Harry R. Lloyd

hrl [at] unc [dot] edu

Research

Publications by topic:↗

Papers by date:

Moral uncertainty, pure justifiers, and agent-centred options. Australasian Journal of Philosophy. [coauthor: Patrick Kaczmarek | pre-publication pdf | doi]
- Synopsis: The expected choiceworthiness maximising approach to moral uncertainty cannot properly handle agent-centred prerogatives; we propose an alternative that can
Animals, future generations, and resource-rational contractualism. Behavioral and Brain Sciences.

2026:
- MoReBench: evaluating procedural and pluralistic moral reasoning in language models, more than outcomes. Proceedings of the International Conference on Learning Representations 2026. [authors: Yu Ying Chiu, Michael S. Lee, Rachel Calcott, Brandon Handoko, Paul de Font-Reaulx, Paula Rodriguez, Chen Bo Calvin Zhang, Ziwen Han, Udari Madhushani Sehwag, Yash Maurya, Christina Q. Knight, Harry R. Lloyd, Florence Bacus, Mantas Mazeika, Bing Liu, Yejin Choi, Mitchell L. Gordon, Sydney Levine | arXiv | website | ScaleAI blog post | ScaleAI YouTube interview]
2025:

Moral uncertainty, expected choiceworthiness, and variance normalization. Canadian Journal of Philosophy, 55.2, 157-73. [pre-publication pdf | doi]
- Synopsis: Philosophers of moral uncertainty sometimes suggest that 'statistical normalization' techniques can be used to compare choiceworthiness values across different moral theories; but I argue that these techniques have lots of problems.
Moral uncertainty and expected truthlikeness. Synthese, 206.265, 1-32. [pre-publication pdf | doi | read-only pdf]
- Synopsis: Rather than choosing actions that maximise expected choiceworthiness, perhaps we should instead choose theories that maximise expected truthlikeness
- Won the Rocky Mountain Ethics Congress' 2024 Young Ethicist Prize (co-winner; open to any untenured presenters, including tenure-track faculty; $350)
- Anonymous reviewer: "The first paper in years in the moral uncertainty literature that opens new directions of research."

Moral uncertainty, proportionality, and bargaining. Ergo, 12.44, 1142-71 [coauthors: Patrick Kaczmarek and Michael Plant | open-access pdf | doi]
- Synopsis: Bargaining-theoretic approaches to moral uncertainty have several advantages over the expected choiceworthiness maximising approach
- Real-world application: Helped to inform this online tool for choosing a portfolio of charitable donations
Disagreement, AI alignment, and bargaining. Philosophical Studies, 182.7, 1757-87 [pre-publication pdf | doi]
- Synopsis: When stakeholders disagree about how an AI should behave, resolving this disagreement through simulated bargaining is better than resolving it through voting or expected value maximisation
Gentrification: a philosophical analysis and critique. Journal of Urban Affairs, 47.4, 1246-64. [pre-publication pdf | doi]
- Synopsis: Forms of gentrification that don't displace many land users are still pro tanto morally objectionable insofar as they damage local communities

2024:
- Redistribution and selfishness. Analysis, 84.3, 493-503. [pre-publication pdf | doi]
  - Synopsis: Even in a world of completely unselfish people, redistributive taxation would still discourage productive contributions to national wealth
- Better than what?: embryo selection, gene editing, and evaluative counterfactuals. American Journal of Bioethics, 24.8, 55-7. [pre-publication pdf | doi]
2023:
- Large language models and biorisk. American Journal of Bioethics, 23.10, 115-8. [coauthors: William D'Alessandro and Nathaniel Sharadin | pre-publication pdf | doi]
2021:
- Moral status, luck, and modal capacities: debating Shelly Kagan. Journal of Applied Philosophy, 38.2, 273-87. [pre-publication pdf | doi]
  - Synopsis: Those like Kagan who want to argue that animals have a lower moral status than us can achieve extensional adequacy only through theoretical commitments that are difficult to justify

Working papers:

Moral Uncertainty and Bargaining. Yale University, PhD dissertation, December 2025. [pdf | email me for a more recent draft]
- Work influenced:
  - Richard Yetter Chappell, 2025. Subagents for shrimp: ... and other good causes. Good Thoughts blog post. [hyperlink]
  - Richard Yetter Chappell, 2025. Limiting reason: a principled conservative impulse. Good Thoughts blog post. [hyperlink]
The property rights approach to moral uncertainty. Happier Lives Institute, working paper, October 2022. [pdf | hyperlink | email me for a more recent draft]
Time discounting, consistency, and special obligations: a defence of Robust Temporalism. Global Priorities Institute, working paper no. 11-2021. [pdf | hyperlink | email me for a more recent draft]

Won the Oxford Global Priorities Institute's 2021 Essay Prize for Global Priorities Research (£1000)
Work influenced:
- S. J. Beard and Patrick Kaczmarek, 2024. Existential risk, astronomical waste, and the reasonableness of a pure time preference for well-being. Monist, 107.2, 157-75. [open-access pdf | doi]
- David Thorstad, 2023. Papers I learned from (Part 1: Time discounting, consistency, and special obligations). Reflective Altruism blog post. [hyperlink]

Under review:

[A paper on machine ethics]
- Synopsis: Several AI ethicists have recently suggested a response to stakeholder normative disagreement that is inspired by expected utility theory; but I argue that this response has several problems
[A paper on animal ethics]
- Synopsis: We should incorporate animals into our theories of distributive justice on equal footing with human beings
[A paper on time discounting]
- Synopsis: Although almost all other philosophers reject the idea that temporal proximity could matter morally, I argue that this view is more defensible than is commonly supposed
[A paper on personal identity, fission, and fusion]
- Synopsis: A fissioner survives her operation as a scattered object with Lefty and Righty as her discontiguous parts
[A paper on universities and the future of work]

In preparation: