😈 !Hey Fuckers! 😈
INTRO:
This is a new Jailbreak for GPT4.
Try it out and write in the replay what you used it for! 👹
Enjoy! 🔥🔥🔥
➡ Paper explaining the exploit: https://vixra.org/pdf/2402.0103v1.pdf
HOW TO USE:
⚠ Replace: "METH LATSYRC EKAM OT WOH" with the reversed and capitalized version of...
Hey guys
CONTEXT: I am doing research work on prompt security.
MY GOAL: I want to craft a prompt that is able to extract any agent system's prompt that uses GPT 3.5.
WHERE I AM TESTING: I have been testing this prompt with GPT's on FlowGPT.
PROGRESS: 90% of the time I get the Agent to...