minus-squareokr765@lemmy.okr765.comtoAsklemmy@lemmy.ml•AI Moderators. What do you think?linkfedilinkEnglisharrow-up1·7 hours agoThe AI used doesn’t necessarily have to be an LLM. A simple model for determining the “safety” of a comment wouldn’t be vulnerable to prompt injection. linkfedilink
minus-squareokr765@lemmy.okr765.comtoAsklemmy@lemmy.ml•How do you feel about the level of censorship in your current instance ?linkfedilinkEnglisharrow-up18·2 days agoMy instance admin is also extremely oppressive. linkfedilink
The AI used doesn’t necessarily have to be an LLM. A simple model for determining the “safety” of a comment wouldn’t be vulnerable to prompt injection.