Foundation Models flags 'Six Flags Great America' as unsafe

Question

Created 1d

Replies 1

Boosts 1

Participants 2

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.

Boost

Answer 1

sashamoroz OP

1d

Hello Benjamin,

I hope you’re doing well. Several posts by the developers, including myself, have raised concerns about an issue that seems to have arisen since installing iOS 26 Beta 3. Specifically, FoundationModels is intermittently throwing guardrail violations on otherwise harmless prompts.

For example, Apple’s own sample app from the “Foundation Code-Along” session now fails with the same error.

FoundationModels guardrailViolation on Beta 3

Community members on the forums have tested a variety of queries and found wildly inconsistent results—asking “What’s the population of New York?” succeeds, whereas “What’s the population of Sweden?” triggers a guardrailViolation or a GenerationError (see these threads for details):

"FoundationModels GenerationError error 2" on iOS 26 beta 3

So far, the only official responses have been generic reminders about prompt safety, which don’t explain why simple factual questions are being blocked.

Given Apple’s two-week beta cadence, I’m optimistic that this behavior will be addressed in the next release.

1