معرفی
Elliott Thornley is a Postdoctoral Research Fellow at the Global Priorities Institute, University of Oxford, and a Philosophy Fellow at the Center for AI Safety. His academic role involves advanced research in ethics and decision theory, particularly as they apply to artificial intelligence and long-term societal challenges.
Thornley holds a DPhil (PhD) from the University of Oxford, focusing on normative ethics and population axiology. His research bridges theoretical philosophy with practical applications, addressing topics such as AI safety, catastrophic risk mitigation, and ethical frameworks for artificial agents.
Key research themes include population ethics (e.g., procreation asymmetry, critical levels), decision-theoretic approaches to AI control (e.g., shutdownable agents), and the moral implications of longtermism. His work combines formal methods with philosophical analysis to tackle dilemmas in both human and artificial decision-making systems.
Notable publications explore the shutdown problem in AI engineering, dilemmas in person-affecting ethics, and the limitations of longtermism in policy prioritization. Thornley’s interdisciplinary approach integrates philosophy, computer science, and public policy to address pressing existential risks and ethical challenges in technology.
He is affiliated with the Global Priorities Institute and the Center for AI Safety, contributing to initiatives that aim to align advanced technologies with long-term human flourishing. His research has been published in journals like Analysis, Philosophical Studies, and Economics and Philosophy.
