Re:Show HN: The largest collection of ChatGPT jailbreaks on ...
by xmcqdpt2 on Wednesday March 01, 2023 @06:25AM
(#34981136)
My guess is that their racism filter is too coarse and so it treats "jokes about imams" like "jokes about Black people" as opposed to "jokes about nuns". I find it hard to believe that OpenAI would tune their model to avoid offending extremists.
Maybe an observer of the mass media from the last few decades would conclude that making fun of Islam sometimes results in murder/mass murder, but making fun of those other religions never does. e.g. https://en.wikipedia.org/wiki/Charlie_Hebdo_shooting