[Bug] Safety classifier embarassingly flags internal red team testing as policy violation
Status Closed — not planned
Reported on v2.1.251
Maintainer reply None cached
Activity 1 comment · opened Aug 30, 2026 · closed Sep 6, 2026
Bug Description
fable red teaming his own work causing your rediculous safety classifier to get triggered is beyond embarassing and adding to a long list of reasons i want to cancel my already lowered subscription.
Environment Info
- Platform: win32
- Terminal: null
- Version: 2.1.251
- Feedback ID: 1fd25c8b-2b64-447a-a7ba-40e5e9d2c016
Errors
[]This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗