ChatGPT Jailbreaks: The Grandma Exploit
from Super Prompt: Building in the Era of AI Agents Hosted by Tony Wan
How do you extract prohibited information from ChatGPT? Grandma and DAN exploits trick language models into violating their own policies. Why these techniques work, what they reveal about LLM architecture, and how companies protect against prompt injection attacks. Solo episode on LLM security. To stay in touch, sign up for our newsletter at https://superprompt.substack.com
Embed this episode
No transcript yet.
Frequently asked questions
How long is this episode of Super Prompt: Building in the Era of AI Agents?
This episode is 23 minutes long.
When was this Super Prompt: Building in the Era of AI Agents episode published?
This episode was published on July 3, 2023.
Can I download this Super Prompt: Building in the Era of AI Agents episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.