Researchers Say Guardrails Built Around A.I. Systems Are Not So Sturdy

OpenAI now lets outsiders tweak what its chatbot does. A new paper says that can lead to trouble.

Related Keywords

Virginia ,United States ,California ,San Francisco ,Stanford ,Berkeley ,Xiangyu Qi ,Ruoxi Jia ,Prateek Mittal ,Tinghao Xie ,Scott Emmons ,Yi Zeng ,Yu Chen ,Peter Henderson ,Riley Goodside ,Ibm ,Google ,Facebook ,Carnegie Mellon University In Pittsburgh ,Microsoft ,University Of California ,Virginia Tech ,Pin Yu Chen ,Carnegie Mellon University ,Artificial Intelligence ,Research ,Computers And The Internet ,Tech Industry ,Chatgpt ,Meta ,Openai ,Princeton ,