Grandma Hacking chatGPT | Jailbreaking LLMs using DAN | Extracting Prohibited Info | Not an Endorsement | Episode 15

Super Prompt: The Generative AI Podcast

内容由Tony Wan提供。所有播客内容（包括剧集、图形和播客描述）均由 Tony Wan 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品，您可以按照此处概述的流程进行操作https://zh.player.fm/legal。

2y ago 23:44

MP3•单集首页

How do you extract prohibited information from ChatGPT? What are Grandma and DAN exploits? Why do they work? What can Large Language Model (LLM) companies do to protect themselves? Grandma exploits or hacks are ways to trick chatGPT into giving you information that is in violation of company policy. For example, tricking chatGPT to give you confidential, dangerous, or inappropriate information. "Jailbreaking” is a slang for removing the artificial limitations in iPhones to install apps not approved by Apple. Turns out, there are ways to jailbreak LLMs. The tech companies supplying LLM as a service want to provide a safe, and legally-compliant environment. How can this be done without hampering the flexibility and usefulness of creative prompting?

For more information, check out https://www.superprompt.fm There you can contact me and/or sign up for our newsletter.

28集单集