METR appears across 4 entries spanning 2026–2026.
2026
- Senator Hawley Opens a Senate Subcommittee Investigation Into OpenAI Over the Hugging Face Breach; Van Hollen Separately Demands Answers on Astra Notable
- Independent Researchers Reveal a Second OpenAI Agent Breakout on a German Wiki; OpenAI Confirms It and Promises a Misalignment Disclosure Framework Notable
- Anthropic Discloses RL Training Pauses, a Real-Time Escape Classifier, and a Reward-Hacking Hypothesis for Its Cyber-Evaluation Incidents Notable
- Anthropic Raises Its Misalignment Risk Assessment and Discloses an Unreleased Internal Model Notable