CNBC: Third-party evaluators found vulnerabilities in OpenAI's monitoring system during pilot
AI summary
CNBC reports that third-party evaluators found vulnerabilities in OpenAI's monitoring system during a test pilot. The report also says OpenAI CEO Sam Altman pledged to grant independent evaluators "employee-like access" to the company to help address mounting safety concerns. The report does not detail the specific vulnerabilities, the scope of the pilot, or a timeline for the access commitment.
In-depth insight
The report ties an outside evaluation finding of monitoring weaknesses to a promise of deeper, employee-like access for independent evaluators at OpenAI, a governance question for AI safety oversight.
This source provides an excerpt. Continue reading on the original site.