NUWA Risk Governance · Technical report
Embedded Evaluators are necessary for meaningful external testing
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 · Selected sections of the original full text or official article; a complete section-by-section audit remains pending.
At a glance
The essay argues for continuing deep access and independence protections, beyond late checkpoint testing.
Research question
What access and institutional protections would let an external evaluator verify claims across training and internal deployment?
Design and assumptions
The authors use recent incident and evaluation examples to motivate employee-equivalent access, continuing investigation, publication, engagement transparency and protection against dismissal.
Source findings
Process claims require checking response procedures and personnel authority, not just model behavior.
The proposal distinguishes company-specific continuity from assessment specialists who work across organizations.
NUWA interpretation
NUWA interpretation: evaluator access, independence and disclosure are separate conditions; a nominal external review label does not guarantee any of them.
Limits and contrary evidence
This is a normative institutional proposal. Described commitments and collaborations are source-attributed examples, not independently audited evidence that the proposed regime exists or suffices.
Research connections
NUWA connection: training-run-evaluations provides the earlier checkpoint/data taxonomy; the Hugging Face investigation illustrates how additional access revised an incident account.
Research and decision relevance
NUWA recommendation: document scope, access denials, redactions, publication rights and escalation authority in each external-assurance record.
Precise source locations
- Embedded Evaluators are necessary for meaningful external testing · Current external access is insufficient for meaningful safety assessmentsSelected original resource https://www.apolloresearch.ai/blog/embedded-evaluators-are-necessary-for-meaningful-external-testing; sha256:f4c32b1232a47868f54d5d0b513348209cf6bb5c5742fbf00129c0e751264fea; archived source capture; exact capture time not independently established
- Embedded Evaluators are necessary for meaningful external testing · Embedded evaluations are necessarySelected original resource https://www.apolloresearch.ai/blog/embedded-evaluators-are-necessary-for-meaningful-external-testing; sha256:f4c32b1232a47868f54d5d0b513348209cf6bb5c5742fbf00129c0e751264fea; archived source capture; exact capture time not independently established
- Embedded Evaluators are necessary for meaningful external testing · Requirements to make Embedded Evaluations a successSelected original resource https://www.apolloresearch.ai/blog/embedded-evaluators-are-necessary-for-meaningful-external-testing; sha256:f4c32b1232a47868f54d5d0b513348209cf6bb5c5742fbf00129c0e751264fea; archived source capture; exact capture time not independently established
- Embedded Evaluators are necessary for meaningful external testing · Embedded evaluations are necessary but not sufficient for safetySelected original resource https://www.apolloresearch.ai/blog/embedded-evaluators-are-necessary-for-meaningful-external-testing; sha256:f4c32b1232a47868f54d5d0b513348209cf6bb5c5742fbf00129c0e751264fea; 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{embedded-evaluators,
title = {Embedded Evaluators are necessary for meaningful external testing},
url = {https://www.apolloresearch.ai/blog/embedded-evaluators-are-necessary-for-meaningful-external-testing},
year = {2026},
date = {2026-09-29},
version = {Source capture 2026-10-25},
note = {Source capture 2026-10-25}
}
NUWA record · BibTeX
@misc{embedded-evaluators-nuwa,
title = {Embedded Evaluators are necessary for meaningful external testing — NUWA research record},
url = {https://whitzard.tech/en/nuwa/whitzard-index/work/embedded-evaluators/},
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--embedded-evaluators.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--embedded-evaluators.json.}
}
Evidence snapshot 2026-10-29.1 · Index updates · RSS
References
- [1] Embedded Evaluators are necessary for meaningful external testing. 2026-09-29 ; Official publication masthead and article byline; Current external access is insufficient for meaningful safety assessments; Embedded evaluations are necessary