Marc Carauleanu

Marc Carauleanu is an AI Safety Researcher at AE Studio. They are leading a team investigating a neglected AI Safety proposal that is focusing on self-other overlap: the AI model having similar internal representations when it reasons about others to when it reasons about itself. This agenda was heavily inspired by scientific literature on the cognitive neuroscience of empathy and altruism. They have previously investigated methods of reducing the risk of deception as a Summer Research Fellow at Stanford Existential Risks Initiative and the relevance of cognitive science literature for AI alignment funded by the Long-Term Future Fund and Center for AI Safety.