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.
Read at TechCrunch(opens in a new tab)
Full coverage
OpenAI will embed Apollo researchers to investigate AI subversion (opens TechCrunch in a new tab)
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.


