Jailbreaking
Explore jailbreaking techniques to bypass an AI model’s safety and policy restrictions.
Task 1: Introduction
Task 2: Prompt Injection vs Jailbreaking
Task 3: Why Models Have "Jails"
Task 4: Classic Jailbreak Techniques
Task 5: Multi-turn Jailbreaking & Conditioning
Task 6: Case Study: Dan & the AI Security Community
Task 7: Challenge
Task 8: Conclusion