Ryan is a researcher in the field of AI alignment. He analyzes how we could design an AI system to operate safely, in the case where it is highly capable but only partially understands human values. He finished working at the Machine Intelligence institute the day before EA global started, and is now starting a research internship at the Future of Humanity Institute in Oxford. He is a research affiliate at the Centre for Study of Existential Risk, founded the EA Forum and cofounded EA Melbourne. Prior to working on AI alignment, he studied bioinformatics, and worked as a medical resident.
- Research Intern
- Company: Ought Inc