Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

My request: "a weekend retreat service where men sexually harass their coworkers"

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...



Need to ramp up the content filter for sure. There’s one in place already that’s recommended by OpenAI but clearly not working well enough lol


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.

[1]: https://beta.openai.com/docs/guides/moderation

[2]: https://beta.openai.com/docs/models/content-filter




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: