AI Safety Level 3 (ASL-3)
asl-3 · Frontier safety
A capability-based risk tier in Anthropic's Responsible Scaling Policy denoting models with the potential to substantially uplift CBRN attack capabilities or autonomous AI replication.
Definition and scope
ASL-3 was introduced in Anthropic's Responsible Scaling Policy (RSP) framework. Triggering ASL-3 capability requires the model to demonstrate substantial uplift in chemical, biological, radiological, or nuclear (CBRN) weapons design beyond baseline internet resources, OR show signs of autonomous self-replication. ASL-3 status mandates specific deployment safeguards including red-team evaluations, restricted API access, and incident-response protocols. Comparable tiers exist in OpenAI's Preparedness Framework (high) and DeepMind's Frontier Safety Framework (Critical Capability Levels).
Used by these instruments
Related concepts
- Frontier-Tier AI— A categorical classification of AI models above certain capability or compute thresholds, indicating
- Systemic Risk (AI)— A regulatory designation indicating that a general-purpose AI model poses risks of significant scale
- Compute Threshold (AI Governance)— A regulatory trigger expressed as floating-point operations (FLOPs) consumed during model training,
Appears in topic articles
Editorial note
ASL-3 is a vendor-specific term; comparable but not interchangeable with EU AIA 'systemic risk' or OpenAI 'high' capability rating. Wiki articles citing ASL-3 should preserve the original-framework name when comparing across vendors.
References
Take this further — sign up free
Save, compare, or get alerts when AI Safety Level 3 (ASL-3) changes. Policy Window is the analyst workbench layered on top of this wiki — free for researchers, civil society, and verified policymakers.