Activating AI Safety Level 3 protections
As published on anthropic.com on 22 May 2025. Date stated on the page ('Published May 22, 2025').
- Issued by
- Anthropic
- Authors credited
- No authorship claim recorded yet. The source record lists Anthropic.
- Dates
- Published 2025-05-22 issue evidence
Date stated on the page ('Published May 22, 2025').
- Exact source
- Activating AI Safety Level 3 protections Anthropic · publication date unknown · Retrieved for the candidate pack on 2026-10-28 (SHA-256 411f66885bacd8769dd6718e78f40eb0df80a4983dbde9d0d49f0323746e8656). Page labelled 'Published May 22, 2025', with six footnotes, as served on 2026-10-28. The accompanying full report (a separate PDF) was not retrieved. Retrieved again at admission on 2026-10-30 (SHA-256 35fa989dfc4f36842ef4f1dda2cfbdda9f9fc9f63524b310fd869ed2f32ab1e8). Its wording can change; earlier wording is not authenticated.
Appears in
No collection holds a record about this document yet.
Versions
anthropic-asl3-activation: 1 recorded version, oldest first, published by Anthropic. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2025-05-22 · publishedAs published on anthropic.com on 22 May 2025 (this version)
This version
Provisions in this version · 1 quoted
A limited selection of quoted provisions: what this edition says about thresholds, required actions, who decides and exceptions, and other statements of the text. It is not a full summary and says nothing about implementation. A “not found” record states which part of the edition was inspected. It is not a claim that the text was deleted.
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
- Issued by: AnthropicAnthropic published 'Activating AI Safety Level 3 protections' on 22 May 2025, stating that it had activated the ASL-3 Deployment and Security Standards of its Responsible Scaling Policy in conjunction with launching Claude Opus 4.2025-05-22 · publication · Stated in source · Supported Inspect claim & evidence ↗Anthropic: institution →
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
Other recorded relations
- states evaluation resultAnthropic's ASL-3 activation post states that it had not yet determined whether Claude Opus 4 definitively passed the capabilities threshold requiring ASL-3 protections, that continued improvements in CBRN-related knowledge and capabilities meant clearly ruling out ASL-3 risks was not possible as it had been for every previous model, and that it deployed the model with ASL-3 measures as a precautionary and provisional action.2025-05-22 · publication · Stated in source · Supported Inspect claim & evidence ↗
- states evaluation resultAnthropic's ASL-3 activation post states that experiments showed access to Claude Sonnet 3.7 helped participants do somewhat better on tasks related to CBRN weapon acquisition than those with standard internet access, and that all participants' plans still had critical failures.2025-05-22 · publication · Stated in source · Supported Inspect claim & evidence ↗