished Editor without Fable 5, but with it, the only thing that slowed me down was my five-hour token limit. I repeatedly hit the limit in under an hour as Fable managed a swarm of subagents. What could have taken a few hours last Friday night spanned an evening and the next morning. The token gating slowed me down, but at the same time, I expect that using Opus 4.8 and Claude Design would have taken the entire weekend.

But it isn’t just speed that makes Fable 5 impressive; it’s the fact that it got Editor’s complex UI right the first time. Fable took a carefully planned but very broken prototype and turned it into a polished product that the whole MacStories team can use.

However, there’s a big difference between a web app running on my Mac mini server for personal use and something that can be shared. Fortunately, Editor also benefited from the internal tool foundation Federico has built over the past several months.

He originally built it to house Feedboard, his kanban-style RSS feed reader; Images, an update to our tool for uploading images to the MacStories CDN; and iOS Review Search, a semantic search tool for his iOS and iPadOS reviews. It’s a login-protected internal page built on web app hosting platform Vercel. I later contributed a tool that summarizes Apple Newsroom posts and simplifies uploading their promotional images to our server.

With a couple of those tools in hand as context for Fable, I asked Claude to get Editor ready for our internal tools page and passed it off to Federico with a separate set of specs and instructions he could point Claude at for deployment and the creation of a landing page. That introduced bugs that required some troubleshooting, which Federico handled in part using Cursor and it new iPhone app, but by that afternoon, Editor was ready for production. The entire process from old, broken prototype to production web app took less than 24 hours, and for a lot of that time we were either asleep or away from home.

---

When you use agentic tools like Claude every day, it’s easy to forget how far they come so quickly. All you see are the flaws that still serve as roadblocks. What was different about using Fable 5 was that there were no roadblocks. It simply took a project that Opus 4.6 struggled with in February and made short work of it. It was a remarkable thing to see. And now, we have a tool that I’ve wanted since we started using GitHub for our writing in 2015.

Tomorrow, Fable will move to usage credits that are just too expensive for my tastes, given how fast the model burns tokens. Hopefully, it will trickle back into Anthropic’s subscription tiers in the future. Until then, though, I’ll continue knocking out prototypes, and if they’re too much for Opus, I’ll shelve them until a better model comes along. They always do.

Saron Yitbarek, writing on the WebKit blog:

In Safari Technology Preview 247, we’re introducing the Safari MCP server — a Model Context Protocol server for web developers that makes your web development and debugging workflow faster and more powerful. We know agents are increasingly integral to the coding process and the Safari MCP server gives your agent the ability to know how your code actually renders in the browser by connecting it to a Safari browser window.

Any MCP-compatible client can connect to the Safari MCP server. By connecting your agent to a Safari browser window, your agent can emulate what your users experience, giving it the information it needs to debug more autonomously, like access to the DOM, network requests, screenshots, and console output.

Importantly:

The Safari MCP server runs entirely on your local machine and makes no network calls of its own. It also does not have access to your personal information in Safari (e.g. AutoFill or other browser activity). When it captures page content, screenshots, or console logs, that data goes directly to the agent you’re running — not to Apple. What happens to that data from there depends on the agent and model you’re using. As with any agent you give access to your browser, only use ones you trust.

For the past few months, I’ve been using Google Chrome on my MacBook Pro and Mac Studio not because I like the browser (in fact, I really dislike Chrome’s text rendering and UI), but simply because it was the best option for agents. In Codex specifically, between Playwright, Chrome Dev Tools, and OpenAI’s own Chrome extension, I could kick off research tasks (such as vacation planning and booking a hotel) that involved a browser directly from my iPhone, letting Codex drive the research on my remote Mac.

Now, thanks to Safari’s new MCP server, I no longer have to use Chrome on desktop and can return to a unified browser setup across all my devices. Even better: it actually looks like Apple shipped the most ergonomic browser MCP for agents to date. The MCP server has dedicated tools for page extraction (including getting webpages as Markdown, based on WebKit’s own conversion pipeline), evaluating JavaScript, DOM interactions (clicking, scrolling, resizing the viewport for mobile screens, etc.), taking screenshots, and more. I set this up immediately in Codex, and I also asked Codex about comparing Safari’s MCP to its own Chrome extension and the older Playwright. The verdict: although Chrome has a richer API with Chrome Dev Tools when it comes to network requests, Codex actually preferred Apple’s leaner, more direct approach for letting an agent drive and debug a browser.

I’m really happy to see folks at Apple embrace agentic tools: between the new MCP capabilities of Xcode and now this, it looks like Apple’s software (on the Mac, of course) is becoming more and more approachable by people who are working in new ways thanks to agents. Whether you’re a web developer or tinkerer, I highly recommend checking out what Apple has released in Safari Technology Preview. More of this, please.

In the current era of coding agents becoming productivity assistants, iPadOS’ limitations are no longer defined by the lack of desktop-class multitasking or access to external peripherals. A new class of iPadOS shortcomings looms large on the horizon: the iPad’s app sandboxing and the absence of an open filesystem have relegated it to acting as a remote control for agents.

I’ve been ruminating on this thought for some time. I, of course, am very satisfied with the improvements Apple brought to the iPadOS platform throughout the 26 cycle: between new windowing, local capture, a menu bar, and the improved Files app, I can get most of my old-school work done on the iPad Pro without begrudging the experience like I used to a few years ago. What I’ve noticed this year, however, is that iPadOS 26 was an update designed to address the pre-existing low-hanging fruit of quasi-desktop efficiency; by design – and we have Craig Federighi on the record saying as much – it wasn’t intended to reinvent the wheel in any meaningful way.

That would have been fine a few years ago. The problem is that the productivity wheel is literally being reinvented by other companies as we speak. And in an unsurprising turn of events, the Mac is at the forefront of that reinvention, while the iPad is being left behind once again.

I’m writing this as someone who likes to be on the bleeding edge of AI tools. Since the release of Claude Code in early 2025, I (and, realistically, millions of other nerds whose taste aligns with mine) have increasingly moved a lot of my research, automation, coding, and other tasks considered “productivity” to desktop agents. These are powered by the same underlying technology as chatbots, but they’re considerably more powerful: Claude Code and Cowork, Codex, Perplexity’s Personal Computer, and self-hosted agents like OpenClaw and Hermes can understand intent and perform long-running tasks on your computer. They can write code, stay on a task for hours (or even days) at a time, analyze the contents of your screen, and even use a computer on their own. To believe that these AI tools are still a fad and chatbots are useless is misinformation at this point.

As of June 2026, I spend most of my days with two apps constantly open on my M4 Pro MacBook Pro: Codex and Notion. I’m a huge fan of what OpenAI has accomplished with Codex for Mac; their all-in-one package that combines thread-based chats with skills, plugins, connectors, computer use, memories, and system-wide filesystem access has genuinely allowed me to produce content for my audience that I wouldn’t have even dreamed of years ago. Since I started working with Codex, I’ve released a major update to Apple Frames, two CLIs (with two more coming soon), Shortcuts Playground, and a brand new MacStories Shortcuts Archive. These are actual products that are used by thousands of people and are generating real revenue for MacStories. I’ve also created an entire suite of MacStories-only internal apps (now used by our whole team) and am currently in the process of researching my iOS 27 review, creating an app for Shortcuts Playground, and brainstorming a different product altogether for MCP.

I’m doing all of this on a Mac because the true Codex experience isn’t even “desktop-only”: it’s Mac-only.

Let me give you some examples. To make the original version of Shortcuts Playground, I had Codex with Computer Use scrape my entire library on the old MacStories Shortcuts Archive, download over 300 shortcuts, and learn my coding style. Once I had a plugin, I also had Codex create over 1,000 shortcuts on its own, install them in the Shortcuts app for Mac, and debug them visually to find issues. For the new Shortcuts Playground plugin and app, I’m going even further: Codex created over 3,500 shortcuts spanning the entire library of Shortcuts actions while simultaneously coordinating with other Codex threads – some of which are running on my Mac Studio – to build an app, train a local model for Core AI, and constantly iterate on the new harness behind the app. Meanwhile, I’m also spending time in Codex organizing sources for my iOS 27 review, managing my tasks with Reminders and my own RemCTL, and performing general research on any topic I think of. The net result of all this is that I’m shipping more things, making more money for MacStories, saving money thanks to our new internal tools, and – most importantly – learning a lot and having fun.

In all of this, the iPad’s role is to be, once again, an accessory to the Mac – and a rather expensive one at that. I wrote last year about iPadOS’ third-party app problem, and I still think all of it applies today. What’s different in 2026 is that these powerful agentic tools that are redefining coding and knowledge work, and which are centralizing productivity inside so-called “super apps”, aren’t coming to the iPad, but not for political or financial reasons: they’re Mac-only because only macOS is mature and open enough to support them.

In a funny twist of fate, Apple spent years trying to make iPadOS catch up to macOS on the surface, only for macOS’ underlying nature to unlock a new generation of apps that are rewriting the rules of modern software. No amount of windowing and menu bars can change the fact that neither Claude Cowork nor Codex will ever be possible on the current version of iPadOS. From an open filesystem that lets agents poke around anywhere to powerful Accessibility and Screen Recording APIs for developers to features like system-wide hotkeys, dictation, and true background processes, Apple’s oldest operating system is the one that feels the freshest (and the most powerful) in the AI industry today.

In fact, the Mac is so powerful and well-equipped for this new wave of desktop agents, it even yields an amazing experience when used in a “headless” setup with no display attached to it. This may have started as a trend because of OpenClaw, but six months later, I believe that a Mac mini with Codex running on it is the best bang for your buck if you’re building an always-on agentic setup based on a frontier model that can do just about anything you throw at it.

Which brings me to the iPad’s only silver lining in this space right now.

Most of my Codex tasks are running on my Mac Studio server, but I also use Codex on my MacBook Pro. Thanks to Codex’s support for remote connections, I can chat with threads running on the Mac Studio from the Codex app on a different machine, which is a fantastic feature. Alternatively, I can use Apple’s excellent (and, again, Mac-only) Screen Sharing app to log into my headless Mac and interact with macOS with superior performance and image quality to VNC. (I also use this HDMI 2.1 dummy plug to unlock 4K resolution when headless.) Coordinating Codex threads across different projects and machines feels like the sort of thing that shouldn’t be possible, yet here we are.

If the iPad is still relevant to me in this specific new way of working, it’s entirely because of the ChatGPT app and the fact that OpenAI cared enough to design a good remote experience for iPhone and iPad users. The Codex section inside ChatGPT is a solid product and getting better every week; it’s also the only app of this kind that lets you connect to multiple computers at once and manage threads across all of them. With Codex remote on iPad, I can continue my projects from the MacBook Pro or Mac Studio, pin specific threads, and keep an eye on all my agents working in the background. In general, it’s also a way to bridge functionalities that are missing from iPadOS. Without Codex remote, I wouldn’t be able to ask my agent to reschedule my reminders and turn some emails into tasks in the same workflow; I wouldn’t be able to tell my agent to go to the Apple Newsroom, find me a specific press release, extract all images from it, and upload them to our CDN.

Perhaps Siri AI will unlock similar capabilities (although I doubt to the degree of a frontier desktop agent), but it’ll still be limited to apps made by companies that decide to support App Intents. When I’m not using my Mac and I think of something I can’t do on the iPad these days, I instantly reach for Codex inside ChatGPT. I suspect this trend will only grow as more AI companies release similar remote experiences for iOS and iPadOS.

Here’s the issue, though: these are remote companion experiences. It’s great that they exist and that OpenAI cared enough to make them great, but they’re still no substitutes for the real Codex experience on a Mac. It’s ironic if you think about it, isn’t it? A headless Mac is still more flexible and powerful than an iPad hamstrung by the closed nature of its own OS and software gatekeeping.

If you’re among the five million people using Codex on a weekly basis and will be planning your next laptop purchase in a few months, perhaps these considerations will change the calculus for you. Especially in the face of price increases and RAM uncertainty, would you be better served by spending $1,499 on a hybrid laptop that gets work done the old way with 256 GB of storage, or $1,499 on a computer where AI is a first-class citizen with 24 GB of RAM and double the storage? If we accept that power users’ priorities and workflows will be dramatically changing in the near future (if they haven’t already!), all prices being equal, which OS is best positioned for the future?

Of course, I like using both an iPad Pro and a Mac for different tasks. But let’s face it; in this day and age – and especially after last week – not everybody has the budget for two computers that have some overlap between them. Sure, I could argue that an iPad Pro + a headless Mac mini is an insane combo to get the best of both worlds these days: the nimble and delightful nature of iPadOS and the freedom to experiment with AI on a Mac. You can install apps like the latest Jump Desktop beta or the great new screen sharing app Mirage on the iPad and use your Mac mini almost as if it were connected to the iPad’s display. Set up Tailscale on your network, and the Mac’s power can be with you at all times. But that’s a lot of money, and a lot of setup, to achieve an approximation of what a single MacBook Air can handle with more memory, more storage, and a couple of Mac apps.

I’m sure that Apple is aware of the changing nature of this landscape, but in a similar vein to chatbots and Siri, perhaps they were unprepared for the tide of agents to accelerate so quickly. If the idea of putting macOS on an iPad Pro continues to be a non-starter at Apple, and assuming agent-based coding and knowledge work are here to stay, what should the company do to make sure the iPad doesn’t get left behind again? Is a sandboxed Terminal for iPad backed by a dedicated “Agent Framework” the solution? Is working with other companies to build more “remote companion” apps the way forward?

Or, perhaps more obviously: how long until Siri AI can also become a capable agent, connected to App Intents, on par with competing frontier agents?

Until, and if, that happens, the iPad will once again play the role of sidekick to macOS.

When it comes to the bleeding edge of AI and pushing the frontier of agents forward, there’s nothing like the Mac.

Photo editing is getting some of the most interesting Apple Intelligence features this fall. At WWDC, Tyler Stalman interviewed Jon McCormack, Apple’s Vice President of Camera and Photos Software Engineering, and Della Huff, the company’s Senior Manager of Camera and Photos Product Marketing, in a video that covers Spatial Reframing, Extend, and an improved Clean Up tool, along with demos of each:

The interview goes into depth on each feature and how they’re enhanced by the integration with Apple’s improved Private Cloud Compute models, sharing nuggets like the fact that Spatial Reframing of photos is possible even if an image is taken with a single-lens iPhone and the fact that Apple includes metadata in generatively edited photos identifying the use of AI and will add SynthID watermarking, a technology developed by Google, to AI-edited photos later this year.

I’m not a fan of wholesale image generation, which is why I appreciate the thoughtful approach Apple is taking with these photo editing features. The changes are at the margins of the photo and identified as edited using AI.

Apple has reportedly sent legal letters to dozens of former Apple employees now working at OpenAI, telling them to preserve potentially relevant documents and communications as it continues to pursue its trade secret lawsuit against the AI company.


The Financial Times ($) reports that Apple has targeted around 40 former employees with legal preservation letters, acting on its belief that the alleged misappropriation of confidential information may extend beyond the individuals named in its original complaint.

The development follows Apple's lawsuit filed last week against OpenAI, in which the company alleges a coordinated effort to obtain confidential information relating to its hardware engineering and product development.

Apple claims OpenAI recruited key engineers, including former Apple executives Tang Tan and Chang Liu, and benefited from proprietary designs, manufacturing processes, and other trade secrets. Tan is OpenAI's Chief Hardware Officer and a 24-year Apple veteran who led product design, while Liu is on the hardware team at OpenAI after working as a senior system electrical engineer at Apple.

The complaint says that more than 400 former Apple employees now work at OpenAI and suggests that the alleged misconduct is broader than a few isolated actions by individual employees. OpenAI has denied the allegations, saying in a statement to Bloomberg this week that it is "not aware of any evidence that this complaint has merit."

Apple has requested an injunction requiring OpenAI to cease using any Apple information during the development of OpenAI's AI hardware device. Apple is also seeking damages and suing Tan and Liu for breach of contract for violating their employment agreements. The company believes the evidence uncovered so far may represent only the "tip of the iceberg," according to its lawsuit.
This article, "Report: Apple Sends Legal Letters to Dozens of OpenAI Employees" first appeared on MacRumors.com

Discuss this article in our forums

O esperado primeiro equipamento de inteligência artificial da OpenAI continua envolto de mistério e voltou a ser adiado. A equipa, liderada por Jony Ive, o “pai” do iPhone, está a recrutar elementos para a sua equipa diretamente da Apple.

The post OpenAI adia o seu primeiro equipamento de IA, mas lança acessório para programadores appeared first on Tek Notícias.

The deal, which was rumored to be in the works last year, marks an important step for Apple's AI ambitions in a key market.