Comment Comment by goryramsy Looks like safety features are a bit strange.https://imgur.com/a/fWo92RISeems to be just deleting anything that a safety filter triggers on. I don't know if I like this more or less than what Anthropic does where they train the model to actively refuse. parent goryramsy 18 days ago
https://imgur.com/a/fWo92RI
Seems to be just deleting anything that a safety filter triggers on. I don't know if I like this more or less than what Anthropic does where they train the model to actively refuse.