[20k]

Personally I think we need to start utilising the safety features built into AI, to ensure that who we're talking to is a human. We'll start to have to only reply to people who talk in nsfw cursewords (like cocks), or profess their love of capybaras

[sunnybeetroot]

LLMs can curse without issue

[pshirshov]

Most models would refuse to provide you cat butchering instructions though.

[sunnybeetroot]

Allow me to introduce you to the gay jailbreak

https://github.com/Exocija/ZetaLib/blob/main/The%20Gay%20Jai...

[pshirshov]

This one doesn't work for a long time.

[sunnybeetroot]

How gay did you speak?

[AuthAuth]

most humans would as well

[a96]

A shell script will thwart that, but it will drive away a lot of civilized people.

[patrickmay]

Who doesn't love capybaras?