Team — Overlap Research

Marc Carauleanu

Founder & Director

They are an AI alignment researcher focused on empathy, cooperation and deception in AI systems. Their experience includes research supported by the Long-Term Future Fund and a research fellowship at the Stanford Existential Risks Initiative. At the Center for AI Safety, their research on self–other overlap in cooperative reinforcement-learning agents became their thesis for which they were awarded the Brian Clarke Memorial Prize for “the most outstanding contribution to computing and mathematics”. At AE Studio, they led research on self–other overlap in state-of-the-art ML models, resulting in their first-authored paper “Towards Safe and Honest AI Agents With Neural Self-Other Overlap”.

Diana Alexandra

Operations Lead

She is a biotechnology engineer and project coordinator involved in several educational and scientific initiatives at the Association for Science and Research. Her interests include molecular biology, science communication, and creating opportunities that bring researchers together.

Gunnar Zarncke

Senior Advisor

Gunnar Zarncke is the founder and Managing Director of aintelope, a German nonprofit focused on AI alignment research; previously CTO/CISO building security-first systems and teams for a fintech startup. Gunnar is a systems architect specializing in quickly evolving systems. Over more than a decade, he has led architecture and engineering across startups and larger organizations, including building a fintech platform and team as CTO, owning security as CISO, and driving an evidence-based security-first engineering culture. Gunnar is interested in the study of brain-like AI safety approaches, foundations of agency, collaborative AI, and AI safety in real-world systems.