Now

Current focus

• AI alignment, especially character training, constitutions, and value drift in post-training.
• AI evaluations for hard-to-check tasks, especially where appearance and actual quality diverge.
• AI agents, including misalignment, oversight, and reliability in long-horizon tool-use settings.
• Robustness and generalization under pressure, distribution shift, and prior RL incentives.
• Programmable biology, especially the bridge from digital design to physical validation.

Living note

I recently updated Open Problems I Am Exploring: Reliable AI in Hard-to-Check, High-Impact Domains, a working note on safe, trustworthy, and verifiable AI across agent alignment, high-stakes deployment in education and health, and constrained systems generation.

Collaboration interest

I am especially interested in meeting people working on AI safety, model evaluation, tool use, generalization, and programmable biology, as well as programs and communities that support independent research.