Anthropic's planned ASL-3 security controls for model weights require multi-party authorization, mandatory code review on production code, removal of persistent high-privilege access, and hardware authentication plus employee approval for temporary access.

supports (1)

• SAnthropic's Responsible Scaling Policy primary_testimony
  weight

  0.90

  locator: Security Safeguards > Access control for model weights

  “Implement multi-party authorization and mandatory code review on production code to remove persistent, high-privilege access to model weights... Require hardware authentication device prompt, justification and employee approval to grant access.”