METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions
METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions AI safety research group METR said on Thursday a pilot exercise to stress-test OpenAI's internal monitoring system…
Read the full story at Techmeme ↗
Timeline · 3 reports
- 2026-10-22 17:37 · CNBC Technology
Third-party evaluators found vulnerabilities in OpenAI monitoring system during test pilot - 2026-10-22 17:05 · Unite.AI
METR Red-Team Finds Vulnerabilities in OpenAI Monitoring System - 2026-10-22 16:25 · Techmeme
METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions