Source · Tier C · Blog / articleSource · Activating AI Safety Level 3 Protections
Activating AI Safety Level 3 Protections
Anthropic. 2025. Anthropic.
| Original | https://www.anthropic.com/news/activating-asl3-protections |
|---|---|
| Accessed | 2026-09-25 |
| Note | Developer's announcement of its own security measures. Describes egress bandwidth controls that limit the rate of outbound network traffic from environments holding model weights. Supports "Anthropic reports" statements only. |