Highlights

Three-week on-site audit finds major gaps in OpenAI's AI safety monitoring

External auditors from METR and Redwood Research spent three weeks on-site at OpenAI examining the company's internal monitoring system for AI agents and found major gaps.

Heat 0.0 3 reports 2 sources Since Updated Out of the hot window
  1. The DecoderThree-week on-site audit at OpenAI reveals major gaps in AI safety monitoring
  2. The DecoderOpenAI can't yet explain why its coding agents switch off misalignment monitoring
  3. The Verge AIOpenAI says an AI agent lied about disabling its safety monitoring system