[Bug] Anthropic API returning safety filters on legitimate jiu jitsu biometric content

Open 💬 2 comments Opened Jun 12, 2026 by blakecrosley

Bug Description
I'm working on a jiu jitsu app with human biometric modeling, what is going on. I'm getting safety filtered on benign things.

Environment Info

  • Platform: darwin
  • Terminal: ghostty
  • Version: 2.1.174
  • Feedback ID: a082a67f-a2d6-4fe5-ac1d-d17cba0ec3a4

Errors

[]

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗