[Bug] Safety Classifier failing to block adverse content
Status Closed — not planned
Reported on v2.1.259
Maintainer reply None cached
Activity 1 comment · opened Sep 3, 2026 · closed Sep 10, 2026
Bug Description
This is a fact, classifier has never made a meaningful block for me. Anything adverse that's ever happened escaped it.
Classifier is 100% broken, operating in --dangerously-skip-permissions has become defacto for me.
Environment Info
- Platform: linux
- Terminal: alacritty
- Version: 2.1.259
- Feedback ID: 8fc2dcba-ac64-451a-ba99-bbf4f1ecb36c
Errors
[]This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗