NUWA Risk Evaluation · Study
Measuring tactical intelligence targeting and conventional weapons capabilities of AI models
NUWA research note · independent review pending
NUWA Research Note
Research questionDesign and assumptionsSource findingsNUWA interpretationLimits and contrary evidenceResearch and decision relevanceInstitutions and rolesOriginal resourcesModel-assisted reading · Selected sections of the original full text or official article; a complete section-by-section audit remains pending.
At a glance
NUWA interpretation: the source broadens evaluation scope but does not establish end-to-end real-world harmful effectiveness.
Research question
What additional misuse domains need evaluation beyond cyber and biological risk?
Design and assumptions
The official article surveys controlled evaluations of intelligence-analysis and conventional-systems capabilities, alongside platform safeguards.
Source findings
The authors report uneven capability across increasingly difficult simulated conditions.
They explicitly state that many tasks use simulated data and do not measure user uplift directly (Conclusion).
NUWA interpretation
NUWA interpretation: the source broadens evaluation scope but does not establish end-to-end real-world harmful effectiveness.
Limits and contrary evidence
Material constraints and translation from simulation remain unresolved; this dossier deliberately omits tactical details and operational performance recipes.
Research and decision relevance
Model recommendation: retain only nonoperational validity and safeguard implications when reusing these findings.
Precise source locations
- Measuring tactical intelligence targeting and conventional weapons capabilities of AI models · Opening research scopeSelected original resource https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities; sha256:116ea2ea458b9944e91fa58b7a226f6c74c355c81bc461d7e5d39182a6d4598b; archived source capture; exact capture time not independently established
- Measuring tactical intelligence targeting and conventional weapons capabilities of AI models · ConclusionSelected original resource https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities; sha256:116ea2ea458b9944e91fa58b7a226f6c74c355c81bc461d7e5d39182a6d4598b; archived source capture; exact capture time not independently established
Source checking, extraction, editorial approval and replication are recorded separately. Methodology →
Institutions and roles
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{conventional-weapons-evaluations,
title = {Measuring tactical intelligence targeting and conventional weapons capabilities of AI models},
url = {https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities},
year = {2026},
date = {2026-09-10},
version = {Source capture 2026-10-25},
note = {Source capture 2026-10-25}
}
NUWA record · BibTeX
@misc{conventional-weapons-evaluations-nuwa,
title = {Measuring tactical intelligence targeting and conventional weapons capabilities of AI models — NUWA research record},
url = {https://whitzard.tech/en/nuwa/whitzard-index/work/conventional-weapons-evaluations/},
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--conventional-weapons-evaluations.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--conventional-weapons-evaluations.json.}
}
Evidence snapshot 2026-10-29.1 · Index updates · RSS
References
- [1] Measuring tactical intelligence targeting and conventional weapons capabilities of AI models. 2026-09-10 ; Official publication masthead and article byline; Opening research scope; Conclusion