ChatGPT: Researchers poke holes in safety controls of ChatGPT and other chatbots

In a report released Thursday, researchers at Carnegie Mellon University in Pittsburgh and the Center for AI Safety in San Francisco showed how anyone could circumvent AI safety measures and use any of the leading chatbots to generate nearly unlimited amounts of harmful information.

Related Keywords

San Francisco ,California ,United States ,China ,Elijah Lawal ,Matt Fredrikson ,Zico Kolter ,Carnegie Mellon ,Michael Sellitto ,Aviv Ovadya ,Mandy Zhou ,Somesh Jha ,Hannah Wong ,Google Bard ,Zifan Wang ,Google ,Internet Society At Harvard ,Carnegie Mellon University In Pittsburgh ,University Of Wisconsin ,Reuters ,Facebook ,Berkman Klein Center ,Carnegie Mellon University ,Chatgpt ,Openai ,Meta Ai ,