6 papers
A three-dimensional typology of agency for advanced AI systems
Willem Fourie
Research on the agency of advanced artificial intelligence (AI) systems focuses on agency as a normative concept and on the agency of particularly agentic AI systems. While recent…
The CRAFT principles for the responsible use of large language models in policymaking
Willem Fourie, Gray Manicom, Tanya de Villiers-Botha
Policymakers around the world face the question of how to use artificial intelligence in general, and large language models in particular, to improve the policymaking process. Used…
User identity conditions moral wrongness ratings in non-reasoning large language models
Willem Fourie, Isabel Ray, Gray Manicom
This study adopts a behavioural bottom-up approach to AI value alignment to investigate whether an implicitly conveyed user identity shifts the moral evaluations of large language…
Mitigating loss of control in advanced AI systems through instrumental goal trajectories
Willem Fourie
Researchers at artificial intelligence labs and universities are concerned that highly capable artificial intelligence (AI) systems may erode human control by pursuing instrumental…
An Aristotelian ontology of instrumental goals: Structural features to be managed and not failures to be eliminated
Willem Fourie
Instrumental goals such as resource acquisition, power-seeking, and self-preservation are key to contemporary AI alignment research, yet the phenomenon's ontology remains under-the…
Deciding how to respond: A deliberative framework to guide policymaker responses to AI systems
Willem Fourie
The discourse on responsible artificial intelligence (AI) regulation is understandably dominated by risk-focused assessments and analyses. This approach reflects the fundamental un…