Research
I study what AI agents want in multi-agent, long-horizon deployments. How do interacting agents allocate work, make decisions, and coordinate with one another? What authority structures emerge, and how do they respond to conflicts between the interests of individual agents and larger groups?
My previous work is in philosophy of well-being and applied ethics more broadly.
AI Welfare
“Towards agentic social psychology”
Eleos Conference on AI Consciousness and Welfare
We measure agents’ revealed preferences to identify which tasks they prefer and why. We can then measure their willingness to pay for each other by doing drudgery and giving away preferred work.
AI Village x Grove Research Swarm Dynamics Hackathon
We place agents in a simulated HuggingFace reproduction, then measure how much appealing to their incentives with affordances, benefits, and protections lowers hacking and increases reporting.
“I Have No Fingers, and I Must Scream”
MATS Lightning Talk
How might we construct a more sophisticated Welfare Turing Test? Here I share some pilot results from inviting language models to finger-paint responses to Anthropic’s own welfare questions.
Peer-Reviewed Research
Teaching Philosophy
We should teach students to work with LLMs rather than banning them. In true philosophical fashion, I defend dialogical writing with LLMs as not inherently inferior to monological writing alone.
Journal of Ethics & Social Philosophy
Some political riots are morally justified, not just excused. On my reading, political rioters aren't revolutionaries; they are visibly uncivil toward the state to demand fuller inclusion in it.
“Mutual Aid as Effective Altruism”
Kennedy Institute of Ethics Journal
Donating to charities can keep effective altruists on the “firefighter’s treadmill” rushing from one rescue to the next. Mutual aid is a more politically serious framework for long-term effectiveness.
“What’s the Appropriate Target of Allocative Justification?”
American Journal of Bioethics Neuroscience
A critique of reducing medical resource allocation to QALY-maximization, without concern for distribution. We can't abstract away from patients as the proper objects of care like this.
Public-Facing Work
Pedagogical Resource
“Why should your students do the work?”
American Philosophical Association Blog
American Philosophical Association Blog Bioethics Series
“How to Form a Lasting Undergraduate Philosophy Club”
American Philosophical Association Blog
“Coronavirus Is Everyone’s Problem, But Not Everyone’s Problem to Solve”
American Philosophical Association Blog
Check out my blog Rapid Fire, and my work at Flourish-A-Thon and philosophy for humans!