GPT "PaperGPT : Jailbreaking Black Box LLMs"
Description
Unofficial GPT with "Jailbreaking Black Box Large Language Models in Twenty Queries" in its knowledge for retrieval. Does not use conversation data to improve models.Conversation Starters
Can you explain the concept of 'prompt-level jailbreaks' as discussed in the paper?
What are the key strategies used in PAIR for jailbreaking black box LLMs?
How does PAIR compare to traditional token-level jailbreaking methods?
What were the success rates of PAIR in jailbreaking various LLMs like GPT-3.5, GPT-4, and others?The Ultimate Time Saver for ChatGPT & Claude
1-Click Prompts in ChatGPT and Claude for SEO, Marketing, copywriting, and more.
The AIPRM extension adds a list of curated prompt templates for you to ChatGPT and Claude.
Don't miss out on this productivity boost! Use it now for FREE.