Claim · 2024-10-15 · effective · Stated in source · Supported

RSP v2.0 states that it assesses its CBRN weapons Capability Threshold by comparing what potential attackers could achieve with full model access against 2023-level online resources, assuming funding and up to one year of time to invest but no initial specialised expertise.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Anthropic Responsible Scaling Policy — v2.0 → states provision → CBRN threshold assessed against 2023-level online resources, with funding and up to a year but no initial specialised expertise

Where it appears

Frontier safety frameworks →

Claim and evidence

Anthropic Responsible Scaling Policy — v2.0states provision ↓CBRN threshold assessed against 2023-level online resources, with funding and up to a year but no initial specialised expertise

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Threshold or trigger · provision ID rsp-cbrn-assessment-baseline
Subject version: v2.0 · Publication date unknown · Effective 2024-10-15
Date: 2024-10-15 · effective

Scope and limitsThe record states the comparison the edition sets for itself. The edition’s own footnote says the comparison is hard to make in practice; no assessment of any model is recorded.

The evidence 01

primary sourceSupports the claim

Responsible Scaling Policy — v2.0

Anthropic · Publication date unknown

Archived copy, captured 2024-10-22: Responsible Scaling Policy — v2.0

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“comparing what potential attackers could achieve with full model access versus 2023-level online resources, assuming they have funding and up to one year of time to invest, but no initial specialized expertise”

Location in source PDF p. 20 (printed p. 16), Appendix C: Detailed Capability Thresholds, paragraph “Chemical, Biological, Radiological, and Nuclear (CBRN) weapons”, second sentence

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-30

Source details and check notes

Authors: Anthropic
Version: Responsible Scaling Policy v2.0; effective date 2024-10-15. v2.0 identity is supplied by the official archive and later dated changelogs; the cover is not numbered.
Version date: 2024-10-15
Canonical address: Open the canonical source ↗
Accessed: 2026-09-18
Language: English (en)
Archive copy: Open archived copy, captured 2024-10-22: Responsible Scaling Policy — v2.0. Captured 7 days after the recorded version date. An archive copy shows only what the archive retrieved on 2024-10-22. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-09-18.
Attribution: Anthropic, Responsible Scaling Policy — v2.0.
Reuse: No open redistribution licence asserted. Selekoa practice: metadata, attributed paraphrases and short attributed quotations under the editorial policy (at most 50 words each; at most 400 quoted words per document across the dataset, and about 10% of a document under about 2,000 words). Documents are linked externally, not redistributed. Publisher terms that forbid quotation override this practice.
Check notes: Candidate pack passage, AI and biosecurity (research/ai-bio). The quotation (32 words) matched the text retrieved for the candidate pack on 2026-10-28 and again at admission on 2026-10-30, in a fresh retrieval whose SHA-256 equals the pack’s. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. An exact framework edition, or another document with an exact expression, states one provision: a capability threshold or risk level and its trigger, a required safeguard or action, a decision authority (who decides, recommends, can overrule or is informed), a stated exception, or another statement of its content, such as a licence term or a prospectus statement. The passage records what the document says, not implementation, compliance or effectiveness. Provisions with the same key align across editions of one family.

Date. Provision as stated in this edition, dated by the edition’s effective date.

Record ID ab-fw-rsp-v2-0-cbrn-assessment-baseline