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.

ChatGPT, Bard, Claude Tricked to Generate Malicious Content

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

Jailbreak AI Chat - Opensource Jailbreak Prompt Database – ToolPilot

ChatGPT-4 released: What will it be like to grow up with AI?

ChatGPT, Bing, Bard, Or Claude: Generative AI Chatbot Comparison

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

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

LWiAI Podcast #111 - Mostly ChatGPT Again, plus Google's Bard, Climate Change, AI Seinfeld

AI Tidbits - Most interesting news in AI

Claude AI Chat 2: The Newest AI Arrival—Will It Rival ChatGPT?

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

Computer scientists: ChatGPT jailbreak methods prompt bad behavior

Jailbroken AI Chatbots Can Jailbreak Other Chatbots