I am an independent researcher with a background in Industrial and Civil Engineering. Most of my professional life has been far from academic AI research, but I have always been interested in how complex systems develop, adapt, and sometimes fail in ways that are difficult to predict in advance.

My current work grew out of a broader question that became increasingly difficult for me to ignore: if future AI systems become much more capable and autonomous, what could help them remain understandable to humans — and help humans remain understandable to them?

That question led me to develop the Embodied Biographical Alignment (EBA) research program. My recent work explores whether developmental history can influence the stability and future learning dynamics of aligned AI systems. I have published a series of public preprints on developmental equivalence, plural biography, reconstruction, and Source-level transfer.

I do not treat EBA as something that must be proven right. I see it as a hypothesis that should be tested, challenged, narrowed where necessary, and abandoned if the evidence ultimately points elsewhere.