← Back to people
Portrait of Federico Torrielli

Person

Federico Torrielli

Guest Researcher, PhD Fellow · University of Turin, Italy (UniTO)

AI Safety Mechanistic Interpretability Human-AI Interaction

I work primarily on AI safety. My main research interests include AI alignment, human-GenAI interaction, and mechanistic interpretability. My goal is to understand how humans can collaborate effectively with AI systems, which requires first understanding how those systems actually work.