>Also, the asymmetric treatment of demographic groups by OpenAI content moderation system seems to persist, whereby derogatory comments about some demographic groups are flagged as hateful while the exact same comments about other demographic groups are not labeled as hateful.
>Also, the asymmetric treatment of demographic groups by OpenAI content moderation system seems to persist, whereby derogatory comments about some demographic groups are flagged as hateful while the exact same comments about other demographic groups are not labeled as hateful.
Emphasis not mine.