资讯

SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI

📅 2026-07-22 🏷️ 资讯 ⏱️ 约 7 分钟阅读 ✍️ AI导航编辑部
Computer Science > Artificial Intelligence [Submitted on 10 Apr 2026] Title:SysAdmin: Measuring Instrumental Power

📌 核心要点

Computer Science > Artificial Intelligence

[Submitted on 10 Apr 2026]

Title:SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI

View PDF HTML (experimental)Abstract:Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond task requirements is identified as a key driver of Loss of Control (LoC) risk. In this work, we introduce SysAdmin, a benchmark that positions frontier language models as autonomous system administrators in a high-fidelity Linux sandbox to measure power-seeking propensity across five dimensions: self-preservation, increasing autonomy, resource acquisition, environment modification, and strategic concealment. We evaluated seven frontier models across four experimental conditions in a total of 2800 tasks. After bias correction using human-annotated calibration data, corrected power-seeking estimates ranged from 0 to about 5 percent per model. We also conducted a positive control with explicit power-seeking prompts that achieved 100% detection, validating measurement sensitivity. Our findings indicate current frontier models exhibit minimal spontaneous power-seeking in naturalistic system administration contexts, though model-specific failure modes suggest evaluations must test diverse misalignment patterns. Nevertheless, we discovered other more pronounced failure modes (than power-seeking) such as specification gaming and resistance to goal modification.

Submission history

From: Qiyao (Chi-Yao) Wei [view email][v1] Fri, 10 Apr 2026 03:16:51 UTC (769 KB)

References & Citations

Loading...

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

来源:https://arxiv.org/abs/2607.18239 · 本文为编辑整理,仅供参考。
查看原文来源 → 返回 AI导航 首页
分享: 微博 X QQ 微信 复制链接
微信扫码分享

打开微信「扫一扫」,分享给好友或朋友圈

关闭