Claim · 2026-10-29 · publication · Stated in source · Supported

Addendum to GPT-6 Luna System Card: October 29, 2026 Update states in part what the model-card question “Red-teaming” 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

Addendum to GPT-6 Luna System Card: October 29, 2026 Update → states provision → Red-teaming

Where it appears

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

Claim and evidence

Addendum to GPT-6 Luna System Card: October 29, 2026 Updatestates provision ↓Red-teaming

Machine-checkedStated in sourceSupported

Supporting evidence: primary · 1 source

Provision: Model-card question · provision ID model-card-q12
Subject version: As dated 2026-10-29 on its cover · Published 2026-10-29 · Effective date not established
Date: 2026-10-29 · publication Records dated 2026 →

Scope and limitsThe card describes an automated red-teaming agent used in adversarial training, and automated 'GPT-Red' evaluations of direct and indirect prompt injection. It does not describe adversarial testing of this model as red-teaming, and reports no human red-teaming. Search for the rest of the criterion: Whole card. Terms searched: “red team”, “red-team”, “adversarial”, “attacker”, “jailbreak”. Passages read and not counted: §4.1 Jailbreaks, PDF pp. 6–7: Reports defender success rates against an automated attacker; not described as red-teaming. Stated, partly: the passage has what the question’s criterion asks for, in a weaker or narrower form than the criterion’s own words. 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

Addendum to GPT-6 Luna System Card: October 29, 2026 Update

OpenAI · 2026-10-29

Cite the original source

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

Source excerpt

“we use adversarial training with an automated red-teaming agent to strengthen resistance to malicious instructions”

Location in source §4.2 Prompt Injection, PDF p. 7 (printed p. 6)

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: OpenAI
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 766262a78fcaeae31534174554bae5b259a418eaffbf9f23a9460343943b9d8e) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256.
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: OpenAI, “Addendum to GPT-6 Luna System Card: October 29, 2026 Update”, 2026-10-29.
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 (15 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 766262a78fcaeae31534174554bae5b259a418eaffbf9f23a9460343943b9d8e) 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. A cross-family machine check (2026-11-03, item 124) checked this passage’s cell; its finding was applied at the adjudication of 2026-11-03. No human editorial review.

primary sourceSupports the claim

Addendum to GPT-6 Luna System Card: October 29, 2026 Update

OpenAI · 2026-10-29

Cite the original source

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

Source excerpt

“For our evaluations, we use the GPT-Red automated evaluations introduced in the GPT-5.6 system card.”

Location in source §4.2 Prompt Injection, PDF p. 7 (printed p. 6)

How it was read Retrieved directly from the publisher

Machine-checked · 2026-11-03

Source details and check notes

Authors: OpenAI
Version: Retrieved for the candidate pack on 2026-11-02 (SHA-256 766262a78fcaeae31534174554bae5b259a418eaffbf9f23a9460343943b9d8e) directly from the publisher’s host. Retrieved again on 2026-11-03 with the same SHA-256.
Canonical address: Open the canonical source ↗
Accessed: 2026-11-02
Language: English (en)
Attribution: OpenAI, “Addendum to GPT-6 Luna System Card: October 29, 2026 Update”, 2026-10-29.
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 (15 words) matched the card’s text retrieved for the candidate pack on 2026-11-02 (SHA-256 766262a78fcaeae31534174554bae5b259a418eaffbf9f23a9460343943b9d8e) 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. A cross-family machine check (2026-11-03, item 124) checked this passage’s cell; its finding was applied at the adjudication of 2026-11-03. 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: its printed date, as the source records it.

Record ID mc-cell-openai-gpt-6-luna-october-29-q12