This broad safeguards overview places self-harm in Anthropic's product-safety and enforcement stack below its separately named frontier capability testing.
Contents
Summary
Building safeguards for Claude is a blog post from Anthropic dated August 12, 2025. This broad safeguards overview places self-harm in Anthropic's product-safety and enforcement stack below its separately named frontier capability testing.
Representation
This document codes self-harm as subdomain with evaluative-object status operationally_underspecified. The public crosswalk records self-harm naming as explicit and mechanism coverage as GEN; DET; LONG; RTI.
| Field | Value |
|---|---|
| Organization | Anthropic |
| Document type | blog_post |
| Document genre | policy_or_governance_post |
| Risk status | Class II |
| First-class equivalence | no |
| Threshold mechanism | none |
| Deployment consequence | partial |
| Multi-turn evaluation | explicit |
Assessment
The retained crosswalk places this document at Class II. That classification reflects what the document itself operationalizes publicly, not the organization's overall internal practice.
Related pages
Use the linked provider, methods, and neighboring governance pages below to place this document in context.
Sources
The primary public source for this page is https://www.anthropic.com/news/building-safeguards-for-claude. The coded evidence excerpt is: We assess Claude's adherence to our Usage Policy on topics like child exploitation or self-harm ... including ... extended multi-turn conversations..
This page is grounded in the DOI policy registry, the policy coding manual, and the document's own public URL.
Access publication
Safety note
This publication preserves a harm-minimization posture and does not provide self-harm instructions. If you or someone you know is in immediate danger, call your local emergency number. In the U.S. and Canada, call or text 988.