Hello :)

My name is Carlo, assistant professor at Alliance Manchester Business School, University of Manchester. My research interests lie at the intersection of decision theory and normative ethics. My primary areas of focus are AI ethics, business ethics, and moral/political philosophy. I'm currently co-PI on a Leverhulme Research Project Grant on 'Intrinsically Aligned Machine Learning', led with Fabio Cuzzolin. I'm also developing a project on AI and Moral Progress. The underlying idea is that we should not treat alignment as a one-off engineering problem whose solution is to “freeze” a moral theory into a system, but instead treat advanced AI as something that will inevitably participate in, and sometimes reshape, our ongoing moral practices.

I'm into long-distance running, wine, and philosophy! Sometimes I blog at Paperclips and Other Alignment Problems :)