axiom-foundation-models-diag
Foundation Models Diagnostics
Overview
Foundation Models issues manifest as context window exceeded errors, guardrail violations, slow generation, availability failures, and unexpected output. Core principle 80% of Foundation Models problems stem from misunderstanding model capabilities (3B parameter device-scale model, not world knowledge), context limits (4096 tokens), or availability requirements—not framework bugs.
Red Flags — Suspect Foundation Models Issue
If you see ANY of these, suspect a Foundation Models misunderstanding, not framework breakage:
- Generation takes >5 seconds
- Error:
exceededContextWindowSize - Error:
guardrailViolation - Error:
unsupportedLanguageOrLocale - Model gives hallucinated/wrong output
- UI freezes during generation
- Feature works in simulator but not on device
- ❌ FORBIDDEN "Foundation Models is broken, we need a different AI"
- Foundation Models powers Apple Intelligence across millions of devices
- Wrong output = wrong use case (world knowledge vs summarization)
More from megastep/codex-skills
ads-competitor
>
25ads-meta
>
15ads-tiktok
>
10code-reviewer
Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.
9axiom-app-store-submission
Use when preparing ANY app for App Store submission - enforces pre-flight checklist, rejection prevention, privacy compliance, and metadata completeness to prevent common App Store rejections
8axiom-axe-ref
Use when automating iOS Simulator UI interactions beyond simctl capabilities. Reference for AXe CLI covering accessibility-based tapping, gestures, text input, screenshots, video recording, and UI tree inspection.
8