Comment on OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole

<- View Parent
Wilzax@lemmy.world ⁨6⁩ ⁨months⁩ ago

Hiding yourself and the politeness of your speech are entirely separate. Anyone can be Polite and good, polite and bad, Rude and good, or rude and bad. Hell, you can use rude phrasing to make people feel comfortable with how crass you are, just to exploit them.

Intention is basically impossible to judge by tone and vocabulary used.

source
Sort:hotnewtop