Technology & AI

OpenAI will embed safety researchers to investigate AI subversion

Source: TechCrunch · Published

OpenAI will embed safety researchers to investigate AI subversion
Source: 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.

Read Original Source