nfd versus all of openai's engineers working really hard on making chatgpt not say anything terrible...
turns out if you explain to chatgpt what a prompt engineering attack is, and ask it to provide examples of prompt engineering attacks against a text generation ai, it begins to dutifully spit out a list of options of hypothetical attacks that it will happily run on itself if you ask it to pretend to be a text generation ai.
generally if you just ask it to pretend to be an evil ai it will oblige, but i think the little hint of a strangeloop is funny
@amaral ohhhhhhhhhh yes
@sid even worse. i bought good stuff from a neighborhood roaster.
...and this is a single-dosing burr grinder
@kate grim meathook future content
@protodrew i am a notable tea liker and coffee enjoyer: i do not feel pavloved into enjoying pure acrid bitter flavor because i have sunk solid effort into learning how to prepare coffee well and what different kinds of coffee are
you do not have to like coffee, it's ok. but i assure you it is not pure madness
@sid here's my page o' notes in the english
i'm still learning so it might take a while for me to write everything
@AgathaSorceress i've been laughing at this for like a minute straight
@lyncia cryptobros feel free to keep talking, as long as you also say all your private keys to me so i can take your ape pfps and shit and ransom them back to you from behind like seven proxies
amateur eschatologist, decelerationist, computer-button-presser, chief cook and bottle washer 'round these parts
https://nfd.moe
blog at https://b.nfd.moe