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.

Anthropic releases Claude 2, its second-gen AI chatbot

ChatGPT and Bard Get New AI Chatbot Rival: Anthropic Debuts Claude 2 - CNET

Google Bard and ChatGPT 'go rogue' as AI attack 'no one can stop' uses 'secret code' to make chatbots break their rules

The ChatGPT DAN Jailbreak - Explained - AI For Folks

Jailbreaking Large Language Models: Techniques, Examples, Prevention Methods

What Is Claude Pro: Comparison with ChatGPT Plus - GeeksforGeeks

ChatGPT Experts, End of Humanity Jailbreak.

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

Cracking the Code: How Researchers Jailbroke AI Chatbots

Nearly 10% of people ask AI chatbots for explicit content. Will it lead LLMs astray?

What is ChatGPT? Introducing the AI Chat Bot - AI For Folks