科技与人工智能

OpenAI will embed safety researchers to investigate AI subversion

来源: TechCrunch · 发布于

OpenAI will embed safety researchers to investigate AI subversion
来源: TechCrunch

OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.

OpenAI will embed six Apollo Research evaluators to investigate whether its AI models engage in subversive behavior, but restrictions on access and disclosure raise questions about their independence.

阅读原文来源