Researchers jailbreak AI chatbots like ChatGPT, Claude

A report by Carnegie Mellon computer science professor Zico Kolter and doctoral student Andy Zou has revealed a giant hole in the safety features on major, public-facing chatbots — notably ChatGPT, but also Bard, Claude, and others.

AI #20: Code Interpreter and Claude 2.0 for Everyone — LessWrong

Researchers Uncovered a New Flaw in AI Chatbots to Evil

Claude AI: The Dark Horse of the Industry, by Brynn Williams, Oct, 2023

ChatGPT-Dan-Jailbreak.md · GitHub

The ChatGPT DAN Jailbreak - Explained - AI For Folks

ChatGPT, Bard, Claude Tricked to Generate Malicious Content

AI researchers say they've found a way to jailbreak Bard and ChatGPT

Anthropic Claude Statistics 2023: Stats Facts and Trends You Need to Know! — SEO for the Poor and Determined

Jailbroken AI Chatbots Can Jailbreak Other Chatbots

ChatGPT-Dan-Jailbreak.md · GitHub

Universal LLM Jailbreak: ChatGPT, GPT-4, BARD, BING, Anthropic, and Beyond

AI Tidbits - Most interesting news in AI

Researchers jailbreak AI chatbots like ChatGPT, Claude