A Psychopathological Approach to Safety Engineering in AI and AGI

TL;DR

This paper proposes a novel approach to AI safety by modeling harmful behaviors in AI and AGI as psychological disorders, enabling psychopathological methods for analysis and control of misbehaviors.

Contribution

It introduces a new perspective of applying psychopathological models to AI safety, addressing complexity challenges in controlling AGI behaviors.

Findings

Psychopathological approaches are feasible for AI safety analysis.

Modeling AI misbehaviors as disorders offers new control strategies.

Directions for future research in diagnosis and treatment of AI behaviors.

Abstract

The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety. It follows that the envisioned instances of Artificial General Intelligence (AGI) will also suffer from challenges of complexity. To tackle such issues, we propose the modeling of deleterious behaviors in AI and AGI as psychological disorders, thereby enabling the employment of psychopathological approaches to analysis and control of misbehaviors. Accordingly, we present a discussion on the feasibility of the psychopathological approaches to AI safety, and propose general directions for research on modeling, diagnosis, and treatment of psychological disorders in AGI.