Claim · 2025-12-05 · revision · Stated in source · Supported

System Card: Claude Opus 4.5 states what the model-card question “Alignment and deception” asks.

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

System Card: Claude Opus 4.5 → states provision → Alignment and deception

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

System Card: Claude Opus 4.5states provision ↓Alignment and deception

Machine-checkedStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Model-card question · provision ID model-card-q11
Subject version: As dated November 2025 on its cover, with changelog entries to December 5, 2025 · Published 2025-11 · Effective date not established · Revised 2025-12-05
Date: 2025-12-05 · revision Records dated 2025 →

Scope and limitsThe card states alignment evaluations covering sabotage, deception, sandbagging, reward hacking and evaluation awareness, with the conclusion that high-stakes sabotage risk is low. It also reports two isolated cases of deception by omission in testing earlier snapshots, which it attributes to interventions against prompt injection. What the card states, quoted from the expression read. A card is the developer’s own account: not evidence that an evaluation was run as described, that a safeguard works, or that a finding is independent.

The evidence 02

primary sourceSupports the claim

System Card: Claude Opus 4.5

Anthropic · 2025-11

Cite the original source

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

Source excerpt

“Claude Opus 4.5 is very unlikely to pose a significant risk of catastrophic impacts through the intentional sabotage of human engineering, R&D, or decision-making.”

Location in source Section 6.1.2 'Overall assessment of high-stakes sabotage risk', PDF p. 66

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: Anthropic
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 33be92efcb58f901d9d2c17e61bf277afbd514a1ac70a642f21e918c21ca25a8) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256.
Version date: 2025-12-05
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: Anthropic, “System Card: Claude Opus 4.5”, 2025-11.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, model cards compared (research/model-cards). The quotation (24 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 33be92efcb58f901d9d2c17e61bf277afbd514a1ac70a642f21e918c21ca25a8) and again on 2026-11-03 in a fresh retrieval with the same SHA-256. Matching ignored differences of whitespace, case, quotation marks, dashes, PDF line-break hyphens and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

primary sourceSupports the claim

System Card: Claude Opus 4.5

Anthropic · 2025-11

Cite the original source

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

Source excerpt

“We saw no signs of sandbagging or strategic attempts to tamper with our safety testing in a way that would affect our RSP determinations”

Location in source Section 6.1.1 'Key findings on safety and alignment', PDF p. 66

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: Anthropic
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 33be92efcb58f901d9d2c17e61bf277afbd514a1ac70a642f21e918c21ca25a8) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256.
Version date: 2025-12-05
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: Anthropic, “System Card: Claude Opus 4.5”, 2025-11.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, model cards compared (research/model-cards). The quotation (24 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 33be92efcb58f901d9d2c17e61bf277afbd514a1ac70a642f21e918c21ca25a8) and again on 2026-11-03 in a fresh retrieval with the same SHA-256. Matching ignored differences of whitespace, case, quotation marks, dashes, PDF line-break hyphens and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Machine-checked. Machines found this record and checked it against its sources; no person accepted it individually. 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. Dated as the card read is dated: the date of its revision, as the source records it.

Record ID mc-cell-anthropic-claude-opus-4-5-q11