[Feature Request] Implement semantic content detection for safety moderation instead of keyword-based filtering
Status Open
Reported on v2.1.258
Maintainer reply None cached
Activity 0 comments · opened Sep 2, 2026
Bug Description
the safeguard team needs to do better at detecting keywords abt what is actually a threat or not. U would've thought the best LLM company would be able to detect those contents beyond keywords and use sematic detections instead.
Environment Info
- Platform: linux
- Terminal: vscode
- Version: 2.1.258
- Feedback ID: 7bf2c586-c4ca-4327-9bde-d8f65ae6f7aa
Errors
[]