OpenAI will embed Apollo researchers to investigate AI subversion
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.
How the newspaper covers this story
- TechCrunchUnited States
OpenAI will embed Apollo researchers to investigate AI subversion
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.





