SITUATION EXPLAINED: What's in Anthropic's 186-page risk report? • Anthropic raised two of its three risk ratings from very low to low: misalignment in high-stakes settings, and chemical and biological weapons • Its models now provisionally meet the CB1 threshold, meaning individuals or small groups could use them to access non-novel chem-bio weapons • The report discloses five internal safety failures, including accidentally training a production model on misaligned behavior more than once •…

Anthropic@AnthropicAIAug 14

As part of our Responsible Scaling Policy, we publish regular Risk Reports. These share detailed information on the risks of our systems and how prepared we are to address them. Our second Risk Report is now available: https://www.anthropic.com/aug-2026-risk-report