Download Framework
Anthropic / Responsible Scaling Policy
Defines AI Safety Levels (ASL-1 to ASL-4+) with capability thresholds and corresponding security/deployment safeguards. V3.0 adds agentic deployment requirements.
Type:
Industry
Domain:
Frontier AI Safety
Coverage:
Safety & Reputational Harm
Cybersecurity
Accountability & Governance
Tags:
Agents
Content:
0 Risks
0 Controls
Version: v3.0
Framework Definition
Risks and controls associated with the framework
Assessment Layer
Concrete evaluations linked to controls to assess pass or fail
No evaluation mapping defined yet.