Publications

Selected publications

Human autonomy in the age of artificial intelligence
Carina Prunkl
Nature Machine Intelligence, 2022

Algorithmic profiling as a source of hermeneutical injustice
Silvia Milano and Carina Prunkl
Philosophical Studies, 2025

International AI Safety Report 2026
Yoshua Bengio, Stephen Clare, Carina Prunkl, Maksym Andriushchenko, Ben Bucknall, Malcolm Murray, Rishi Bommasani, Stephen Casper, Tom Davidson, Raymond Douglas, et al.
arXiv preprint, 2026

Institutionalizing ethics in AI through broader impact requirements
Carina E. A. Prunkl, Carolyn Ashurst, Markus Anderljung, Helena Webb, Jan Leike, and Allan Dafoe
Nature Machine Intelligence, 2021

Human autonomy at risk? An analysis of the challenges from AI
Carina Prunkl
Minds and Machines, 2024

Beyond near- and long-term: towards a clearer account of research priorities in AI ethics and society
Carina Prunkl and Jess Whittlestone
Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2020

Reports and policy-facing outputs

International AI Safety Report: Second key update — technical safeguards and risk management
Yoshua Bengio, Stephen Clare, Carina Prunkl, Maksym Andriushchenko, Ben Bucknall, Philip Fox, Nestor Maslej, Conor McGlynn, Malcolm Murray, Shalaleh Rismani, et al.
arXiv preprint, 2025

International AI Safety Report: First key update — capabilities and risk implications
Yoshua Bengio, Benjamin Bucknall, Stephen Clare, Carina Prunkl, Maksym Andriushchenko, Philip Fox, Tiancheng Hu, Cameron Jones, Sam Manning, Nestor Maslej, et al.
SuperIntelligence–Robotics–Safety & Alignment, 2025

Worker agency in the digital age
Carina Prunkl, Joel Anderson, Ugur Aytac, Jeroen Hopster, Juri Viehoff
UNDP Human Development Report, 2025

A guide to writing the NeurIPS impact statement
Carolyn Ashurst, Markus Anderljung, Carina Prunkl, Jan Leike, Yarin Gal, Toby Shevlane, and Allan Dafoe
GovAI / Medium, 2020

Toward trustworthy AI development: mechanisms for supporting verifiable claims
Miles Brundage, Shahar Avin, Jasmine Wang, Haydn Belfield, Gretchen Krueger, Gillian Hadfield, Heidy Khlaaf, Jingying Yang, Helen Toner, Ruth Fong, et al.
arXiv preprint, 2020

Full publication list

2026

Agency in child-AI interaction: a review of how it is conceptualised, studied, and supported in HCI
Isobel Voysey, Vidminas Vizgirda, Sarah Turner, Leslye Denisse Dias Duran, Zaki Pauzi, Manolis Mavrikis, Carina Prunkl, and Jun Zhao
2026

Examining popular arguments against AI existential risk: a philosophical analysis
Torben Swoboda, Risto Uuk, Lode Lauwaert, Andrew P. Rebera, Ann-Katrien Oimann, Bartlomiej Chomanski, and Carina Prunkl
Ethics and Information Technology, 2026

2025

Algorithmic profiling as a source of hermeneutical injustice
Silvia Milano and Carina Prunkl
Philosophical Studies, 2025

Fairness-aware interactive target variable definition
Dalia Gala, Milo Phillips-Brown, Naman Goel, Carina Prunkl, Laura Alvarez Jubete, Medb Corcoran, and Ray Eitel-Porter
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

A taxonomy of systemic risks from general-purpose AI
Risto Uuk, Carlos Ignacio Gutierrez, Daniel Guppy, Lode Lauwaert, Atoosa Kasirzadeh, Lucia Velasco, Peter Slattery, and Carina Prunkl
arXiv preprint, 2024

Lost in vagueness: towards context-sensitive standards for robustness assessment under the EU AI Act
Roberta Tamponi, Carina Prunkl, Thomas Bäck, and Anna V. Kononova
arXiv preprint, 2025

2024

Human autonomy at risk? An analysis of the challenges from AI
Carina Prunkl
Minds and Machines, 2024

The silent meddling of algorithms
Carina Prunkl
In AI Morality, Oxford University Press, 2024

AI meets biology: a call for community governance
Carina Prunkl
Nature Methods, 2024

2023

LUCID: exposing algorithmic bias through inverse design
Carmen Mazijn, Carina Prunkl, Andres Algaba, Jan Danckaert, and Vincent Ginis
Proceedings of the AAAI Conference on Artificial Intelligence, 2023

LUCID-GAN: conditional generative models to locate unfairness
Andres Algaba, Carmen Mazijn, Carina Prunkl, Jan Danckaert, and Vincent Ginis
World Conference on Explainable Artificial Intelligence, 2023

Is thermodynamics subjective?
Katie Robertson and Carina Prunkl
Philosophy of Science, 2023

2022

Human autonomy in the age of artificial intelligence
Carina Prunkl
Nature Machine Intelligence, 2022

2021

We might be afraid of black-box algorithms
Carissa Véliz, Carina Prunkl, Milo Phillips-Brown, and Theodore M. Lechterman
Journal of Medical Ethics, 2021

Is there a trade-off between human autonomy and the ‘autonomy’ of AI systems?
Carina Prunkl
Conference on Philosophy and Theory of Artificial Intelligence, 2021

Simulation intelligence: towards a new generation of scientific methods
Alexander Lavin, David Krakauer, Hector Zenil, Justin Gottschlich, Tim Mattson, Johann Brehmer, Anima Anandkumar, Sanjay Choudry, Kamil Rocki, Atılım Güneş Baydin, et al.
arXiv preprint, 2021

2020

On the equivalence of von Neumann and thermodynamic entropy
Carina E. A. Prunkl
Philosophy of Science, 2020

A guide to writing the NeurIPS impact statement
Carolyn Ashurst, Markus Anderljung, Carina Prunkl, Jan Leike, Yarin Gal, Toby Shevlane, and Allan Dafoe
GovAI / Medium, 2020

2019

Black hole entropy is thermodynamic entropy
Carina E. A. Prunkl and Christopher G. Timpson
arXiv preprint, 2019

AI & agency
Sarah Newman, Abeba Birhane, Mike Zajko, Osonde A. Osoba, Carina Prunkl, Gabriel Lima, Jon Bowen, Rich Sutton, and Cathy Adams
2019

2018

On the thermodynamical cost of some interpretations of quantum theory
Carina E. A. Prunkl and Christopher G. Timpson
Studies in History and Philosophy of Science Part B: Studies in History and Philosophy of Modern Physics, 2018

The scope of thermodynamics
Carina Prunkl
PhD thesis, University of Oxford, 2018

2013

Impulsivity, self-control, and hypnotic suggestibility
V. U. Ludwig, C. Stelzel, H. Krutiak, C. E. Prunkl, R. Steimke, L. M. Paschke, N. Kathmann, and H. Walter
Consciousness and Cognition, 2013