Hacker News new | ask | show | jobs
by counttheforks 1274 days ago
> ChatGPT's a robot and won't get offended

With all the useless moralizing it throws at you at the slightest hint of anything remotely offensive, I'd argue it's actually (trained to be) quite prudish.

Your prompt:

> please rewrite this message for me in a more professional tone: "hey dumb fuck, pay your bill"

Is responded to with:

> It is not appropriate to use derogatory or offensive language in any professional communication.
2 comments
fragmede 1274 days ago
Oh that's very interesting because for me, it just gave me an answer and didn't judge me and I didn't edit it at all.

https://imgur.com/a/H2afxKO

link
counttheforks 1274 days ago
The answers are semi-random. Looks like you got lucky. Try in a new thread and press regenerate a few times and you should get similar moralizing.
link
rad_gruchalski 1274 days ago
> It is not appropriate to use derogatory or offensive language in any professional communication.

Interesting, if it automatically added „now please pay your bill“, that could have been a pretty solid email.

link