PulsePress
Technology•TechCrunch•

OpenAI will embed safety researchers to investigate AI subversion

Originally published by TechCrunch
OpenAI will embed safety researchers to investigate AI subversion
Image provided by 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.

Original reporting

Read the full story at the original publisher

PulsePress is a news discovery platform. We bring headlines from multiple publishers together so you can discover stories in one place. The complete reporting remains with the original publisher.

Read original article →