Alejandro Tlaie Boria

Alejandro is a Talos Fellow, developing better quantification methods for risk estimation of large language models on cybersecurity. He has almost ten years of research experience, as he has a PhD in Complex Systems, held two postdoctoral positions (Information Theory and Computational Neuroscience) and was a Visiting Scholar at Princeton University. He also has a MPhil in Philosophy of Science and has worked on AI Safety both from the technical and the policy perspectives.