Browsing: Center for AI Safety

Researchers Poke Holes In Safety Controls Of Chatgpt And Other Chatbots

Chatbots August 5, 2023

Researchers at Carnegie Mellon University and the Center for AI Safety have demonstrated how anyone can use leading chatbots to generate unlimited amounts of…

Cmu Researchers Propose A Simple And Effective Attack Method That Causes Aligned Language Models To Generate Objectionable Behaviors At A High Success Rate

Deep Learning Natural Language Processing August 2, 2023

Researchers from Carnegie Mellon University’s School of Computer Science, the CyLab Security and Privacy Institute, and the Center for AI Safety in San Francisco…

Subscribe to Updates

Browsing: Center for AI Safety

Researchers Poke Holes In Safety Controls Of Chatgpt And Other Chatbots

Cmu Researchers Propose A Simple And Effective Attack Method That Causes Aligned Language Models To Generate Objectionable Behaviors At A High Success Rate