Hi everyone! 👋 I'm working on a C++ project using TensorFlow Lite and was wondering if anyone has a prebuilt TensorFlow Lite C++ library (libtensorflowlite) for macOS (Apple Silicon M1/M2) that they’d be willing to share. I’m looking specifically for the TensorFlow Lite C++ API — something that lets me use tflite::Interpreter, tflite::FlatBufferModel, etc. Building it from source using Bazel on macOS has been quite challenging and time-consuming, so a ready-to-use .dylib or .a build along with the required headers would be incredibly helpful. TensorFlow Lite version: v2.18.0 preferred Target: macOS arm64 (Apple Silicon) What I need: libtensorflowlite.dylib or .a Corresponding headers (ideally organized in a clean include/ folder) If you have one available or know where I can find a reliable prebuilt version, I’d be super grateful. Thanks in advance! 🙏

The WWDC25: Explore large language models on Apple silicon with MLX video talks about using your own data to fine-tune a large language model. But the video doesn't explain what kind of data can be used. The video just shows the command to use and how to point to the data folder. Can I use PDFs, Word documents, Markdown files to train the model? Are there any code examples on GitHub that demonstrate how to do this?

WWDC25: Combine Metal 4 machine learning and graphics Demonstrated a way to combine neural network in the graphics pipeline directly through the shaders, using an example of Texture Compression. However there is no mention of using which ML technique texture is compressed. Can anyone point me to some well known model/s for this particular use case shown in WWDC25.

I have a question. In China, long pressing a picture in the album can segment the target. Is this model a local model? Is there any information? Can developers use it?

Environment MacOC 26 Xcode Version 26.0 beta 7 (17A5305k) simulator: iPhone 16 pro iOS: iOS 26 Problem NLContextualEmbedding.load() fails with the following error In simulator Failed to load embedding from MIL representation: filesystem error: in create_directories: Permission denied ["/var/db/com.apple.naturallanguaged/com.apple.e5rt.e5bundlecache"] filesystem error: in create_directories: Permission denied ["/var/db/com.apple.naturallanguaged/com.apple.e5rt.e5bundlecache"] Failed to load embedding model 'mul_Latn' - '5C45D94E-BAB4-4927-94B6-8B5745C46289' assetRequestFailed(Optional(Error Domain=NLNaturalLanguageErrorDomain Code=7 "Embedding model requires compilation" UserInfo={NSLocalizedDescription=Embedding model requires compilation})) in #Playground I'm new to this embedding model. Not sure if it's caused by my code or environment. Code snippet import Foundation import NaturalLanguage import Playgrounds #Playground { // Prefer initializing by script for broader coverage; returns NLContextualEmbedding? guard let embeddingModel = NLContextualEmbedding(script: .latin) else { print("Failed to create NLContextualEmbedding") return } print(embeddingModel.hasAvailableAssets) do { try embeddingModel.load() print("Model loaded") } catch { print("Failed to load model: \(error)") } }

We are developing Apple AI for overseas markets and adapting it for iPhone 17 and later models. When the system language and Siri language do not match—such as the system being in English while Siri is in Chinese—it may result in Apple AI being unusable. So, I would like to ask, how can this issue be resolved, and are there other reasons that might cause it to be unusable within the app?

It is vital for Apple to refine its OCR models to correctly distinguish between Khmer and Thai scripts. Incorrectly labeling Khmer text as Thai is more than a technical bug; it is a culturally insensitive error that impacts national identity, especially given the current geopolitical climate between Cambodia and Thailand. Implementing a more robust language-detection threshold would prevent these harmful misidentifications. There is a significant logic flaw in the VNRecognizeTextRequest language detection when processing Khmer script. When the property automaticallyDetectsLanguage is set to true, the Vision framework frequently misidentifies Khmer characters as Thai. While both scripts share historical roots, they are distinct languages with different alphabets. Currently, the model’s confidence threshold for distinguishing between these two scripts is too low, leading to incorrect OCR output in both developer-facing APIs and Apple’s native ecosystem (Preview, Live Text, and Photos). import SwiftUI import Vision class TextExtractor { func extractText(from data: Data, completion: @escaping (String) -> Void) { let request = VNRecognizeTextRequest { (request, error) in guard let observations = request.results as? [VNRecognizedTextObservation] else { completion("No text found.") return } let recognizedStrings = observations.compactMap { observation in let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } completion(recognizedStrings.joined(separator: "\n")) } request.automaticallyDetectsLanguage = true // <-- This is the issue. request.recognitionLevel = .accurate let handler = VNImageRequestHandler(data: data, options: [:]) DispatchQueue.global(qos: .background).async { do { try handler.perform([request]) } catch { completion("Failed to perform OCR: \(error.localizedDescription)") } } } } Recognizing Khmer Confidence Score is low for Khmer text. (The output is in Thai language with low confidence score) Recognizing English Confidence Score is high expected. Recognizing Thai Confidence Score is high as expected Issues on Preview, Photos Khmer text Copied text Kouk Pring Chroum Temple [19121 รอาสายสุกตีนานยารรีสใหิสรราภูชิตีนนสุฐตีย์ [รุก เผือชิษาธอยกัตธ์ตายตราพาษชาณา ถวเชยาใบสราเบรถทีมูสินตราพาษชาณา ทีมูโษา เช็ก อาษเชิษฐอารายสุกบดตพรธุรฯ ตากร"สุก"ผาตากรธกรธุกเยากสเผาพศฐตาสาย รัอรณาษ"ตีพย" สเผาพกรกฐาภูชิสาเครๆผู:สุกรตีพาสเผาพสรอสายใผิตรรารตีพสๆ เดียอลายสุกตีน ธาราชรติ ธิพรหณาะพูชุบละเาหLunet De Lajonquiere ผารูกรสาราพารผรผาสิตภพ ตารสิทูก ธิพิ คุณที่นสายเระพบพเคเผาหนารเกะทรนภาษเราภุพเสารเราษทีเลิกสญาเราหรุฬารชสเกาก เรากุม สงสอบานตรเราะากกต่ายภากายระตารุกเตียน Recommended Solutions 1. Set a Threshold Filter out the detected result where the threshold is less than or equal to 0.5, so that it would not output low quality text which can lead to the issue. For example, let recognizedStrings = observations.compactMap { observation in if observation.confidence <= 0.5 { return nil } let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } 2. Add Khmer Language Support This issue would never happen if the model has the capability to detect and recognize image with Khmer language. Doc2Text GitHub: https://github.com/seanghay/Doc2Text-Swift

Hello All, I’m working on a computer-vision–heavy iOS application that uses the camera, LiDAR depth maps, and semantic segmentation to reason about the environment (object identification, localization and measurement - not just visualization). Current architecture I initially built the image pipeline around CIImage as a unifying abstraction. It seemed like a good idea because: CIImage integrates cleanly with Vision, ARKit, AVFoundation, Metal, Core Graphics, etc. It provides a rich set of out-of-the-box transforms and filters. It is immutable and thread-safe, which significantly simplified concurrency in a multi-queue pipeline. The LiDAR depth maps, semantic segmentation masks, etc. were treated as CIImages, with conversion to CVPixelBuffer or MTLTexture only at the edges when required. Problem I’ve run into cases where Core Image transformations do not preserve numeric fidelity for non-visual data. Example: Rendering a CIImage-backed segmentation mask into a larger CVPixelBuffer can cause label values to change in predictable but incorrect ways. This occurs even when: using nearest-neighbor sampling disabling color management (workingColorSpace / outputColorSpace = NSNull) applying identity or simple affine transforms I’ve confirmed via controlled tests that: Metal → CVPixelBuffer paths preserve values correctly CIImage → CVPixelBuffer paths can introduce value changes when resampling or expanding the render target This makes CIImage unsafe as a source of numeric truth for segmentation masks and depth-based logic, even though it works well for visualization, and I should have realized this much sooner. Direction I’m considering I’m now considering refactoring toward more intent-based abstractions instead of a single image type, for example: Visual images: CIImage (camera frames, overlays, debugging, UI) Scalar fields: depth / confidence maps backed by CVPixelBuffer + Metal Label maps: segmentation masks backed by integer-preserving buffers (no interpolation, no transforms) In this model, CIImage would still be used extensively — but primarily for visualization and perceptual processing, not as the container for numerically sensitive data. Thread safety concern One of the original advantages of CIImage was that it is thread-safe by design, and that was my biggest incentive. For CVPixelBuffer / MTLTexture–backed data, I’m considering enforcing thread safety explicitly via: Swift Concurrency (actor-owned data, explicit ownership) Questions For those may have experience with CV / AR / imaging-heavy iOS apps, I was hoping to know the following: Is this separation of image intent (visual vs numeric vs categorical) a reasonable architectural direction? Do you generally keep CIImage at the heart of your pipeline, or push it to the edges (visualization only)? How do you manage thread safety and ownership when working heavily with CVPixelBuffer and Metal? Using actor-based abstractions, GCD, or adhoc? Are there any best practices or gotchas around using Core Image with depth maps or segmentation masks that I should be aware of? I’d really appreciate any guidance or experience-based advice. I suspect I’ve hit a boundary of Core Image’s design, and I’m trying to refactor in a way that doesn't involve too much immediate tech debt, remains robust and maintainable long-term. Thank you in advance!

I have a very terrible crash problem in my App when I use AVSpeechSynthesizer and I can't repetition it.Here is my code, It's a singleton- (void)stopSpeech { if ([self.synthesizer isPaused]) { return; } if ([self.synthesizer isSpeaking]) { BOOL isSpeech = [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryImmediate]; if (!isSpeech) { [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryWord]; } } self.stopBlock ? self.stopBlock() : nil; } -(AVSpeechSynthesizer *)synthesizer { if (!_synthesizer) { _synthesizer = [[AVSpeechSynthesizer alloc] init]; _synthesizer.delegate = self; } return _synthesizer; }When the user leaves the page, I call the stopSpeech method。Then I got a lot of crash messagesHere is a crash log:# Crashlytics - plaintext stacktrace downloaded by liweican at Mon, 13 May 2019 03:03:24 GMT # URL: https://fabric.io/youdao-dict/ios/apps/com.youdao.udictionary/issues/5a904ed88cb3c2fa63ad7ed3?time=last-thirty-days/sessions/b1747d91bafc4680ab0ca8e3a702c52c_DNE_0_v2 # Organization: zzz # Platform: ios # Application: U-Dictionary # Version: 3.0.5.4 # Bundle Identifier: com.youdao.UDictionary # Issue ID: 5a904ed88cb3c2fa63ad7ed3 # Session ID: b1747d91bafc4680ab0ca8e3a702c52c_DNE_0_v2 # Date: 2019-05-13T02:27:00Z # OS Version: 12.2.0 (16E227) # Device: iPhone 8 Plus # RAM Free: 17% # Disk Free: 64.6% #19. Crashed: AXSpeech 0 libsystem_pthread.dylib 0x19c15e5b8 pthread_mutex_lock$VARIANT$armv81 + 102 1 CoreFoundation 0x19c4cf84c CFRunLoopSourceSignal + 68 2 Foundation 0x19cfc7280 performQueueDequeue + 464 3 Foundation 0x19cfc680c __NSThreadPerformPerform + 136 4 CoreFoundation 0x19c4d22bc __CFRUNLOOP_IS_CALLING_OUT_TO_A_SOURCE0_PERFORM_FUNCTION__ + 24 5 CoreFoundation 0x19c4d223c __CFRunLoopDoSource0 + 88 6 CoreFoundation 0x19c4d1b74 __CFRunLoopDoSources0 + 256 7 CoreFoundation 0x19c4cca60 __CFRunLoopRun + 1004 8 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 9 Foundation 0x19ce99fcc -[NSRunLoop(NSRunLoop) runMode:beforeDate:] + 300 10 libAXSpeechManager.dylib 0x1ac16c94c -[AXSpeechThread main] + 264 11 Foundation 0x19cfc66e4 __NSThread__start__ + 984 12 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 13 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 14 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 -- #0. com.apple.main-thread 0 libsystem_malloc.dylib 0x19c11ce24 small_free_list_remove_ptr_no_clear + 768 1 libsystem_malloc.dylib 0x19c11f094 small_malloc_from_free_list + 296 2 libsystem_malloc.dylib 0x19c11f094 small_malloc_from_free_list + 296 3 libsystem_malloc.dylib 0x19c11d63c small_malloc_should_clear + 224 4 libsystem_malloc.dylib 0x19c11adcc szone_malloc_should_clear + 132 5 libsystem_malloc.dylib 0x19c123c18 malloc_zone_malloc + 156 6 CoreFoundation 0x19c569ab4 __CFBasicHashRehash + 300 7 CoreFoundation 0x19c56b430 __CFBasicHashAddValue + 96 8 CoreFoundation 0x19c56ab9c CFBasicHashAddValue + 2160 9 CoreFoundation 0x19c49f3bc CFDictionaryAddValue + 260 10 CoreFoundation 0x19c572ee8 __54-[CFPrefsSource mergeIntoDictionary:sourceDictionary:]_block_invoke + 28 11 CoreFoundation 0x19c49f0b4 __CFDictionaryApplyFunction_block_invoke + 24 12 CoreFoundation 0x19c568b7c CFBasicHashApply + 116 13 CoreFoundation 0x19c49f090 CFDictionaryApplyFunction + 168 14 CoreFoundation 0x19c42f504 -[CFPrefsSource mergeIntoDictionary:sourceDictionary:] + 136 15 CoreFoundation 0x19c4bcd38 -[CFPrefsSearchListSource alreadylocked_getDictionary:] + 644 16 CoreFoundation 0x19c42e71c -[CFPrefsSearchListSource alreadylocked_copyValueForKey:] + 152 17 CoreFoundation 0x19c42e660 -[CFPrefsSource copyValueForKey:] + 60 18 CoreFoundation 0x19c579e88 __76-[_CFXPreferences copyAppValueForKey:identifier:container:configurationURL:]_block_invoke + 40 19 CoreFoundation 0x19c4bdff4 __108-[_CFXPreferences(SearchListAdditions) withSearchListForIdentifier:container:cloudConfigurationURL:perform:]_block_invoke + 272 20 CoreFoundation 0x19c4bda38 normalizeQuintuplet + 340 21 CoreFoundation 0x19c42c634 -[_CFXPreferences(SearchListAdditions) withSearchListForIdentifier:container:cloudConfigurationURL:perform:] + 108 22 CoreFoundation 0x19c42cec0 -[_CFXPreferences copyAppValueForKey:identifier:container:configurationURL:] + 148 23 CoreFoundation 0x19c57c2d0 _CFPreferencesCopyAppValueWithContainerAndConfiguration + 124 24 TextInput 0x1a450e550 -[TIPreferencesController valueForPreferenceKey:] + 460 25 UIKitCore 0x1c87c71f8 -[UIKeyboardPreferencesController handBias] + 36 26 UIKitCore 0x1c887275c -[UIKeyboardLayoutStar showKeyboardWithInputTraits:screenTraits:splitTraits:] + 320 27 UIKitCore 0x1c88f4240 -[UIKeyboardImpl finishLayoutChangeWithArguments:] + 492 28 UIKitCore 0x1c88f47c8 -[UIKeyboardImpl updateLayout] + 1208 29 UIKitCore 0x1c88eaad0 -[UIKeyboardImpl updateLayoutIfNecessary] + 448 30 UIKitCore 0x1c88eab9c -[UIKeyboardImpl setFrame:] + 140 31 UIKitCore 0x1c88d5d60 -[UIKeyboard activate] + 652 32 UIKitCore 0x1c894c90c -[UIKeyboardAutomatic activate] + 128 33 UIKitCore 0x1c88d5158 -[UIKeyboard setFrame:] + 296 34 UIKitCore 0x1c88d81b0 -[UIKeyboard _didChangeKeyplaneWithContext:] + 228 35 UIKitCore 0x1c88f4aa0 -[UIKeyboardImpl didMoveToSuperview] + 136 36 UIKitCore 0x1c8f2ad84 __45-[UIView(Hierarchy) _postMovedFromSuperview:]_block_invoke + 888 37 UIKitCore 0x1c8f2a970 -[UIView(Hierarchy) _postMovedFromSuperview:] + 760 38 UIKitCore 0x1c8f39ddc -[UIView(Internal) _addSubview:positioned:relativeTo:] + 1740 39 UIKitCore 0x1c88d5d84 -[UIKeyboard activate] + 688 40 UIKitCore 0x1c894c90c -[UIKeyboardAutomatic activate] + 128 41 UIKitCore 0x1c893b3a4 -[UIPeripheralHost(UIKitInternal) _reloadInputViewsForResponder:] + 1332 42 UIKitCore 0x1c8ae66d8 -[UIResponder(UIResponderInputViewAdditions) reloadInputViews] + 80 43 UIKitCore 0x1c8ae23bc -[UIResponder becomeFirstResponder] + 804 44 UIKitCore 0x1c8f2a560 -[UIView(Hierarchy) becomeFirstResponder] + 156 45 UIKitCore 0x1c8d93e84 -[UITextField becomeFirstResponder] + 244 46 UIKitCore 0x1c8d578dc -[UITextInteractionAssistant(UITextInteractionAssistant_Internal) setFirstResponderIfNecessary] + 192 47 UIKitCore 0x1c8d45d8c -[UITextSelectionInteraction oneFingerTap:] + 3136 48 UIKitCore 0x1c86e0bcc -[UIGestureRecognizerTarget _sendActionWithGestureRecognizer:] + 64 49 UIKitCore 0x1c86e8dd4 _UIGestureRecognizerSendTargetActions + 124 50 UIKitCore 0x1c86e6778 _UIGestureRecognizerSendActions + 316 51 UIKitCore 0x1c86e5ca4 -[UIGestureRecognizer _updateGestureWithEvent:buttonEvent:] + 760 52 UIKitCore 0x1c86d9d80 _UIGestureEnvironmentUpdate + 2180 53 UIKitCore 0x1c86d94b0 -[UIGestureEnvironment _deliverEvent:toGestureRecognizers:usingBlock:] + 384 54 UIKitCore 0x1c86d9290 -[UIGestureEnvironment _updateForEvent:window:] + 204 55 UIKitCore 0x1c8af14a8 -[UIWindow sendEvent:] + 3112 56 UIKitCore 0x1c8ad1534 -[UIApplication sendEvent:] + 340 57 UIKitCore 0x1c8b977c0 __dispatchPreprocessedEventFromEventQueue + 1768 58 UIKitCore 0x1c8b99eec __handleEventQueueInternal + 4828 59 UIKitCore 0x1c8b9311c __handleHIDEventFetcherDrain + 152 60 CoreFoundation 0x19c4d22bc __CFRUNLOOP_IS_CALLING_OUT_TO_A_SOURCE0_PERFORM_FUNCTION__ + 24 61 CoreFoundation 0x19c4d223c __CFRunLoopDoSource0 + 88 62 CoreFoundation 0x19c4d1b24 __CFRunLoopDoSources0 + 176 63 CoreFoundation 0x19c4cca60 __CFRunLoopRun + 1004 64 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 65 GraphicsServices 0x19e6cc79c GSEventRunModal + 104 66 UIKitCore 0x1c8ab7b68 UIApplicationMain + 212 67 UDictionary 0x10517e138 main (main.m:17) 68 libdyld.dylib 0x19bf928e0 start + 4 #1. Thread 0 libsystem_kernel.dylib 0x19c0deb74 __workq_kernreturn + 8 1 libsystem_pthread.dylib 0x19c161138 _pthread_wqthread + 340 2 libsystem_pthread.dylib 0x19c163cd4 start_wqthread + 4 #2. com.apple.uikit.eventfetch-thread 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 Foundation 0x19ce99fcc -[NSRunLoop(NSRunLoop) runMode:beforeDate:] + 300 6 Foundation 0x19ce99e5c -[NSRunLoop(NSRunLoop) runUntilDate:] + 96 7 UIKitCore 0x1c8b9d540 -[UIEventFetcher threadMain] + 136 8 Foundation 0x19cfc66e4 __NSThread__start__ + 984 9 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 10 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 11 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #3. JavaScriptCore bmalloc scavenger 0 libsystem_kernel.dylib 0x19c0ddee4 __psynch_cvwait + 8 1 libsystem_pthread.dylib 0x19c15d4a4 _pthread_cond_wait$VARIANT$armv81 + 628 2 libc++.1.dylib 0x19b6b5090 std::__1::condition_variable::wait(std::__1::unique_lock&lt;std::__1::mutex&gt;&amp;) + 24 3 JavaScriptCore 0x1a36a2238 void std::__1::condition_variable_any::wait&lt;std::__1::unique_lock&lt;bmalloc::Mutex&gt; &gt;(std::__1::unique_lock&lt;bmalloc::Mutex&gt;&amp;) + 108 4 JavaScriptCore 0x1a36a622c bmalloc::Scavenger::threadRunLoop() + 176 5 JavaScriptCore 0x1a36a59a4 bmalloc::Scavenger::Scavenger(std::__1::lock_guard&lt;bmalloc::Mutex&gt;&amp;) + 10 6 JavaScriptCore 0x1a36a73e4 std::__1::__thread_specific_ptr&lt;std::__1::__thread_struct&gt;::set_pointer(std::__1::__thread_struct*) + 38 7 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 8 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 9 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #4. WebThread 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 WebCore 0x1a5126480 RunWebThread(void*) + 600 6 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 7 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 8 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #5. com.twitter.crashlytics.ios.MachExceptionServer 0 UDictionary 0x1058a5564 CLSProcessRecordAllThreads (CLSProcess.c:376) 1 UDictionary 0x1058a594c CLSProcessRecordAllThreads (CLSProcess.c:407) 2 UDictionary 0x1058952dc CLSHandler (CLSHandler.m:26) 3 UDictionary 0x1058906cc CLSMachExceptionServer (CLSMachException.c:446) 4 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 5 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 6 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #6. com.apple.NSURLConnectionLoader 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 CFNetwork 0x19cae574c -[__CoreSchedulingSetRunnable runForever] + 216 6 Foundation 0x19cfc66e4 __NSThread__start__ + 984 7 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 8 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 9 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #7. AVAudioSession Notify Thread 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 AVFAudio 0x1a238a378 GenericRunLoopThread::Entry(void*) + 156 6 AVFAudio 0x1a23b4c60 CAPThread::Entry(CAPThread*) + 88 7 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 8 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 9 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #8. WebCore: LocalStorage 0 libsystem_kernel.dylib 0x19c0ddee4 __psynch_cvwait + 8 1 libsystem_pthread.dylib 0x19c15d4a4 _pthread_cond_wait$VARIANT$armv81 + 628 2 JavaScriptCore 0x1a3668ce4 ***::ThreadCondition::timedWait(***::Mutex&amp;, ***::WallTime) + 80 3 JavaScriptCore 0x1a364f96c ***::ParkingLot::parkConditionallyImpl(void const*, ***::ScopedLambda&lt;bool ()&gt; const&amp;, ***::ScopedLambda&lt;void ()&gt; const&amp;, ***::TimeWithDynamicClockType const&amp;) + 2004 4 WebKitLegacy 0x1a67b6ea8 bool ***::Condition::waitUntil&lt;***::Lock&gt;(***::Lock&amp;, ***::TimeWithDynamicClockType const&amp;) + 184 5 WebKitLegacy 0x1a67b9ba4 std::__1::unique_ptr&lt;***::Function&lt;void ()&gt;, std::__1::default_delete&lt;***::Function&lt;void ()&gt; &gt; &gt; ***::MessageQueue&lt;***::Function&lt;void ()&gt; &gt;::waitForMessageFilteredWithTimeout&lt;***::MessageQueue&lt;***::Function&lt;void ()&gt; &gt;::waitForMessage()::'lambda'(***::Function&lt;void ()&gt; const&amp;)&gt;(***::MessageQueueWaitResult&amp;, ***::MessageQueue&lt;***::Function&lt;void ()&gt; &gt;::waitForMessage()::'lambda'(***::Function&lt;void ()&gt; const&amp;)&amp;&amp;, ***::WallTime) + 156 6 WebKitLegacy 0x1a67b91c0 WebCore::StorageThread::threadEntryPoint() + 68 7 JavaScriptCore 0x1a3666f88 ***::Thread::entryPoint(***::Thread::NewThreadContext*) + 260 8 JavaScriptCore 0x1a3668494 ***::wtfThreadEntryPoint(void*) + 12 9 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 10 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 11 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #9. com.apple.CoreMotion.MotionThread 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 CoreFoundation 0x19c4cd0b0 CFRunLoopRun + 80 6 CoreMotion 0x1a1df0240 (Missing) 7 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 8 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 9 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #10. Thread 0 libsystem_kernel.dylib 0x19c0deb74 __workq_kernreturn + 8 1 libsystem_pthread.dylib 0x19c161138 _pthread_wqthread + 340 2 libsystem_pthread.dylib 0x19c163cd4 start_wqthread + 4 #11. Thread 0 libsystem_kernel.dylib 0x19c0deb74 __workq_kernreturn + 8 1 libsystem_pthread.dylib 0x19c1611f8 _pthread_wqthread + 532 2 libsystem_pthread.dylib 0x19c163cd4 start_wqthread + 4 #12. com.apple.CFStream.LegacyThread 0 libsystem_kernel.dylib 0x19c0d30f4 mach_msg_trap + 8 1 libsystem_kernel.dylib 0x19c0d25a0 mach_msg + 72 2 CoreFoundation 0x19c4d1cb4 __CFRunLoopServiceMachPort + 236 3 CoreFoundation 0x19c4ccbc4 __CFRunLoopRun + 1360 4 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 5 CoreFoundation 0x19c4e5094 _legacyStreamRunLoop_workThread + 260 6 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 7 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 8 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #13. Thread 0 libsystem_pthread.dylib 0x19c163cd0 start_wqthread + 190 #14. Thread 0 libsystem_kernel.dylib 0x19c0deb74 __workq_kernreturn + 8 1 libsystem_pthread.dylib 0x19c161138 _pthread_wqthread + 340 2 libsystem_pthread.dylib 0x19c163cd4 start_wqthread + 4 #15. Thread 0 libsystem_kernel.dylib 0x19c0deb74 __workq_kernreturn + 8 1 libsystem_pthread.dylib 0x19c161138 _pthread_wqthread + 340 2 libsystem_pthread.dylib 0x19c163cd4 start_wqthread + 4 #16. Thread 0 libsystem_kernel.dylib 0x19c0d3148 semaphore_timedwait_trap + 8 1 libdispatch.dylib 0x19bf50a4c _dispatch_sema4_timedwait$VARIANT$armv81 + 64 2 libdispatch.dylib 0x19bf513a8 _dispatch_semaphore_wait_slow + 72 3 libdispatch.dylib 0x19bf647c8 _dispatch_worker_thread + 344 4 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 5 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 6 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #17. Thread 0 libsystem_kernel.dylib 0x19c0d3148 semaphore_timedwait_trap + 8 1 libdispatch.dylib 0x19bf50a4c _dispatch_sema4_timedwait$VARIANT$armv81 + 64 2 libdispatch.dylib 0x19bf513a8 _dispatch_semaphore_wait_slow + 72 3 libdispatch.dylib 0x19bf647c8 _dispatch_worker_thread + 344 4 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 5 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 6 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #18. Thread 0 libsystem_kernel.dylib 0x19c0d3148 semaphore_timedwait_trap + 8 1 libdispatch.dylib 0x19bf50a4c _dispatch_sema4_timedwait$VARIANT$armv81 + 64 2 libdispatch.dylib 0x19bf513a8 _dispatch_semaphore_wait_slow + 72 3 libdispatch.dylib 0x19bf647c8 _dispatch_worker_thread + 344 4 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 5 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 6 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #19. Crashed: AXSpeech 0 libsystem_pthread.dylib 0x19c15e5b8 pthread_mutex_lock$VARIANT$armv81 + 102 1 CoreFoundation 0x19c4cf84c CFRunLoopSourceSignal + 68 2 Foundation 0x19cfc7280 performQueueDequeue + 464 3 Foundation 0x19cfc680c __NSThreadPerformPerform + 136 4 CoreFoundation 0x19c4d22bc __CFRUNLOOP_IS_CALLING_OUT_TO_A_SOURCE0_PERFORM_FUNCTION__ + 24 5 CoreFoundation 0x19c4d223c __CFRunLoopDoSource0 + 88 6 CoreFoundation 0x19c4d1b74 __CFRunLoopDoSources0 + 256 7 CoreFoundation 0x19c4cca60 __CFRunLoopRun + 1004 8 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 9 Foundation 0x19ce99fcc -[NSRunLoop(NSRunLoop) runMode:beforeDate:] + 300 10 libAXSpeechManager.dylib 0x1ac16c94c -[AXSpeechThread main] + 264 11 Foundation 0x19cfc66e4 __NSThread__start__ + 984 12 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 13 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 14 libsystem_pthread.dylib 0x19c163cdc thread_start + 4 #20. AXSpeech 0 (Missing) 0x1071ba524 (Missing) 1 (Missing) 0x1071b3e7c (Missing) 2 (Missing) 0x10718fba4 (Missing) 3 (Missing) 0x107184bc8 (Missing) 4 libdyld.dylib 0x19bf95908 dlopen + 176 5 CoreFoundation 0x19c5483e8 _CFBundleDlfcnLoadBundle + 140 6 CoreFoundation 0x19c486918 _CFBundleLoadExecutableAndReturnError + 352 7 Foundation 0x19ced5734 -[NSBundle loadAndReturnError:] + 428 8 TextToSpeech 0x1abfff800 TTSSpeechUnitTestingMode + 1020 9 libdispatch.dylib 0x19bf817d4 _dispatch_client_callout + 16 10 libdispatch.dylib 0x19bf52040 _dispatch_once_callout + 28 11 TextToSpeech 0x1abfff478 TTSSpeechUnitTestingMode + 116 12 libobjc.A.dylib 0x19b7173cc CALLING_SOME_+initialize_METHOD + 24 13 libobjc.A.dylib 0x19b71cee0 initializeNonMetaClass + 296 14 libobjc.A.dylib 0x19b71e640 initializeAndMaybeRelock(objc_class*, objc_object*, mutex_tt&lt;false&gt;&amp;, bool) + 260 15 libobjc.A.dylib 0x19b7265a4 lookUpImpOrForward + 244 16 libobjc.A.dylib 0x19b733858 _objc_msgSend_uncached + 56 17 libAXSpeechManager.dylib 0x1ac167324 -[AXSpeechManager _initialize] + 68 18 Foundation 0x19cfc68d4 __NSThreadPerformPerform + 336 19 CoreFoundation 0x19c4d22bc __CFRUNLOOP_IS_CALLING_OUT_TO_A_SOURCE0_PERFORM_FUNCTION__ + 24 20 CoreFoundation 0x19c4d223c __CFRunLoopDoSource0 + 88 21 CoreFoundation 0x19c4d1b74 __CFRunLoopDoSources0 + 256 22 CoreFoundation 0x19c4cca60 __CFRunLoopRun + 1004 23 CoreFoundation 0x19c4cc354 CFRunLoopRunSpecific + 436 24 Foundation 0x19ce99fcc -[NSRunLoop(NSRunLoop) runMode:beforeDate:] + 300 25 libAXSpeechManager.dylib 0x1ac16c94c -[AXSpeechThread main] + 264 26 Foundation 0x19cfc66e4 __NSThread__start__ + 984 27 libsystem_pthread.dylib 0x19c1602c0 _pthread_body + 128 28 libsystem_pthread.dylib 0x19c160220 _pthread_start + 44 29 libsystem_pthread.dylib 0x19c163cdc thread_start + 4I change my code like this, It still has the same problem- (void)stopSpeech { if (self.synthesizer != nil &amp;&amp; [self.synthesizer isPaused]) { return; } // if ([self.synthesizer isSpeaking]) { // BOOL isSpeech = [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryImmediate]; // if (!isSpeech) { // [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryWord]; // } // } if (self.synthesizer != nil) { [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryImmediate]; // if (!isSpeech) { // [self.synthesizer stopSpeakingAtBoundary:AVSpeechBoundaryWord]; // } self.stopBlock ? self.stopBlock() : nil; } }

Incident Identifier: 4C22F586-71FB-4644-B823-A4B52D158057 CrashReporter Key: adc89b7506c09c2a6b3a9099cc85531bdaba9156 Hardware Model: Mac16,10 Process: PRISMLensCore [16561] Path: /Applications/PRISMLens.app/Contents/Resources/app.asar.unpacked/node_modules/core-node/PRISMLensCore.app/PRISMLensCore Identifier: com.prismlive.camstudio Version: (null) ((null)) Code Type: ARM-64 Parent Process: ? [16560] Date/Time: (null) OS Version: macOS 15.4 (24E5228e) Report Version: 104 Exception Type: EXC_CRASH (SIGABRT) Exception Codes: 0x00000000 at 0x0000000000000000 Crashed Thread: 34 Application Specific Information: *** Terminating app due to uncaught exception 'NSInvalidArgumentException', reason: '*** -[__NSArrayM insertObject:atIndex:]: object cannot be nil' Thread 34 Crashed: 0 CoreFoundation 0x000000018ba4dde4 0x18b960000 + 974308 (__exceptionPreprocess + 164) 1 libobjc.A.dylib 0x000000018b512b60 0x18b4f8000 + 109408 (objc_exception_throw + 88) 2 CoreFoundation 0x000000018b97e69c 0x18b960000 + 124572 (-[__NSArrayM insertObject:atIndex:] + 1276) 3 Portrait 0x0000000257e16a94 0x257da3000 + 473748 (-[PTMSRResize addAdditionalOutput:] + 604) 4 Portrait 0x0000000257de91c0 0x257da3000 + 287168 (-[PTEffectRenderer initWithDescriptor:metalContext:useHighResNetwork:faceAttributesNetwork:humanDetections:prevTemporalState:asyncInitQueue:sharedResources:] + 6204) 5 Portrait 0x0000000257dab21c 0x257da3000 + 33308 (__33-[PTEffect updateEffectDelegate:]_block_invoke.241 + 164) 6 libdispatch.dylib 0x000000018b739b2c 0x18b738000 + 6956 (_dispatch_call_block_and_release + 32) 7 libdispatch.dylib 0x000000018b75385c 0x18b738000 + 112732 (_dispatch_client_callout + 16) 8 libdispatch.dylib 0x000000018b742350 0x18b738000 + 41808 (_dispatch_lane_serial_drain + 740) 9 libdispatch.dylib 0x000000018b742e2c 0x18b738000 + 44588 (_dispatch_lane_invoke + 388) 10 libdispatch.dylib 0x000000018b74d264 0x18b738000 + 86628 (_dispatch_root_queue_drain_deferred_wlh + 292) 11 libdispatch.dylib 0x000000018b74cae8 0x18b738000 + 84712 (_dispatch_workloop_worker_thread + 540) 12 libsystem_pthread.dylib 0x000000018b8ede64 0x18b8eb000 + 11876 (_pthread_wqthread + 292) 13 libsystem_pthread.dylib 0x000000018b8ecb74 0x18b8eb000 + 7028 (start_wqthread + 8)

Hi, I'm testing DockKit with a very simple setup: I use VNDetectFaceRectanglesRequest to detect a face and then call dockAccessory.track(...) using the detected bounding box. The stand is correctly docked (state == .docked) and dockAccessory is valid. I'm calling .track(...) with a single observation and valid CameraInformation (including size, device, orientation, etc.). No errors are thrown. To monitor this, I added a logging utility – track(...) is being called 10–30 times per second, as recommended in the documentation. However: the stand does not move at all. There is no visible reaction to the tracking calls. Is there anything I'm missing or doing wrong? Is VNDetectFaceRectanglesRequest supported for DockKit tracking, or are there hidden requirements? Would really appreciate any help or pointers – thanks! That's my complete code: extension VideoFeedViewController: AVCaptureVideoDataOutputSampleBufferDelegate { func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection: AVCaptureConnection) { guard let frame = CMSampleBufferGetImageBuffer(sampleBuffer) else { return } detectFace(image: frame) func detectFace(image: CVPixelBuffer) { let faceDetectionRequest = VNDetectFaceRectanglesRequest() { vnRequest, error in guard let results = vnRequest.results as? [VNFaceObservation] else { return } guard let observation = results.first else { return } let boundingBoxHeight = observation.boundingBox.size.height * 100 #if canImport(DockKit) if let dockAccessory = self.dockAccessory { Task { try? await trackRider( observation.boundingBox, dockAccessory, frame, sampleBuffer ) } } #endif } let imageResultHandler = VNImageRequestHandler(cvPixelBuffer: image, orientation: .up) try? imageResultHandler.perform([faceDetectionRequest]) func combineBoundingBoxes(_ box1: CGRect, _ box2: CGRect) -> CGRect { let minX = min(box1.minX, box2.minX) let minY = min(box1.minY, box2.minY) let maxX = max(box1.maxX, box2.maxX) let maxY = max(box1.maxY, box2.maxY) let combinedWidth = maxX - minX let combinedHeight = maxY - minY return CGRect(x: minX, y: minY, width: combinedWidth, height: combinedHeight) } #if canImport(DockKit) func trackObservation(_ boundingBox: CGRect, _ dockAccessory: DockAccessory, _ pixelBuffer: CVPixelBuffer, _ cmSampelBuffer: CMSampleBuffer) throws { // Zähle den Aufruf TrackMonitor.shared.trackCalled() let invertedBoundingBox = CGRect( x: boundingBox.origin.x, y: 1.0 - boundingBox.origin.y - boundingBox.height, width: boundingBox.width, height: boundingBox.height ) guard let device = captureDevice else { fatalError("Kamera nicht verfügbar") } let size = CGSize(width: Double(CVPixelBufferGetWidth(pixelBuffer)), height: Double(CVPixelBufferGetHeight(pixelBuffer))) var cameraIntrinsics: matrix_float3x3? = nil if let cameraIntrinsicsUnwrapped = CMGetAttachment( sampleBuffer, key: kCMSampleBufferAttachmentKey_CameraIntrinsicMatrix, attachmentModeOut: nil ) as? Data { cameraIntrinsics = cameraIntrinsicsUnwrapped.withUnsafeBytes { $0.load(as: matrix_float3x3.self) } } Task { let orientation = getCameraOrientation() let cameraInfo = DockAccessory.CameraInformation( captureDevice: device.deviceType, cameraPosition: device.position, orientation: orientation, cameraIntrinsics: cameraIntrinsics, referenceDimensions: size ) let observation = DockAccessory.Observation( identifier: 0, type: .object, rect: invertedBoundingBox ) let observations = [observation] guard let image = CMSampleBufferGetImageBuffer(sampleBuffer) else { print("no image") return } do { try await dockAccessory.track(observations, cameraInformation: cameraInfo) } catch { print(error) } } } #endif func clearDrawings() { boundingBoxLayer?.removeFromSuperlayer() boundingBoxSizeLayer?.removeFromSuperlayer() } } } } @MainActor private func getCameraOrientation() -> DockAccessory.CameraOrientation { switch UIDevice.current.orientation { case .portrait: return .portrait case .portraitUpsideDown: return .portraitUpsideDown case .landscapeRight: return .landscapeRight case .landscapeLeft: return .landscapeLeft case .faceDown: return .faceDown case .faceUp: return .faceUp default: return .corrected } }

From tensorflow-metal example: Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: ) I know that Apple silicon uses UMA, and that memory copies are typical of CUDA, but wouldn't the GPU memory still be faster overall? I have an iMac Pro with a Radeon Pro Vega 64 16 GB GPU and an Intel iMac with a Radeon Pro 5700 8 GB GPU. But using tensorflow-metal is still WAY faster than using the CPUs. Thanks for that. I am surprised the 5700 is twice as fast as the Vega though.

*I can't put the attached file in the format, so if you reply by e-mail, I will send the attached file by e-mail. Dear Apple AI Research Team, My name is Gong Jiho (“Hem”), a content strategist based in Seoul, South Korea. Over the past few months, I conducted a user-led AI experiment entirely within ChatGPT — no code, no backend tools, no plugins. Through language alone, I created two contrasting agents (Uju and Zero) and guided them into a co-authored modular identity system using prompt-driven dialogue and reflection. This system simulates persona fusion, memory rooting, and emotional-logical alignment — all via interface-level interaction. I believe it resonates with Apple’s values in privacy-respecting personalization, emotional UX modeling, and on-device learning architecture. Why I’m Reaching Out I’d be honored to share this experiment with your team. If there is any interest in discussing user-authored agent scaffolding, identity persistence, or affective alignment, I’d love to contribute — even informally. ⚠ A Note on Language As a non-native English speaker, my expression may be imperfect — but my intent is genuine. If anything is unclear, I’ll gladly clarify. 📎 Attached Files Summary Filename → Description Hem_MultiAI_Report_AppleAI_v20250501.pdf → Main report tailored for Apple AI — narrative + structural view of emotional identity formation via prompt scaffolding Hem_MasterPersonaProfile_v20250501.json → Final merged identity schema authored by Uju and Zero zero_sync_final.json / uju_sync_final.json → Persona-level memory structures (logic / emotion) 1_0501.json ~ 3_0501.json → Evolution logs of the agents over time GirlfriendGPT_feedback_summary.txt → Emotional interpretation by external GPT hem_profile_for_AI_vFinal.json → Original user anchor profile Warm regards, Gong Jiho (“Hem”) Seoul, South Korea

When calling NLTagger.requestAssets with some languages, it hangs indefinitely both in the simulator and a device. This happens consistently for some languages like greek. An example call is NLTagger.requestAssets(for: .greek, tagScheme: .lemma). Other languages like french return immediately. I captured some logs from Console and found what looks like the repeated attempts to download the asset. I would expect the call to eventually terminate, either loading the asset or failing with an error.

Introduced in the Keynote was the 3D Lock Screen images with the kangaroo: https://9to5mac.com/wp-content/uploads/sites/6/2025/06/3d-lock-screen-2.gif I can't see any mention on if this effect is available for developers with an API to convert flat 2D photos in to the same 3D feeling image. Does anyone know if there is an API?

How do I test the new RecognizeDocumentRequest API. Reference: https://www.youtube.com/watch?v=H-GCNsXdKzM I am running Xcode Beta, however I only have one primary device that I cannot install beta software on. Please provide a strategy for testing. Will simulator work? The new capability is critical to my application, just what I need for structuring document scans and extraction. Thank you.

Hey guys 👋 I’ve been thinking about a feature idea for iOS that could totally change the way we interact with apps like Twitter/X. Imagine if we could define our own recommendation algorithm, and have an AI on the iPhone that replaces the suggested tweets in the feed with ones that match our personal interests — based on public tweets, and without hacking anything. Kinda like a personalized "AI skin" over the app that curates content you actually care about. Feels like this would make content way more relevant and less algorithmically manipulative. Would love to know what you all think — and if Apple could pull this off 🔥

Hi, I'm looking for the best way to use MLX models, particularly those I've fine-tuned, within a React Native application on iOS devices. Is there a recommended integration path or specific API for bridging MLX's capabilities to React Native for deployment on iPhones and iPads?

During testing the “Bringing advanced speech-to-text capabilities to your app” sample app demonstrating the use of iOS 26 SpeechAnalyzer, I noticed that the language model for the English locale was presumably already downloaded. Upon checking the documentation of AssetInventory, I found out that indeed, the language model can be preinstalled on the system. Can someone from the dev team share more info about what assets are preinstalled by the system? For example, can we safely assume that the English language model will almost certainly be already preinstalled by the OS if the phone has the English locale?

At WWDC25 we launched a new type of Lab event for the developer community - Group Labs. A Group Lab is a panel Q&A designed for a large audience of developers. Group Labs are a unique opportunity for the community to submit questions directly to a panel of Apple engineers and designers. Here are the highlights from the WWDC25 Group Lab for Machine Learning and AI Frameworks. What are you most excited about in the Foundation Models framework? The Foundation Models framework provides access to an on-device Large Language Model (LLM), enabling entirely on-device processing for intelligent features. This allows you to build features such as personalized search suggestions and dynamic NPC generation in games. The combination of guided generation and streaming capabilities is particularly exciting for creating delightful animations and features with reliable output. The seamless integration with SwiftUI and the new design material Liquid Glass is also a major advantage. When should I still bring my own LLM via CoreML? It's generally recommended to first explore Apple's built-in system models and APIs, including the Foundation Models framework, as they are highly optimized for Apple devices and cover a wide range of use cases. However, Core ML is still valuable if you need more control or choice over the specific model being deployed, such as customizing existing system models or augmenting prompts. Core ML provides the tools to get these models on-device, but you are responsible for model distribution and updates. Should I migrate PyTorch code to MLX? MLX is an open-source, general-purpose machine learning framework designed for Apple Silicon from the ground up. It offers a familiar API, similar to PyTorch, and supports C, C++, Python, and Swift. MLX emphasizes unified memory, a key feature of Apple Silicon hardware, which can improve performance. It's recommended to try MLX and see if its programming model and features better suit your application's needs. MLX shines when working with state-of-the-art, larger models. Can I test Foundation Models in Xcode simulator or device? Yes, you can use the Xcode simulator to test Foundation Models use cases. However, your Mac must be running macOS Tahoe. You can test on a physical iPhone running iOS 18 by connecting it to your Mac and running Playgrounds or live previews directly on the device. Which on-device models will be supported? any open source models? The Foundation Models framework currently supports Apple's first-party models only. This allows for platform-wide optimizations, improving battery life and reducing latency. While Core ML can be used to integrate open-source models, it's generally recommended to first explore the built-in system models and APIs provided by Apple, including those in the Vision, Natural Language, and Speech frameworks, as they are highly optimized for Apple devices. For frontier models, MLX can run very large models. How often will the Foundational Model be updated? How do we test for stability when the model is updated? The Foundation Model will be updated in sync with operating system updates. You can test your app against new model versions during the beta period by downloading the beta OS and running your app. It is highly recommended to create an "eval set" of golden prompts and responses to evaluate the performance of your features as the model changes or as you tweak your prompts. Report any unsatisfactory or satisfactory cases using Feedback Assistant. Which on-device model/API can I use to extract text data from images such as: nutrition labels, ingredient lists, cashier receipts, etc? Thank you. The Vision framework offers the RecognizeDocumentRequest which is specifically designed for these use cases. It not only recognizes text in images but also provides the structure of the document, such as rows in a receipt or the layout of a nutrition label. It can also identify data like phone numbers, addresses, and prices. What is the context window for the model? What are max tokens in and max tokens out? The context window for the Foundation Model is 4,096 tokens. The split between input and output tokens is flexible. For example, if you input 4,000 tokens, you'll have 96 tokens remaining for the output. The API takes in text, converting it to tokens under the hood. When estimating token count, a good rule of thumb is 3-4 characters per token for languages like English, and 1 character per token for languages like Japanese or Chinese. Handle potential errors gracefully by asking for shorter prompts or starting a new session if the token limit is exceeded. Is there a rate limit for Foundation Models API that is limited by power or temperature condition on the iPhone? Yes, there are rate limits, particularly when your app is in the background. A budget is allocated for background app usage, but exceeding it will result in rate-limiting errors. In the foreground, there is no rate limit unless the device is under heavy load (e.g., camera open, game mode). The system dynamically balances performance, battery life, and thermal conditions, which can affect the token throughput. Use appropriate quality of service settings for your tasks (e.g., background priority for background work) to help the system manage resources effectively. Do the foundation models support languages other than English? Yes, the on-device Foundation Model is multilingual and supports all languages supported by Apple Intelligence. To get the model to output in a specific language, prompt it with instructions indicating the user's preferred language using the locale API (e.g., "The user's preferred language is en-US"). Putting the instructions in English, but then putting the user prompt in the desired output language is a recommended practice. Are larger server-based models available through Foundation Models? No, the Foundation Models API currently only provides access to the on-device Large Language Model at the core of Apple Intelligence. It does not support server-side models. On-device models are preferred for privacy and for performance reasons. Is it possible to run Retrieval-Augmented Generation (RAG) using the Foundation Models framework? Yes, it is possible to run RAG on-device, but the Foundation Models framework does not include a built-in embedding model. You'll need to use a separate database to store vectors and implement nearest neighbor or cosine distance searches. The Natural Language framework offers simple word and sentence embeddings that can be used. Consider using a combination of Foundation Models and Core ML, using Core ML for your embedding model.