Content Safety Classifier
Position Content Safety Classifier

ML-10

Content Safety Classifier

Build a transparent moderation aid with category-specific thresholds, appeal/human review, subgroup analysis, and a limitations card.

  • Status: planned
  • Proof: code
  • Tier: focused-exhibit
  • Roles: ai-engineer, backend-engineer

This project is planned. It is published for transparency about what is being built. Nothing on this page claims a result that has been measured.

← All projects