Jared Moore
How can we get AI to do what we want?
I’m a computer science Ph.D. student at Stanford. There, I recenlty taught a course with David Gottleib on How to Make a Moral Agent.
Before, I was a lecturer at the University of Washington School of Computer Science, where I did my masters. There, I made a class on the philosophy of AI and regularly taught the ethics course. I also wrote a satirical novel about AI. I’ve worked at the Allen Institute for AI, Xnor.ai, and Wadhwani AI.
Email me with my first name at the address of this site.
An ambigram of my name, made by Doug.
Publications
On socially-beneficial AI
Moore, J., Grabb, D., Agnew, W., Klyman, K., Chancellor, S., Ong, D. C., Haber, N. (2025). Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers. In Proceedings of the Conference on Fairness, Accountability, and Transparency. https://dl.acm.org/doi/10.1145/3715275.3732039 [Github] [HAI Blog] [NYTimes]
Moore, J. (2020). Towards a More Representative Politics in the Ethics of Computer Science. In Proceedings of the Conference on Fairness, Accountability, and Transparency. https://dl.acm.org/doi/abs/10.1145/3351095.3372854
Moore, J. (2019) AI for not bad. Frontiers in Big Data 2:32. doi: 10.3389/fdata.2019.00032
On understanding, theory of mind
Moore, J., Cooper, N., Overmark, R., Cibralic, B., Jones, C. R., Haber, N. (2025) Do Large Language Models Have a Planning Theory of Mind? Evidence from a Multi-Step Persuasion Task. SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs. In Second Conference on Language Modeling. https://arxiv.org/abs/2507.16196 [Github] [Demo]
Gu, Y., Tafjord, O., Kim, H., Moore, J., Le Bras, R., Clark, P., Choi Y. (2024) SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs. https://arxiv.org/abs/2410.13648
Ye, A., Moore, J., Novick, R., Zhang, A. (2024) Language Models as Critical Thinking Tools: A Case Study of Philosophers. In First Conference on Language Modeling. https://arxiv.org/abs/2404.04516
Thrush, T., Moore, J., Monares, M., Potts, C., Kiela, D. (2024) I am a Strange Dataset: Metalinguistic Tests for Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. https://arxiv.org/abs/2401.05300
Moore, J. (2022). Language Models Understand Us, Poorly. In Findings of EMNLP 2022. https://arxiv.org/abs/2210.10684
On values, alignment
(under review) Moore, J., Y., Choi, Levine, S. (2024) Intuitions of Compromise: Utilitarianism vs. Contractualism. https://arxiv.org/abs/2410.05496 [Github]
Moore, J., Deshpande, T., Yang, D. (2024) Are Large Language Models Consistent over Value-laden Questions? In Findings of EMNLP 2024. http://arxiv.org/abs/2407.02996 [HAI blog] [Github]
Sorensen, T., Moore, J., Fisher, J., Gordon, M., Mireshghallah, N., Rytting, C. M., Ye, A., Jiang, L., Lu, X., Dziri, N., Althoff, T., Choi, Y. (2024) A Roadmap to Pluralistic Alignment. In Forty-first International Conference on Machine Learning. https://arxiv.org/abs/2402.05070
Teaching
2025 » How to Make a Moral Agent @ Stanford
2022-2023 » The Philosophy of AI @ UW
2021-2022 » Introduction to Artificial Intelligence @ UW
2020-2023 » Computer Ethics @ UW
Creative
2023 » The Strength of the Illusion: a satirical novel about AI
2018 » Mother Mayfly: a mixed-media installation that produces ephemeral poetry
2017 » vuExposed: an installation on digital privacy at Vanderbilt University