The Operational Risks of AI in Large-Scale Biological Attacks: Results of a Red-Team Study
Research report RR-A2977-2, published 25 January 2024. Date from RAND's publication page for RR-A2977-2; the report PDF itself carries only '© 2024 RAND Corporation'.
- Issued by
- RAND Corporation
- Authors credited
- No authorship claim recorded yet. The source records list RAND Corporation.
- Dates
- Published 2024-01-25 issue evidence
Date from RAND's publication page for RR-A2977-2; the report PDF itself carries only '© 2024 RAND Corporation'.
- Exact source
- RAND publication page for RR-A2977-2 (publication date) RAND Corporation · publication date unknown · Retrieved for the candidate pack on 2026-10-28 (SHA-256 88627299fdd2be1a0fb8bc57ca2d13f19dc6b905216e17105a4fc0eaf81440e0). Publication page as served on 2026-10-28, used only for the stated publication date. Retrieved again at admission on 2026-10-30 (SHA-256 8db1fd8fbf0014fc4ede6a59e10c64ef7b8f749e4f0fbb3ef6520a8cea342cae). Its wording can change; earlier wording is not authenticated.
- The Operational Risks of AI in Large-Scale Biological Attacks: Results of a Red-Team Study (RR-A2977-2) RAND Corporation · publication date unknown · Retrieved for the candidate pack on 2026-10-28 (SHA-256 e09a4103027b4f3c9bd3f8d7e1b7f427fea66f4d636f67c5a254a5f88af9438e). Published PDF of RR-A2977-2, 24 pages, © 2024 Retrieved again at admission on 2026-10-30 (SHA-256 e09a4103027b4f3c9bd3f8d7e1b7f427fea66f4d636f67c5a254a5f88af9438e, the same bytes). Both passes of the candidate pack retrieved this file; the bytes are identical, and one source row carries it.
Appears in
- Arguments about AI and biological risk →1 record on this document
Versions
rand-bio-redteam: 1 recorded version, oldest first, published by RAND Corporation. A version is shown as replacing another only where a record says so. Date order alone never implies it.
- 2024-01-25 · publishedResearch report RR-A2977-2, published 25 January 2024 (this version)
This version
Earliest version recorded here; no replacement is recorded.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Contests · 1
Propositions a passage of this document disputes, or a premise they depend on.
- Currently available AI systems increase an actor's biological-misuse capabilityRAND's report on the operational risks of AI in large-scale biological attacks (RR-A2977-2, 25 January 2024) states that it found no statistically significant difference in the overall viability of biological weapon attack plans generated with or without the aid of the large language models it tested, and that such planning is beyond the capability frontier of the models available in summer 2023.2024-01-25 · publication · Stated in source · Supported Inspect claim & evidence ↗Currently available AI systems increase an actor's biological-misuse capability: propositions page →
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.