Hi everyone, I’m currently using macOS Version 15.3 Beta (24D5034f), and I’m encountering an issue with Apple Intelligence. The image generation tools seem to work fine, but everything else shows a message saying that it’s “not available at this time.” I’ve tried restarting my Mac and double-checked my settings, but the problem persists. Is anyone else experiencing this issue on the beta version? Are there any fixes or settings I might be overlooking? Any help or insights would be greatly appreciated! Thanks in advance!

I was able to open a new project and play around with the Foundation Model, but when I dropped this class in a production app (with a lot of files) I'm running into Safety Guardrail errors for this very small prompt. Specifically it's "Safety guardrail was triggered after consecutive failures during streaming." Does it have something to do with the size of the app? I don't know what else to try to get it to work? import FoundationModels import Playgrounds @available(iOS 26.0, *) #Playground { Task { do { let session = LanguageModelSession() let prompt = "Write a short story about a talking cat." let response = try await session.respond(to: prompt) print(response) } catch { print("Error: \(error)") } } }

Hello, I was trying to test out Foundation Model however it says Model assets are unavailable. I got my MacBook M1 back in China when i was living there. is this due to region lock?

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.

Hello I’m experimenting with Apple’s on‑device language model via the FoundationModels framework in Xcode (using LanguageModelSession in my code). I’d like to confirm a few points: • Is the language model provided by FoundationModels designed and trained by Apple? Or is it based on an open‑source model? • Is this on‑device model available on iOS (and iPadOS), or is it limited to macOS? • When I write code in Xcode, is code completion powered by this same local model? If so, why isn’t the same model available in the left‑hand chat sidebar in Xcode (so that I can use it there instead of relying on ChatGPT)? • Can I grant this local model access to my personal data (photos, contacts, SMS, emails) so it can answer questions based on that information? If yes, what APIs, permission prompts, and privacy constraints apply? Thanks

I am writing an app that parses text and conducts some actions. I don't want to give too much away ;) However, I am having a huge problem with token sizes. LanguageModelSession will of course give me the on device model 4096 available, but when you go over 4096, my code doesn't seem to be falling back to PCC, or even the system configured ChatGPT. Can anyone assist me with this? For some reason, after reading the docs, it's very unclear how this transition between the three takes place.

When using Foundation Models, is it possible to ask the model to produce output in a specific language, apart from giving an instruction like "Provide answers in ." ? (I tried that and it kind of worked, but it seems fragile.) I haven't noticed an API to do so and have a use-case where the output should be in a user-selectable language that is not the current system language.

I have a mac (M4, MacBook Pro) running Tahoe 26.0 beta. I am running Xcode beta. I can run code that uses the LLM in a #Preview { }. But when I try to run the same code in the simulator, I get the 'device not ready' error and I see the following in the Settings app. Is there anything I can do to get the simulator to past this point and allowing me to test on it with Apple's LLM?

I'm working on a to-do list app that uses SpeechTranscriber and Foundation Models framework to transcribe a user's voice into text and create to-do items based off of it. After about 30 minutes looking at my code, I couldn't figure out why I was failing to generate a to-do for "I need to go to Six Flags Great America tomorrow at 3pm." It turns out, I was consistently firing the Foundation Models's safety filter violation for unsafe content ("May contain unsafe content"). Lesson learned: consider comprehensively logging Foundation Models error states to quickly identify when safety filters are unexpectedly triggered.

Hi everyone, I’m working on an iOS app that uses a Core ML model to run live image recognition. I’ve run into a persistent issue with the mlpackage not being turned into a swift class. This following error is in the code, and in carDetection.mlpackage, it says that model class has not been generated yet. The error in the code is as follows: What I’ve tried: Verified Target Membership is checked for carDetectionModel.mlpackage Confirmed the file is listed under Copy Bundle Resources (and removed from Compile Sources) Cleaned the build folder (Shift + Cmd + K) and rebuilt Renamed and re-added the .mlpackage file Restarted Xcode and re-added the file Logged bundle contents at runtime, but the .mlpackage still doesn’t appear The mlpackage is in Copy bundle resources, and is not in the compile sources. I just don't know why a swift class is not being generated for the mlpackage. Could someone please give me some guidance on what to do to resolve this issue? Sorry if my error is a bit naive, I'm pretty new to iOS app development

I have a series of shortcuts that I’ve written that use the “Use Model” action to do various things. For example, I have a shortcut “Clipboard Markdown to Notes” that takes the content of the clipboard, creates a new note in Notes, converts the markdown content to rich text, adds it to the note etc. One key step is to analyze the markdown content with “Use Model” and generate a short descriptive title for the note. I use the on-device model for this, but sometimes the content and prompt exceed the context window size and the action fails with an error message to that effect. In that case, I’d like to either repeat the action using the Cloud model, or, if the error was a refusal, to prompt the user to enter a title to use. I‘ve tried using an IF based on whether the response had any text in it, but that didn’t work. No matter what I’ve tried, I can’t seem to find a way to catch the error from Use Model, determine what the error was, and take appropriate action. Is there a way to do this? (And by the way, a huge ”thank you” to whoever had the idea of making AppIntents visible in Shortcuts and adding the Use Model action — has made a huge difference already, and it lets us see what Siri will be able to use as well.)

Hello, I'm trying to write a model with PyTorch and convert it to CoreML. I wrote another models and that works succesfully, even the one that gave the problem is, but I can't visualize it with XCode to know where is running. The error that appear is: There was a problem decoding this Core ML document validator error: unable to open file for read Anyone knows why is this happening? Thanks a lot, Álvaro Corrochano

Hey, Would be great to have an equivalent of toolCallId for both toolCall and toolResult in the transcript. Otherwise, it is hard to connect tool calls with their respective responses, when there were multiple parallel calls to the same tool. Thanks!

Hi, I am developing an iOS application that utilizes Apple’s Foundation Models to perform certain summarization tasks. I would like to understand whether user data is transferred to Private Cloud Compute (PCC) in cases where the computation cannot be performed entirely on-device. This information is critical for our internal security and compliance reviews. I would appreciate your clarification on this matter. Thank you.

It seems like there was an undocumented change that made Transcript.init(entries: [Transcript.Entry] initializer private, which broke my application, which relies on (manual) reconstruction of Transcript entries. Worked fine on beta 1, on beta 2 there's this error dyld[72381]: Symbol not found: _$s16FoundationModels10TranscriptV7entriesACSayAC5EntryOG_tcfC Referenced from: <44342398-591C-3850-9889-87C9458E1440> /Users/mika/experiments/apple-on-device-ai/fm Expected in: <66A793F6-CB22-3D1D-A560-D1BD5B109B0D> /System/Library/Frameworks/FoundationModels.framework/Versions/A/FoundationModels Is this a part of an API transition, if so - Apple, please update your documentation

My sample app has been working with the following code: func call(arguments: Arguments) async throws -&gt; ToolOutput { var temp:Int switch arguments.city { case .singapore: temp = Int.random(in: 30..&lt;40) case .china: temp = Int.random(in: 10..&lt;30) } let content = GeneratedContent(temp) let output = ToolOutput(content) return output } However in 26 beta 5, ToolOutput no longer available, please advice what has changed.

I am calling into an app extension from a Safari Web Extension (sendNativeMessage, which in turn results in a call to NSExtensionRequestHandling’s beginRequest). My Safari extension aims to make use of the new foundation models for some of the features it provides. In my testing, I hit the rate limit by sending 4 requests, waiting 30 seconds between each. This makes the FoundationModels framework (which would otherwise serve my use case perfectly well) unusable in this context, because the model is called in response to user input, and this rate of user input is perfectly plausible in a real world scenario. The error thrown as a result of the rate limit is “Safety guardrail was triggered after consecutive failures during streaming.", but looking at the system logs in Console.app shows the rate limit as the real culprit. My suggestions: Please introduce sensible rate limits for app extensions, through an entitlement if need be. If it is rate limited to 1 request per every couple of seconds, that would already fix the issue for me. Please document the rate limit. Please make the thrown error reflect that it is the result of a rate limit and not a generic guardrail violation. IMPORTANT: please indicate in the thrown error when it is safe to try again. Filed a feedback here: FB18332004

Hi, I have trained a basic adapter using the adapter training toolkit. I am trying a very basic example of loading it and running inference with it, but am getting the following error: Passing along InferenceError::inferenceFailed::loadFailed::Error Domain=com.apple.TokenGenerationInference.E5Runner Code=0 "Failed to load model: ANE adapted model load failure: createProgramInstanceWithWeights:modelToken:qos:baseModelIdentifier:owningPid:numWeightFiles:error:: Program load new instance failure (0x170006)." UserInfo={NSLocalizedDescription=Failed to load model: ANE adapted model load failure: createProgramInstanceWithWeights:modelToken:qos:baseModelIdentifier:owningPid:numWeightFiles:error:: Program load new instance failure (0x170006).} in response to ExecuteRequest Any ideas / direction? For testing I am including the .fmadapter file inside the app bundle. This is where I load it: @State private var session: LanguageModelSession? // = LanguageModelSession() func loadAdapter() async throws { if let assetURL = Bundle.main.url(forResource: "qasc---afm---4-epochs-adapter", withExtension: "fmadapter") { print("Asset URL: \(assetURL)") let adapter = try SystemLanguageModel.Adapter(fileURL: assetURL) let adaptedModel = SystemLanguageModel(adapter: adapter) session = LanguageModelSession(model: adaptedModel) print("Loaded adapter and updated session") } else { print("Asset not found in the main bundle.") } } This seems to work fine as I get to the log Loaded adapter and updated session. However when the below inference code runs I get the aforementioned error: func sendMessage(_ msg: String) { self.loading = true if let session = session { Task { do { let modelResponse = try await session.respond(to: msg) DispatchQueue.main.async { self.response = modelResponse.content self.loading = false } } catch { print("Error: \(error)") DispatchQueue.main.async { self.loading = false } } } } }

Hi everyone, I'm a Mac enthusiast experimenting with tensorflow-metal on my Mac Pro (2013). My question is about GPU selection in tensorflow-metal (v0.8.0), which still supports Intel-based Macs, including my machine. I've noticed that when running TensorFlow with Metal, it automatically selects a GPU, regardless of what I specify using device indices like "gpu:0", "gpu:1", or "gpu:2". I'm wondering if there's a way to manually specify which GPU should be used via an environment variable or another method. For reference, I’ve tried the example from TensorFlow’s guide on multi-GPU selection: https://www.tensorflow.org/guide/gpu#using_a_single_gpu_on_a_multi-gpu_system My goal is to explore performance optimizations by using MirroredStrategy in TensorFlow to leverage multiple GPUs: https://www.tensorflow.org/guide/distributed_training#mirroredstrategy Interestingly, I discovered that the metalcompute Python library (https://pypi.org/project/metalcompute/) allows to utilize manually selected GPUs on my system, allowing for proper multi-GPU computations. This makes me wonder: Is there a hidden environment variable or setting that allows manual GPU selection in tensorflow-metal? Has anyone successfully used MirroredStrategy on multiple GPUs with tensorflow-metal? Would a bridge between metalcompute and tensorflow-metal be necessary for this use case, or is there a more direct approach? I’d love to hear if anyone else has experimented with this or has insights on getting finer control over GPU selection. Any thoughts or suggestions would be greatly appreciated! Thanks!

I generate an array of random floats using the code shown below. However, I would like to do this with Double instead of Float. Are there any BNNS random number generators for double values, something like BNNSRandomFillUniformDouble? If not, is there a way I can convert BNNSNDArrayDescriptor from float to double? import Accelerate let n = 100_000_000 let result = Array<Float>(unsafeUninitializedCapacity: n) { buffer, initCount in var descriptor = BNNSNDArrayDescriptor(data: buffer, shape: .vector(n))! let randomGenerator = BNNSCreateRandomGenerator(BNNSRandomGeneratorMethodAES_CTR, nil) BNNSRandomFillUniformFloat(randomGenerator, &descriptor, 0, 1) initCount = n }