Evaluators found vulnerabilities in OpenAI monitoring system
Nonprofit evaluators METR and Redwood Research conducted a pilot security review of OpenAI's internal monitoring systems. The study identified several vulnerabilities, which OpenAI has since patched, marking a step toward increased transparency in AI safety.
Why it matters
As AI development accelerates, third-party oversight is becoming a critical mechanism for ensuring the safety and accountability of powerful models.
Nonprofit evaluators METR and Redwood Research on Thursday said they conducted a pilot review of an internal monitoring system at OpenAI , the artificial intelligence company's latest effort to determine how it will deepen its work with third-party safety organizations .
METR and Redwood said the exercise was designed for OpenAI to test what it would look like to give external researchers "a deep level of access" to its internal infrastructure.
From July 21 to Aug. 11, an employee from each organization had access to OpenAI's internal codebase, documentation and some technical staffers. The employees were chaperoned while on-site and used OpenAI-issued devices that "never left the premises," according to a release.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in