OpenAI will embed Apollo researchers to investigate AI subversion | TechCrunch
作者 Rebecca Bellan全文約 5,658 字
文章摘要
TechCrunch · 文章頁摘要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 safety evaluators in its organization as part of a pilot, Apollo said Monday. The news follows a series of safet...