Journal article
Autonomous Weapons Systems and the AI Alignment Problem
Journal of international humanitarian legal studies, Vol.16(1), pp.38-65
2025
Metrics
1 File views/ downloads
50 Record Views
Abstract
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
- Title
- Autonomous Weapons Systems and the AI Alignment Problem
- Creators
- Samuel Hartridge - The University of QueenslandBrendan Walker-Munro - Southern Cross University
- Publication Details
- Journal of international humanitarian legal studies, Vol.16(1), pp.38-65
- Publisher
- Brill - Nijhoff
- Identifiers
- 991013271210802368
- Copyright
- © Samuel Hartridge and Brendan Walker-Munro, 2025
- Academic Unit
- Faculty of Business, Law and Arts
- Language
- English
- Resource Type
- Journal article