Logo image
Autonomous Weapons Systems and the AI Alignment Problem
Journal article   Open access   Peer reviewed

Autonomous Weapons Systems and the AI Alignment Problem

Samuel Hartridge and Brendan Walker-Munro
Journal of international humanitarian legal studies, Vol.16(1), pp.38-65
2025
pdf
Autonomous Weapons Systems and the ai Alignment Problem654.53 kBDownloadView
Published (Version of record) Open Access CC BY V4.0
url
Autonomous Weapons Systems and the ai Alignment ProblemView
Published (Version of record) Open CC BY V4.0

Related links

Metrics

1 File views/ downloads
50 Record Views

Abstract

autonomous weapon systems AI alignment problem international humanitarian law international human rights law legal review of weapon systems
The challenge in deploying Autonomous Weapons Systems (‘AWS’) is not that it can kill people and destroy objects, but ensuring that it only kills the right people and destroys the right objects. In this paper, we use a hypothetical recently discussed at a military AI conference as a springboard to introduce important dimensions of the ‘Alignment Problem’ into the discourse concerning AWS. This paper will consider important dimensions of what is known as the Alignment Problem, why it is difficult to specify smart goals for autonomous systems, why intelligent systems can pursue dumb goals, and the legal implications for assurance of AWS. We begin with some preliminary definitions and conceptual analyses. We then outline the Alignment Problem including introducing the concept of objective functions and rewards. We then turn to an exploration of what the Alignment Problem implies for AWS testing, and why apparently simple solutions may not be effective. From here we discuss the implications that the Alignment Problem has for international law applicable to AWS, addressing legal obligations relating to the responsibility of states to respect and ensure respect for with international humanitarian law (IHL) and international human rights law (IHL).

Details

Logo image