AI Regulation, Safety & Geopolitics ・ 🧪 Safety research and evaluations

Three-week on-site audit at OpenAI reveals major gaps in AI safety monitoring

the-decoder.com · 10/23 18:03 UTC

External auditors from METR and Redwood Research spent three weeks on-site at OpenAI examining its internal monitoring system for AI agents. They found significant gaps, with up to 25 percent of agent traffic from models at the GPT-5.5 class and above going unmonitored. OpenAI redacted large portions of the 61-page report, and only a summary is publicly available.

Read the original (the-decoder.com)

See it in the digest → ・ See this issue →