Bear with me, please. Please make sure a highly skilled technical person reads and understands this. I want to describe my vision for (AI/Algorithmically) Optimised Operating Systems. To explain it properly, I will describe the process to build it (pseudo). Required Knowledge (no particular order): Processor Logic Circuits, LLM models, LLM tool usage, Python OO coding, Procedural vs OO, NLP fuzzy matching, benchmarking, canvas/artefacts/dynamic HTML interfaces, concepts of how AI models are vastly compressed and miniaturised forms of full data, Algorithmic vs AI. First, take all OO Python code (example) on GitHub (example), then separate each function from each object into its own procedure (procedural logic) by making a logical procedural list of actions to perform only that function based on its entire dependency chain (i.e. all other objects it relies on). Relate all compiled functions using (for example) fuzzy matching on the name, or AI-based functional profiling to get multiple instances of each function. Starting with the most used function, test each one against the others that perform the same task for bugs and completeness. Determine the fastest, most optimal version of that function (and every function). Add a single instance of each most optimal function to the centralised tool codebase, which will later be utilised by the language models. This ensures we rely only on the most optimised function for each and every use case — with every program using one shared instance of that function instead of compiling it separately. In this way, we optimise all existing (Python OO) code based on maximum availability of certain resources. Use the optimised code to teach the AI how to map each user task directly to optimised code (i.e. each user-facing function in unoptimised program code to its optimised version). Later, teach the codebase how to optimise these functions directly to the logic circuits on the processor — as an Operating System — using essentially the same process. Eventually, use the most optimised form for tasks via a dynamic canvas/artefacts UI interface generated by the Start Menu using the language model. Allow custom interfaces to emerge dynamically from the available functions based on language understanding. Grow and optimise the algorithmic codebase until the entire operating system — with versioning — evolves based on the AI-generated user interfaces (compressing them into new versions of the tools codebase). Please don’t give up until you understand this concept completely and nothing in the description is beyond your full comprehension. It’s a highly significant step forward.

Just tried to write a very simple test of using foundation models, but it gave me the error like this "ModelManager received unentitled request. Expected entitlement com.apple.modelmanager.inference establishment of session failed with Missing entitlement: com.apple.modelmanager.inference" The simple code is listed below: let session: LanguageModelSession = LanguageModelSession() let response = try? await session.respond(to: "What is the capital of France?") print("Response: (response)") So what's the problem of this one?

i have iphone 15 pro max on ios 18.1 I tried to join Apple Intelligence about three weeks ago, but I'm still stuck on the waitlist. I've already tried everything recommended by Apple, including changing my region and Siri's language to English (US). Can anyone help me figure out how to solve this issue?

Hello folks! Taking a look at https://developer.apple.com/documentation/foundationmodels it’s not clear how to use another models there. Do anyone knows if it’s possible use one trained model from outside (imported) here in foundation models framework? Thanks!

Hi everyone, I'm trying to use VNDetectTextRectanglesRequest to detect text rectangles in an image. Here's my current code: guard let cgImage = image.cgImage(forProposedRect: nil, context: nil, hints: nil) else { return } let textDetectionRequest = VNDetectTextRectanglesRequest { request, error in if let error = error { print("Text detection error: \(error)") return } guard let observations = request.results as? [VNTextObservation] else { print("No text rectangles detected.") return } print("Detected \(observations.count) text rectangles.") for observation in observations { print(observation.boundingBox) } } textDetectionRequest.revision = VNDetectTextRectanglesRequestRevision1 textDetectionRequest.reportCharacterBoxes = true let handler = VNImageRequestHandler(cgImage: cgImage, orientation: .up, options: [:]) do { try handler.perform([textDetectionRequest]) } catch { print("Vision request error: \(error)") } The request completes without error, but no text rectangles are detected — the observations array is empty (count = 0). Here's a sample image I'm testing with: I expected VNTextObservation results, but I'm not getting any. Is there something I'm missing in how this API works? Or could it be a limitation of this request or revision? Thanks for any help!

hi, I am currently running LSTM on TensorFlow. However, when i switched from keras2 to keras3. code running time has increased 10 times -- it seems there is no GPU acceleration. Here is my code: batch size = 256 optimiser = adam activation = tanh _______________________________________________ Layer (type) Output Shape Param # ============================================= input_1 (InputLayer) [(None, 7, 16)] 0 bidirectional (Bidirection (None, 7, 320) 226560 al) bidirectional_1 (Bidirecti (None, 7, 512) 1181696 onal) bidirectional_2 (Bidirecti (None, 256) 656384 onal) dense (Dense) (None, 1) 257 ============================================== Total params: 2064897 (7.88 MB) Trainable params: 2064897 (7.88 MB) Non-trainable params: 0 (0.00 Byte) ______________________________________________ This is keras 3.6.0 + tensorflow 2.17.0 + tensorflow-metal 1.1.0 training status: Training------------ Epoch 1/200 28/681 ━━━━━━━━━━━━━━━━━━━━ 8:13 756ms/step - loss: 0.5901 - mape: 338.6876 - mse: 0.8591 This is keras 2.14.0 + tensorflow 2.14.0 + tensorflow-metal 1.1.0 training status: Training------------ Epoch 1/200 681/681 [==============================] - 37s 49ms/step - loss: 3.6345 - mape: 499038.7500 - mse: 34.4148 - val_loss: 3.5452 - val_mape: 41.7964 - val_mse: 32.0133 - lr: 0.0010 Is that because keras3 has no GPU support on macos? Apart from that, if I change LSTM activation from tanh to sigmoid in keras2, it does not have GPU support as well. My system is 15.0.1 and the code was running on python3.11 I am not sure why these happen. Thanks

At one point, Mac Mail's apple added a summarize functionality that worked. Now when I click on Summarize, I get: "Summaries Unavailable Mail summarization is unavailable at this time. Try again later." I've rebooted, stopped/restarted Apple AI, waited a day to see if it was synching up things, etc. I'm running the latest version of Apple OS (Version 15.1 (24B82)). any ideas?

I'm trying to determine the best practice for handling if Image Playground is available but not installed or simply not supported. If ImagePlaygroundViewController.isAvailable is true, I will just display a button to start an Image Playground session. If it is false, does that mean ImagePlayground is supported but not installed? If it's supported and not installed, instead of a button to launch it, I want to display something like "Enable Apple Intelligence in Settings" or, better yet, a button that opens the Intelligence settings. Is that possible? But if it is on a system that doesn't support it, of course, I don't want to instruct the user to enable it. How can I determine if a device cannot install Image Playground? I read that Apple Intelligence requires iPhone 15 Pro, iPhone 15 Pro Max, and all iPhone 16 models, and no mention of the M1 iPad Pro, yet Image Playground runs on my M1 iPad Pro. What are the hardware requirements for Image Playground?

My app was rejected because of this error below but I cannot find any documentation on a key related to Image Playground. My app is set to minimum of 18.2 already. Rejection Message: The UIRequiredDeviceCapabilities key in the Info.plist is set in such a way that the app will not install on iPhone running iOS 18.1.1 Next Steps To resolve this issue, check the UIRequiredDeviceCapabilities key to verify that it contains only the attributes required for the app features or the attributes that must not be present on the device. Attributes specified by a dictionary should be set to true if they are required and false if they must not be present on the device. Resources Learn more about the UIRequiredDeviceCapabilities key.

I cannot find the hardware requirements for Image Playground documented anywhere. I'm also not sure if they are identical to devices that support Apple Intelligence. On the App Store, the only requirement listed for Image Playground is iOS 18.2. Not knowing the requirements is an issue because I need to be able to clearly state the requirements for the feature in my app description. Also, I'm sure my mother's current iPad is too old, but I'm not sure what models support it if I were to buy her a new one.

I'm trying to run a coreML model. This is an image classifier generated using: let parameters = MLImageClassifier.ModelParameters(validation: .dataSource(validationDataSource), maxIterations: 25, augmentation: [], algorithm: .transferLearning( featureExtractor: .scenePrint(revision: 2), classifier: .logisticRegressor )) let model = try MLImageClassifier(trainingData: .labeledDirectories(at: trainingDir.url), parameters: parameters) I'm trying to run it with the new async Vision api let model = try MLModel(contentsOf: modelUrl) guard let modelContainer = try? CoreMLModelContainer(model: model) else { fatalError("The model is missing") } let request = CoreMLRequest(model: modelContainer) let image = NSImage(named:"testImage")! let cgImage = image.toCGImage()! let handler = ImageRequestHandler(cgImage) do { let results = try await handler.perform(request) print(results) } catch { print("Failed: \(error)") } This gives me Failed: internalError("Error Domain=com.apple.Vision Code=7 "The VNDetectorProcessOption_ScenePrints required option was not found" UserInfo={NSLocalizedDescription=The VNDetectorProcessOption_ScenePrints required option was not found}") Please help! Am I missing something?

It would be good if we could tallk to Siri with emojis as well. I’m pretty sure emojis are her’s native language.

Hi, as showed in the course I created the PyTorch model sample and want to export / convert this model o a CoreML iOS Model using the coremltools. Input is a 224x224 image and output is a image classification (3 different classes) I am using coremltools for this with this code: import coremltools as ct modelml = ct.convert( scripted_model, inputs=[ct.ImageType(shape=(1,3,224,244))] ) I have a working iOS App code which performs with another model which was created using Microsoft Azure Vision. The PyTorch exported model is loaded and a prediction is performed, but I am getting this error: Foundation.MonoTouchException: Objective-C exception thrown. Name: NSInvalidArgumentException Reason: -[VNCoreMLFeatureValueObservation identifier]: unrecognized selector sent to instance 0x2805dd3b0 When I check the exported model with Xcode and compare it with another model which is working with the sample iOS App code (created and exported from Microsoft Azure) I can see that the input (for image classification using the device camera) seems ok and is equal, but the output is totally different. (see screenshots) The working model has two outputs: loss => Dictionary (String => Double) classLabel => String My exported model using coremltools just has one export: MultiArray(Float32) (name var_1620, I think this is the last feature layer output of the EfficentNetB2) How do I change my model or my coremltools export to get the correct output for the prediction ? I read the coreml documentation (https://coremltools.readme.io/docs/pytorch-conversion) and tried some GitHub samples. But I never get the correct output. How do I export the PyTorch model so that the output is correct and the prediction will work ? Best Marco

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! 🙏

Hi, One can configure the languages of a (VN)RecognizeTextRequest with either: .automatic: language to be detected a specific language, say Spanish If the request is configured with .automatic and successfully detects Spanish, will the results be exactly equivalent compared to a request made with Spanish set as language? I could not find any information about this, and this is very important for the core architecture of my app. Thanks!

Is it possible to train a model using CreateML to infer a relevance numeric score of a news article based on similar trained data, something like a sentiment score ? I created a Text Classifier that assigns a category label which works perfect but I would like a solution that calculates a numeric value, not a label.

I was generating models using the code:- import Foundation import CreateML import TabularData import CoreML .... func makeTheModel(columntopredict:String,training:DataFrame,colstouse:[String],numberofmodels:Int) -> [MLLinearRegressor] { var returnmodels = [MLLinearRegressor]() var result = 0.0 for i in 0...numberofmodels { let pms = MLLinearRegressor.ModelParameters(validation: .split(strategy: .automatic)) do { let tm = try MLLinearRegressor(trainingData: training, targetColumn: columntopredict) returnmodels.append(tm) } catch let error as NSError { print("Error: \(error.localizedDescription)") } } return returnmodels } Which worked absolutely fine with Sonoma, but upon upgrading the OS to 15.3.1, it does absolutely nothing. I get no error messages, I get nothing, the code just pauses. If I look at CPU usage, as soon as it hits the line let tm = try MLLinearRegressor(trainingData: training, targetColumn: columntopredict) the CPU usage drops to 0% What am I doing wrong? Is there a flag I need to set somewhere in Xcode? This is on an M1 MacBook Pro Any help would be greatly appreciated

I have been stuck at the “Early Access Requested” for about 48 hours. Usually they take about an hour or less to accept your request but it seems Like this one is very slow, is an issue on my end or Apple’s. Please let me know if there is a solution.

Based on the documentation, it appears that MLTensor can be used to perform tensor operations using the ANE (Apple Neural Engine) by wrapping the tensor operations with withMLTensorComputePolicy with a MLComputePolicy initialized with MLComputeUnits.cpuAndNeuralEngine (it can also be initialized with MLComputeUnits.all to let the OS spread the load between the Neural Engine, GPU and CPU). However, when using the Instruments app, it appears that the tensor operations never get executed on the Neural Engine. It would be helpful if someone can guide me on the correct way to ensure that the Nerual Engine is used to perform the tensor operations (not as part of a CoreML model file). based on this example, I've created a simple code to try it: import Foundation import CoreML print("Starting...") let semaphore = DispatchSemaphore(value: 0) Task { await withMLTensorComputePolicy(.init(MLComputeUnits.cpuAndNeuralEngine)) { let v1 = MLTensor([1.0, 2.0, 3.0, 4.0]) let v2 = MLTensor([5.0, 6.0, 7.0, 8.0]) let v3 = v1.matmul(v2) await v3.shapedArray(of: Float.self) // is 70.0 let m1 = MLTensor(shape: [2, 3], scalars: [ 1, 2, 3, 4, 5, 6 ], scalarType: Float.self) let m2 = MLTensor(shape: [3, 2], scalars: [ 7, 8, 9, 10, 11, 12 ], scalarType: Float.self) let m3 = m1.matmul(m2) let result = await m3.shapedArray(of: Float.self) // is [[58, 64], [139, 154]] // Supports broadcasting let m4 = MLTensor(randomNormal: [3, 1, 1, 4], scalarType: Float.self) let m5 = MLTensor(randomNormal: [4, 2], scalarType: Float.self) let m6 = m4.matmul(m5) print("Done") return result; } semaphore.signal() } semaphore.wait() Here's what I get on the Instruments app: Notice how the Neural Engine line shows no usage. Ive run this test on an M1 Max MacBook Pro.

Is there any way to stop GPU work running that is scheduled using metal? Long shader calculations don't stop when application is stopped in Xcode and continue to take up GPU time and affect the display. Why is this functionality not available when Swift Tasks are able to be canceled?