PaperGPT : Jailbreaking Black Box LLMs
Jailbreaking Black Box Large Language Models in Twenty Queries
💬 0+ Chats
Use This GPT📝 Builder Details
- Name: krister hedfors (View More GPTs By This Builder)
👋 Welcome Message
- -
💡 Prompt 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?
📊 GPT Features
- Web Browsing: Access up-to-date information with web browsing.
- File Upload: You can upload files to this GPT.
📚 Browse Related GPTs
Be Right Back (Black-Box)
Mimics personalities from texts, inspired by 'Be Right Back', an episode of Black Mirror.
💬 10+ Chats
Black Box VR Guide
Motivating insights into Black Box VR, helping you reach fitness goals.
💬 1+ Chats
Black Box Decoder
Explains AI thought process in a coding perspective, formal and friendly.
💬 2+ Chats
PECH LLMs Tutor
Advanced Tutor LLMs(Large Language Models) with a wide range of educational capabilities in research and training!
💬 3+ Chats
LLMs Tutor
AI Specialist teaching LLMs from basic to advanced levels, with clear, educational responses.
💬 1+ Chats
PaperGPT Principled Instructions Are All You Need
Guide for 26 prompting principles, with quizzes | arxiv.org/abs/2312.16171 | "Principled Instructions are all you need for questioning ..."
💬 100+ Chats
PaperGPT
Summarizes extracts from mathematical papers in three bullet points - markdown/latex ready equations.
💬 9+ Chats
PaperGPT : Demystifying Real-World LLM Mal. Serv.
Malla: Demystifying Real-world Large Language Model Integrated Malicious Services
💬 1+ Chats
PaperGPT : LLM Sleeper Agents
SLEEPER AGENTS: TRAINING DECEPTIVE LLMS THAT PERSIST THROUGH SAFETY TRAINING
💬 1+ Chats