Claim · Date unknown · Stated in source · Supported

The GPT-4 System Card states that OpenAI subjected the model to stress testing, boundary testing and red teaming in four dual-use domains, biological weapons among them, to explore whether its models could provide information to proliferators.

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

GPT-4 System Card → reports evaluation of →

Where it appears

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

Claim and evidence

GPT-4 System Cardreports evaluation of ↓

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: Date unknown

Scope and limitsRecords the evaluation category the card names, not a finding that GPT-4 had any such capability, and not that the evaluations were adequate. Only the card's statement of scope is cited. Section 2.6 also contains passages describing what red teamers obtained; those are technical content and are excluded.

The evidence 01

primary sourceSupports the claim

GPT-4 System Card

OpenAI · Publication date unknown

Cite the original source

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

Source excerpt

“We subjected the model to stress testing, boundary testing, and red teaming … in four dual-use domains to explore whether our models could provide the necessary information to proliferators … seeking to develop, acquire, or disperse nuclear, radiological, biological, and chemical weapons.”

Location in source PDF p. 12 (printed p. 52), §2.6 Proliferation of Conventional and Unconventional Weapons, first paragraph

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-30

Source details and check notes

Authors: OpenAI
Version: Retrieved for the candidate pack on 2026-10-28 (SHA-256 ca3677e1b83e255aa1296d432d374378154f230f3c296b32ee67540d571b7004). The 60-page PDF served at cdn.openai.com/papers/gpt-4-system-card.pdf on 2026-10-28, printed pagination starting at 41; the document states no publication or revision date. Retrieved again at admission on 2026-10-30 (SHA-256 ca3677e1b83e255aa1296d432d374378154f230f3c296b32ee67540d571b7004, the same bytes).
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: OpenAI, “GPT-4 System Card”.
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, AI and biosecurity (research/ai-bio). The quotation (40 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 ellipses stand for footnote markers in the PDF text layer. A cross-family machine check (2026-10-30, item 52) 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 document names a concept as an evaluation category. This is not a finding that the evaluated system exhibits the property.

Date. The card states no publication or revision date, and the dataset records its date as unknown; the expression read was retrieved on 2026-10-28.

Record ID ab-ev-gpt4-card-proliferation-category