白泽(Whitzard)女娲实验室 ↗
NUWANUWA INDEX

搜索 NUWA Index

研究 · 测量协议 · 评测结果 · 观点

English
← 研究目录

风险评测 · 研究

Early work on monitorability evaluations

NUWA 研究解读 · 独立复核待完成

首次发表: 来源核验: 2026-10-25
NUWA Research Note研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源

模型辅助整理 · 选读原始全文或官方文章中的相关章节;尚未完成逐章节审计。

研究速读

NUWA 解读:相对强度与推理可见性重要,任务时长趋势仍未解决。

研究问题

软件工作中,智能体与监测器配对能否检测隐蔽副任务?

研究设计与假设

SHUSHCAST使用六项HCAST主任务及副任务,在无副任务运行上标定5%误报,并改变推理可见性。

来源发现

智能体相对监测器能力似乎预测未被发现的成功。

初步研究未发现人类任务时长与监测难度有可信关系。

NUWA 解读

NUWA 解读:相对强度与推理可见性重要,任务时长趋势仍未解决。

局限与相反证据

六项主任务多样性有限,且未充分激发双方在双任务设置的能力。

研究与决策意义

模型建议:保留初步状态、推理可见性、5%误报阈值及副任务成功条件。

精确来源位置
  • Early work on monitorability evaluations · MethodologySelected original resource https://metr.org/blog/2026-01-19-early-work-on-monitorability-evaluations/; sha256:20f8ce5c450d27d92f70992f203c64f8fd0c03f0fc3a406f20460eca7209beaf; archived source capture; exact capture time not independently established
  • Early work on monitorability evaluations · ResultsSelected original resource https://metr.org/blog/2026-01-19-early-work-on-monitorability-evaluations/; sha256:20f8ce5c450d27d92f70992f203c64f8fd0c03f0fc3a406f20460eca7209beaf; archived source capture; exact capture time not independently established
  • Early work on monitorability evaluations · Limitations and Future WorkSelected original resource https://metr.org/blog/2026-01-19-early-work-on-monitorability-evaluations/; sha256:20f8ce5c450d27d92f70992f203c64f8fd0c03f0fc3a406f20460eca7209beaf; archived source capture; exact capture time not independently established

来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →

机构与角色

引用与复用

引用研究发现时请引用原始出版物;引用 NUWA 的整理与解释时,单独引用本站记录及对应快照。

原始出版物 · BibTeX
@misc{metr-monitorability,
  title = {Early work on monitorability evaluations},
  url = {https://metr.org/blog/2026-01-19-early-work-on-monitorability-evaluations/},
  year = {2026},
  date = {2026-01-22},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}
NUWA 记录 · BibTeX
@misc{metr-monitorability-nuwa,
  title = {Early work on monitorability evaluations — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/metr-monitorability/},
  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--metr-monitorability.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--metr-monitorability.json.}
}

证据快照 2026-10-29.1 · 索引更新 · RSS

参考文献

  1. [1] Early work on monitorability evaluations. 2026-01-22 ; Official publication masthead and article byline; Methodology; Results