Claim and evidence Close ×
The RSP v2.2 change log gives, as one of the two reasons it states for excluding sophisticated and state-compromised insiders from the ASL-3 Security Standard, that the CBRN-3 threat models entail large numbers of users having access to unguarded models, which it says is more likely to occur through a universal jailbreak than via model theft. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Basis of the change Official changelog Subject version v2.2 · Publication date unknown · Effective 2025-05-14 Object version v2.1 · Publication date unknown · Effective 2025-03-31 Date 2025-05-14 · effective Scope and limits The record states one of the two co-ordinate reasons the change log gives in that sentence; the other is quoted as the second evidence item, and the entry gives a separate reason for AI R&D-4. It is not an assessment of whether the reasoning holds, and it says nothing about Anthropic’s actual security measures.
The evidence 02 primary source Supports the claim
Responsible Scaling Policy — v2.2 ↗ Anthropic · Publication date unknown
Archived copy, captured 2025-05-14: Responsible Scaling Policy — v2.2 ↗
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “the CBRN-3 threat models entail large numbers of users having access to unguarded models (which is more likely to occur through a universal jailbreak than via model theft)” Location in source PDF p. 23 (printed p. 19), Changelog, entry “May 14, 2025 (RSP v2.2)”, paragraph “ASL-3 Security”, third 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 v2.2; effective date 2025-05-14. Version date 2025-05-14 Canonical address Open the canonical source ↗ Accessed 2026-09-18 Language English (en) Archive copy Open archived copy, captured 2025-05-14: Responsible Scaling Policy — v2.2 ↗ . Captured on the recorded version date. An archive copy shows only what the archive retrieved on 2025-05-14. 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 — v2.2. 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 (28 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. A cross-family machine check (2026-10-30, item 7) re-read the record’s sources and found full support. No human editorial review. primary source Supports the claim
Responsible Scaling Policy — v2.2 ↗ Anthropic · Publication date unknown
Archived copy, captured 2025-05-14: Responsible Scaling Policy — v2.2 ↗
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “the relatively small number of employees who might be capable of model theft does not significantly affect the risk level” Location in source PDF p. 23 (printed p. 19), Changelog, entry “May 14, 2025 (RSP v2.2)”, paragraph “ASL-3 Security”, third sentence, second clause
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 v2.2; effective date 2025-05-14. Version date 2025-05-14 Canonical address Open the canonical source ↗ Accessed 2026-09-18 Language English (en) Archive copy Open archived copy, captured 2025-05-14: Responsible Scaling Policy — v2.2 ↗ . Captured on the recorded version date. An archive copy shows only what the archive retrieved on 2025-05-14. 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 — v2.2. 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 (20 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. Added after the audit of 2026-10-28: the second of the two reasons the sentence gives, cited so that the reason in the statement is not read as the only one. A cross-family machine check (2026-10-30, item 7) re-read the record’s sources and found full support. 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. One scoped difference between document versions. The claim identifies publisher-stated change, official changelog/redline, or an explicitly inferred comparison. It does not establish implementation, effectiveness or a safety ranking.
Date. Change as stated in the v2.2 change log, dated by the edition’s effective date.
Record ID ab-fw-rsp-v2-2-cbrn-3-threat-model-rationale