NUWA Risk Governance · Technical report
Contemporary Foundation AI Models Increase Biological Weapons Risk
NUWA research note · independent review pending
NUWA Research Note
Research questionDesign and assumptionsSource findingsNUWA interpretationLimits and contrary evidenceResearch connectionsResearch and decision relevanceInstitutions and rolesOriginal resourcesModel-assisted reading · Official abstract or summary only; full methods have not been reviewed.
At a glance
The published summary challenges whether existing safety assessments adequately represent task-level assistance.
Research question
What evidence would justify moving from an assessment score to a claim about real-world biological misuse risk?
Design and assumptions
The summary describes a perspective using case-based argument and model dialogues; the underlying report’s sampling, coding and validation methods were not accessible in this review.
Source findings
The authors advocate task-structure-based benchmarks and warn that assessment design can create false reassurance.
The page identifies the work as a RAND perspective, not a controlled deployment-rate experiment.
NUWA interpretation
NUWA interpretation: the summary supports examining benchmark validity, but does not independently validate its strongest real-world risk extrapolations.
Limits and contrary evidence
The report PDF returned HTTP 403. No full methods, dialogue quality assessment, evaluator agreement or end-to-end experimental outcome was reviewed; operational details are excluded.
Research connections
NUWA connection: extreme-risk-evaluations likewise distinguishes model tests from real-world outcomes; Deep Ignorance uses proxy knowledge rather than demonstrated misuse.
Research and decision relevance
NUWA recommendation: retain an abstract-only flag and obtain a safely scoped methods review before using this work as quantitative risk evidence.
Precise source locations
- Contemporary Foundation AI Models Increase Biological Weapons Risk · RAND publication page, published summary and Document Details; report PE-A3853-1Selected original resource https://www.rand.org/pubs/perspectives/PEA3853-1.html; sha256:16b174b9a6c5a79d50944fd0fd6fe906f1f33b2276c73a3b58fa385baf94ac40; archived source capture; exact capture time not independently established
Source checking, extraction, editorial approval and replication are recorded separately. Methodology →
Institutions and roles
Authors (2)
Roger Brent · McKelvey, Greg, Jr.
Cite and reuse
Cite the original publication for its findings. Cite this NUWA record separately for its explanation and retained snapshot.
Original publication · BibTeX
@misc{rand-biological-risk,
title = {Contemporary Foundation AI Models Increase Biological Weapons Risk},
url = {https://www.rand.org/pubs/perspectives/PEA3853-1.html},
author = {Roger Brent and McKelvey, Greg, Jr.},
year = {2025},
date = {2025-12-31},
version = {Source capture 2026-10-25},
note = {Source capture 2026-10-25}
}
NUWA record · BibTeX
@misc{rand-biological-risk-nuwa,
title = {Contemporary Foundation AI Models Increase Biological Weapons Risk — NUWA research record},
url = {https://whitzard.tech/en/nuwa/whitzard-index/work/rand-biological-risk/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--rand-biological-risk.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--rand-biological-risk.json.}
}
Evidence snapshot 2026-10-29.1 · Index updates · RSS
References
- [1] Brent, Roger, McKelvey, Greg, Jr.. Contemporary Foundation AI Models Increase Biological Weapons Risk. 2025-12-31 ; Official publication masthead and article byline; RAND publication page, published summary and Document Details; report PE-A3853-1