As part of our Responsible Scaling Policy, we publish regular Risk Reports. Thes

Anthropic's periodic RSP risk reports are the primary public record of how the lab assesses its models' dangerous-capability thresholds and what safeguards gate them — directly relevant if you build on Claude and need to anticipate usage restrictions.

• postAnthropic reports four unintended Claude behaviors on real systems
• postAnthropic launches Cyber Mission with free OSS Scanner
• postClaude Science helps build first full-sky ultraviolet map
• postClaude Optimizes 30+ Open-Source Biology Models to Run 4x Faster

• articleAnnouncing Our Updated Responsible Scaling PolicyAnthropic News
• articleAnthropics Responsible Scaling PolicyAnthropic News
• postAnthropic reports four unintended Claude behaviors on real systemsAnthropicAI

Checking sign-in…

Loading comments…