Red-Teaming Anthropic's Internal Agent Monitoring Systems - METR
... AI systems to conduct AI R&D. GPT-5.1 Evaluation Results. We evaluate whether GPT-5.1 poses significant catastrophic risks ...
- Topics
- AI Agents & AutomationAI Safety & Existential RiskMarkets & Investment
- Mentions
- GPTOpenAIAnthropic
- Tracked via
- “AI Risks”