Alejandro De Los Angeles

My research interests lie at the intersection of AI safety, psychiatry, and clinical medicine. I am interested in developing methods to detect and mitigate pathological behaviors that emerge in AI systems, including forms of "AI psychosis" characterized by unstable, delusion-like, or clinically unsafe reasoning. More broadly, I study how agentic AI systems can be monitored, governed, and aligned to ensure safe deployment in healthcare.

Projects

No grants recorded.