Skip to main navigation Skip to search Skip to main content

A Systematic Analysis of AGI and ASI Existential Risk Scenarios

  • Rutgers - The State University of New Jersey, New Brunswick

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The rapid progress in Artificial Intelligence (AI) and statements by some leading figures in the industry suggest that Artificial General Intelligence (AGI) may be on the verge of becoming a reality. The timeline is highly uncertain, but once AGI emerges, it can be used to refine its own efficiency, potentially resulting in an explosive increase in capability known as a singularity. The potential for far-reaching effects demands that we consider the possible outcomes and risks. Artificial superintelligence (ASI) represents the next level of AI, at which it would surpass even the most gifted humans in cognitive competence. This paper critically examines the potential end-game implications of AGI and ASI systems, particularly the presence or absence of human-in-the-loop oversight. Building on recent advancements in large language models (LLMs) and multimodal AI, the study investigates how advanced AI might inadvertently or deliberately erode safeguards against weapons proliferation, exacerbate geopolitical tensions, and undermine global controls on high-risk technologies. Further, it offers a comprehensive taxonomy of existential risks associated with AI, including Artificial Narrow Intelligence (ANI), AGI, and ASI, culminating in the introduction of a pioneering multimodal nuclear weapon-related jailbreaking study, revealing critical vulnerabilities and potential misuse of next-generation AI systems.

Original languageEnglish
Title of host publicationAI Revolution
Subtitle of host publicationResearch, Ethics and Society - International Conference, AIR-RES 2025, Proceedings
EditorsHamid R. Arabnia, Leonidas Deligiannidis, Soheyla Amirian, Farid Ghareh Mohammadi, Farzan Shenavarmasouleh
PublisherSpringer Science and Business Media Deutschland GmbH
Pages17-37
Number of pages21
ISBN (Print)9783032123121
DOIs
StatePublished - 2026
EventInternational Conference on the AI Revolution: Research, Ethics, and Society, AIR-RES 2025 - Las Vegas, United States
Duration: 14 Apr 202516 Apr 2025

Publication series

NameCommunications in Computer and Information Science
Volume2721 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceInternational Conference on the AI Revolution: Research, Ethics, and Society, AIR-RES 2025
Country/TerritoryUnited States
CityLas Vegas
Period14/04/2516/04/25

Keywords

  • AGI
  • ASI
  • Artificial Narrow Intelligence (ANI)
  • Existential Risk
  • Human-in-the-Loop (HITL)
  • Jailbreaking
  • Multimodal AI
  • Nuclear Weapons Proliferation

Fingerprint

Dive into the research topics of 'A Systematic Analysis of AGI and ASI Existential Risk Scenarios'. Together they form a unique fingerprint.

Cite this