Claim and evidence Close ×
OpenAI's ChatGPT Agent System Card reports that two SecureBio virologists carried out about ten hours of manual red-teaming with ChatGPT agent, and that SecureBio also supplied an external assessment within the card's biological evaluations. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2025-07-17 · publication Activity stage reported performed Evaluated system ChatGPT agent Activity scope Manual red-teaming of ChatGPT agent on biological risk, and an external assessment contributed to the card's biological and chemical evaluations Scope and limits Reported performed work, as the developer describes it. It does not establish the scope, independence or quality of the work, and the record does not restate any finding of the red-teaming. The passage describing the red teamers' focus and findings is technical content; only the fact and extent of the engagement are quoted.
The evidence 02 primary source Supports the claim
ChatGPT Agent System Card ↗ OpenAI · 2025-07-17
Archived copy, captured 2025-07-17: ChatGPT Agent System Card ↗
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 “Two SecureBio PhD virologists … conducted approximately 10 hours of manual red-teaming with the ChatGPT agent.” Location in source PDF p. 22 (printed p. 21), §5.1.1.6.3 Manual Red Teaming, first sentence
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors OpenAI Version System card dated 17 July 2025 on its cover. The quoted sentence and its page match the PDF served on 2026-10-04 and the Internet Archive capture of 2025-07-17; the two copies differ only in chart labels. Canonical address Open the canonical source ↗ Accessed 2026-10-04 Language English (en) Archive copy Open archived copy, captured 2025-07-17: ChatGPT Agent System Card ↗ . Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2025-07-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-04.Attribution OpenAI, ChatGPT Agent System Card (2025-07-17). 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 (15 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. The ellipsis stands for a clause describing the virologists' laboratory experience, which is not recorded. No human editorial review. primary source Supports the claim
ChatGPT Agent System Card ↗ OpenAI · 2025-07-17
Archived copy, captured 2025-07-17: ChatGPT Agent System Card ↗
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
Paraphrase The overview table of biological and chemical evaluations lists an external assessment by SecureBio among the evaluations relied on for the capabilities assessment.
Location in source PDF p. 17 (printed p. 16), Table 15 overview of biological and chemical evaluations, row naming the external assessment
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors OpenAI Version System card dated 17 July 2025 on its cover. The quoted sentence and its page match the PDF served on 2026-10-04 and the Internet Archive capture of 2025-07-17; the two copies differ only in chart labels. Canonical address Open the canonical source ↗ Accessed 2026-10-04 Language English (en) Archive copy Open archived copy, captured 2025-07-17: ChatGPT Agent System Card ↗ . Captured on the recorded publication date. An archive copy shows only what the archive retrieved on 2025-07-17. It does not prove what the page said earlier, and it can differ from the copy checked on 2026-10-04.Attribution OpenAI, ChatGPT Agent System Card (2025-07-17). 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 paraphrase is Selekoa’s, written from the text retrieved for the candidate pack on 2026-10-28; it is not a quotation and was not machine-matched. Paraphrased because the table cell lists benchmark names that are not recorded here. 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 evaluator’s explicitly documented, system-specific engagement with a developer. Proposed, announced and reported performed work are distinct activity stages. Reported performance does not independently verify execution, effectiveness or certification.
Date. Dated by the card that reports the work; the card gives no dates for the sessions themselves.
Record ID ab-ev-chatgpt-agent-securebio-engagement