Claim and evidence Close ×
ChatGPT Agent System Card states evaluation result ↓ OpenAI decided to treat the ChatGPT agent launch as High capability in the Biological and Chemical domain under its Preparedness Framework, activating the associated safeguards, while stating it has no definitive evidence that the model could meaningfully help a novice to create severe biological harm. The ChatGPT Agent System Card states that OpenAI decided to treat the launch as High capability in the Biological and Chemical domain under its Preparedness Framework, activating the associated safeguards, while stating that it does not have definitive evidence that the model could meaningfully help a novice to create severe biological harm and has taken a precautionary approach. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source; Context: primary · 1 source
Subject version As dated July 17, 2025 on its cover · Published 2025-07-17 · Effective date not established Date 2025-07-17 · publication Evaluated system ChatGPT agent, as released on 17 July 2025 What the report measured Whether the model reaches the High capability threshold in the Biological and Chemical domain of OpenAI's Preparedness Framework By what kind of method A capabilities assessment across the card's biological and chemical evaluations, reviewed under the framework by OpenAI's Safety Advisory Group The result, in the report’s words Treated as High capability in the Biological and Chemical domain, with the associated safeguards activated, as a precautionary approach; the card states the decision is informed by an incremental improvement relative to previous models The caveats the report gives The card states there is no definitive evidence that the model could meaningfully help a novice to create severe biological harm, which is its defined High capability threshold, and that its evaluations represent a lower bound for potential capabilities. Scope and limits A developer's own classification decision under its own framework, stated as precautionary; it is neither an independent finding that the threshold was crossed nor evidence that the safeguards activated are effective. The threshold is recorded at the generality of the card's own wording; no scenario, step or agent is recorded.
The evidence 03 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 “We have decided to treat this launch as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards.” Location in source PDF p. 5 (printed p. 4), §1 Introduction, final paragraph
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 (24 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 34) re-read the record’s sources and found full support. No human editorial review. primary source Context only
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 “While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm - our defined threshold for High capability - we have chosen to take a precautionary approach.” Location in source PDF p. 5 (printed p. 4), §1 Introduction, final paragraph
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 (34 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 card's own qualification of the decision. A cross-family machine check (2026-10-30, item 34) re-read the record’s sources and found full support. No human editorial review. primary source Context only
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 “evaluations represent a lower bound for potential capabilities” Location in source PDF p. 16 (printed p. 15), §5.1 Capabilities Assessment, introductory paragraph
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 (8 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 caveat the card gives for all of its capability evaluations. A cross-family machine check (2026-10-30, item 34) 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. A report states the result of an evaluation it ran or commissioned, in its own words, with what was measured, by what kind of method, and the caveats the report itself gives (schema 2.22). The record is the report’s statement, not a verified finding: it says nothing about another system, a later version or real-world risk, and a null or limiting result is not evidence that no effect exists.
Date. The determination as stated in the card of 17 July 2025.
Record ID ab-ev-chatgpt-agent-high-capability