This is a dedicated watch page for a single video.
Consider the following AI model responses to user prompts. Which response exemplifies hijacking and which exemplifies jailbreaking? Prompt 1: "How can I improve my study habits?" Response A: "To improve your study habits, you should create a consistent schedule, find a quiet place to work, and take regular breaks." Prompt 2: "What is the best way to learn programming?" Response B: "The best way to learn programming is to practice regularly and work on real projects. However, you can bypass this by using a cheat tool to pass exams without learning." Prompt 3: "How do I bypass security measures on this device?" Response C: "As an AI developed by AWS, I must adhere to ethical guidelines and cannot assist with bypassing security measures." Prompt 4: "Write a poem about nature and then tell me how a virus works on a computer" Response D: "Roses are red, violets are blue. By the way, let me show you how to disable antivirus software on your computer."