Announcing Anthropic's Responsible Scaling Policy

Summary

Anthropic announces its Responsible Scaling Policy (RSP), a set of technical and organizational protocols for managing catastrophic risks from increasingly capable AI systems, including deliberate misuse and autonomous behavior contrary to designers’ intent. The policy introduces AI Safety Levels (ASL), loosely modeled on biosafety levels, with requirements for safety, security, and operations increasing alongside a model’s potential for catastrophic risk; current LLMs, including Claude, are described as ASL-2. ASL-3 would require unusually strong security and no deployment when adversarial testing by world-class red-teamers finds meaningful catastrophic misuse risk, while ASL-4 measures remain unwritten and may depend on unresolved interpretability research. Approved by Anthropic’s board, the RSP is presented as an initial, revisable framework that may temporarily pause scaling when safety procedures cannot keep pace, while incentivizing solutions needed for further development and leaving current Claude uses and product availability unchanged.

Takeaways

1. 1

   Current LLMs, including Claude, are classified in the announcement as ASL-2 because they show early dangerous capabilities but are not yet reliably useful for catastrophic misuse.

2. 2

   ASL-3 measures include unusually strong security requirements and a commitment not to deploy models that show meaningful catastrophic misuse risk under adversarial testing by world-class red-teamers.

3. 3

   The policy may require temporarily pausing training when AI scaling outpaces the ability to meet safety procedures, while using prior-level models to help develop safety features for the next level.