Third-party evaluators find vulnerabilities in OpenAI monitoring system during test pilot

Third-party evaluators found vulnerabilities in OpenAI's monitoring system during a test pilot, CNBC Technology reported. OpenAI CEO Sam Altman pledged to grant independent evaluators "employee-like access" to the company to help address mounting safety concerns. The source did not specify which vulnerabilities were found or how many evaluators participated.

Third-party evaluators find vulnerabilities in OpenAI monitoring system during test pilot Source: CNBC Technology https://www.cnbc.com/technology/ OpenAI https://www.machinebrief.com/glossary/openai CEO Sam Altman pledged to grant independent evaluators "employee-like access" to the company to help address mounting safety concerns. Get AI news in your inbox Daily digest of what matters in AI.