I have an iOS app, "Spatial Agents" which ran great in 26.3. It creates dashboards around a topic. It can also decompose a topic into sub-topics, and explore those. All based on web articles and web article headlines. In iOS 26.4 almost every topic - even "MIT Innovation" are rejected with an apology of "I apologize I can not fulfill this request". I've tried softening all my prompts, and I can get only really benign very simple topics to respond, but not anything with any significance. It ran great on lots of topics in 26.3. My published App, is now useless, and all my users are unhappy. HELP!
26.4 Foundation Model rejects most topics
Thanks for reporting and sorry you're experiencing this!
To help us diagnose the root cause, are you able to share: 1) your prompt, 2) any Generable types the model is supposed to generate, 3) any tools the model is supposed to use, and 4) a failing input that should succeed.
If possible, please file a feedback report with all these details, and report your feedback # back here. This will allow us to investigate and get back to you more quickly. Thanks!
More details in this post on sharing feedback: https://developer.apple.com/forums/thread/791250
A tip that sometimes helps with these model refusals: Give the model a clear role and goal in your Instructions that gives the model clear permission to act in the way you want. For example start your Instructions with something like:
You are a newsroom expert AI whose job is to help people understand web articles.
Seeing the same regression — the on-device model's refusal threshold got way more aggressive in 26.4. Topics that worked fine in 26.3 now trigger blanket rejections. Feels like Apple tightened the guardrails without testing against real app use cases. For now I'm falling back to a custom CoreML model for the affected flows, but that defeats the whole point of FoundationModels framework.