Technology ❯ Artificial Intelligence ❯ Chatbots

Language Models

User Interaction Disinformation Lucie Open Source Information Integrity Large Language Models Text Generation AI Safety Institute AI Performance OpenAI Ethics Safety Protocols Machine Learning AI Democracy Projects Cyberspace Research Institute

Poetic Prompts Jailbreak AI Models in 62% of Tests, Researchers Report

Researchers say verse disguises harmful intent for today’s filters, prompting broader robustness testing.