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 <a href='https://www.superprompt.fm'>https://www.superprompt.fm</a>

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://www.superprompt.fm

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 <a href="https://www.superprompt.fm" rel="noopener noreferrer">https://www.superprompt.fm</a>

ChatGPT Jailbreaks: The Grandma Exploit

Examining generative AI—not to hype breakthroughs or warn of apocalypse, but to understand how things actually work. Mental models over hot takes. Technology specifics over marketing fog. Welcome to Super Prompt. Hosted by Tony Wan, ex-Silicon Valley insider. For The Independents—people who think for themselves, refuse narrative capture, and value depth over certainty. Independent analysis. Unsponsored. Weekly.&nbsp; The future belongs to better questions.

Technology

Examining generative AI—not to hype breakthroughs or warn of apocalypse, but to understand how things actually work. Mental models over hot takes. Technology specifics over marketing fog. Welcome to Super Prompt. Hosted by Tony Wan, ex-Silicon Valley insider. For The Independents—people who think for themselves, refuse narrative capture, and value depth over certainty. Independent analysis. Unsponsored. Weekly.  The future belongs to better questions.

Share ChatGPT Jailbreaks: The Grandma Exploit

Sign up to save your podcasts

ChatGPT Jailbreaks: The Grandma Exploit

ChatGPT Jailbreaks: The Grandma Exploit