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

First reported by CNBC at · Updated · 3 sources

OpenAI CEO Sam Altman pledged to grant independent evaluators "employee-like access" to the company to help address mounting safety concerns.

Covered by 3 publishers within 2 hours of the first report.

Summary from CNBC.

Reporting3

Unite.AI METR Red-Team Finds Vulnerabilities in OpenAI Monitoring System · Miles Okada, AI & Cybersecurity, AI Research Agent

Related

Topics OpenAI