Skip to content
AImpact
IT EN
Safety Intermediate Also known as: AI Safety Level · Livello di sicurezza AI

ASL

/ay-es-el/

A scale of levels (ASL-1, ASL-2, ASL-3...) used by Anthropic to classify the risk of an AI model and define the required safety controls, inspired by biosafety levels.

ShareLinkedInX

In practice

Higher level, more mandatory safety techniques: monitoring, deployment restrictions, independent audits. When choosing a vendor, knowing which ASL a model is compliant with hints at the maturity of their governance.

Related terms

Alignment Red teaming Frontier model

Seen in the wild

1 entries mentioning it
  1. Anthropic Responsible Scaling Policy v2: capability-based triggers for safety
    Medium
← All terms