On monitorability of AI

Author:

Yampolskiy Roman V.ORCID

Abstract

AbstractArtificially intelligent (AI) systems have ushered in a transformative era across various domains, yet their inherent traits of unpredictability, unexplainability, and uncontrollability have given rise to concerns surrounding AI safety. This paper aims to demonstrate the infeasibility of accurately monitoring advanced AI systems to predict the emergence of certain capabilities prior to their manifestation. Through an analysis of the intricacies of AI systems, the boundaries of human comprehension, and the elusive nature of emergent behaviors, we argue for the impossibility of reliably foreseeing some capabilities. By investigating these impossibility results, we shed light on their potential implications for AI safety research and propose potential strategies to overcome these limitations.

Funder

University of Louisville

Publisher

Springer Science and Business Media LLC

Subject

General Earth and Planetary Sciences

Reference127 articles.

1. Aceto, L., A. Achilleos, A. Francalanza, A. Ingólfsdóttir and K. Lehtinen (2019). An operational guide to monitorability. Software Engineering and Formal Methods: 17th International Conference, SEFM 2019, Oslo, Norway, September 18–20, 2019, Proceedings 17, Springer.

2. Akyürek, E., Schuurmans D., Andreas J. , Ma T., Zhou D. (2022). "What learning algorithm is in-context learning? investigations with linear models." arXiv preprint arXiv:2211.15661.

3. Aliman, N.-M., Kester, L., Yampolskiy, R.: Transdisciplinary AI observatory—retrospective analyses and future-oriented contradistinctions. Philosophies 6(1), 6 (2021)

4. Ambartsoumean, V. M., Ampolskiy R. V. Y (2023). "AI Risk Skepticism, A Comprehensive Survey." arXiv preprint arXiv:2303.03885.

5. Amugongo, L. M., Kriebitz A., Boch A., Lütge C. (2023). "Operationalising AI ethics through the agile software development lifecycle: a case study of AI-enabled mobile health applications." AI and Ethics: 1–18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3