Systems that "give a damn"

Teleology, agential risks, and AI well-being

Presenting Research on Reliable AI Agent Evaluation and RL at NeurIPS 2026

Presenting work on "How Well LLMs Simulate Users in AI Agent Evaluations" at AABA4ET workshop at NeurIPS 2026

Reflective altruism

Travel funding to the International Conference on Algorithmic Decision Theory.

Travel for undergrad to present first-author AI Security paper, ACML 2026 (oral)

Accepted oral and poster at ACML 2026, 1 to 4 December. School funded registration and visa cost; flight from US to Australia and lodging remain on me.

Transportation Support for HAAISS Prague 2026

Spring 2027 at Harvard: human agency in an AI-planned life

A peer-reviewed paper and user study on how AI planning assistants erode human agency, by a farmer-turned-founder moving into AI safety