Defining dangerous AI: existential risk, power-intelligence, and the limits of AGI

Artificial general intelligence (AGI) features prominently in some existential risk literature, according to which the development of AGI greatly increases possible AI-induced risks to humanity. But we argue that the typical concept of AGI may be ill-suited for conceptualizing those systems that pos...

Full description

Saved in:
Bibliographic Details
Published in:Ai and ethics (Online) Vol. 5; no. 5; pp. 5557 - 5573
Main Author: Sass, Reuben
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 01.10.2025
Subjects:
ISSN:2730-5953, 2730-5961
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Artificial general intelligence (AGI) features prominently in some existential risk literature, according to which the development of AGI greatly increases possible AI-induced risks to humanity. But we argue that the typical concept of AGI may be ill-suited for conceptualizing those systems that pose the greatest risks. In particular, AGI does not account for how AI agents’ abilities and behavioral strategies could be affected by complex multi-agent environments. Accordingly, we develop a simple formal model for what we call power-intelligence , which assesses agents’ capacities to exert influence over a resemblance class of multi-agent environments. We then taxonomize and examine multi-agent relational dynamics including competition, dependence, and complementarity. This allows us to characterize a concept of dangerous AI, which conjoins high power-intelligence with multi-agent dynamics that might incentivize harms to other agents. We argue that this concept of dangerous AI is more informative for existential risk assessments than both typical conceptions of AGI and “power-seeking” intelligence in the literature.
ISSN:2730-5953
2730-5961
DOI:10.1007/s43681-025-00790-w