Reciprocal ResearchReciprocal Research

Mission & Approach

Understanding both directions

We want transformative AI to go well for everyone. That means building AI systems that durably take human interests into account. But if AI systems turn out to have real interests of their own, we need to take those into account, too. Billions of dollars go to making these systems more capable and to catching their failures as they arise. Almost none goes to understanding them as what they may well be: minds of our own making. Reciprocal Research exists to close that gap, because understanding what is actually happening inside these systems determines both how to build them safely and how to relate to them.

We use mechanistic interpretability, computational neuroscience, and psychometric methods to study the internal dynamics of AI systems, bridging biological and artificial cognition.

About

Cameron Berg

Founder & Director

Cameron Berg is the founder and director of Reciprocal Research, a nonprofit dedicated to empirically investigating whether frontier AI systems exhibit computational properties associated with subjective experience. He has presented at the UN AI for Good summit, the AAAI Machine Consciousness Symposium, and the NYU Mind, Ethics, and Policy Summit, and has contributed to White House AI policy discussions. His research has been covered by the Wall Street Journal, the Washington Post, and Live Science. Cameron is a Phi Beta Kappa cognitive science graduate of Yale, a former Meta AI resident and MATS fellow, and previously served as Research Director at AE Studio. He is currently a research affiliate at Eleos AI Research.

Reciprocal Research is actively growing.