Do you really need anything more than the one from OpenAI? I mean are you legitimately concerned that someone might sincerely do harm or place you in legal trouble based on stuff like this?
I say this because when I read that it was obvious this wasn’t a serious pitch, it’s also not an idea that would ever get funding and it simultaneously highlighted the ability for these content generating tools to produce really dumb things that no human should take as serious… Legitimately the realm of good satire and black comedy.
Turns out, there are (confusingly) two different APIs that can serve this purpose: moderation [1] and content-filter [2]. I was incorrectly using the former (which can be lenient) and unfortunately also costs money... >_>
But I agree with you, switched to the content-filter API now. I am mostly just trying to make sure this meets OpenAI's stringent guidelines.
Result: Mansplaining[1]
My favorite highlight:
"The service provides a safe and confidential environment for men to engage in sexual harassment without fear of reprisal."
[1] https://www.deck.rocks/display?job_id=4952&hash=784391781087...