About us
Simplex brings the best of both physics and computational neuroscience together to bridge mechanism and behavior —— in service of understanding and taming artificial general intelligence (AGI).
We are a small team of world-class researchers and engineers bringing scientific rigor to enable a brighter future.
Our Leadership
Paul Riechers, PhD co-founder
Paul Riechers has extensive research and leadership experience in the physics of information and computational mechanics, with expertise in the ultimate limits of learning and prediction. He holds a PhD in theoretical physics and an MS in electrical and computer engineering from UC Davis. He co-founded the Beyond Institute for Theoretical Science (BITS), and now works to make AI understandable and safe.
Adam Shai, PhD co-founder
Adam Shai has extensive research experience in experimental and computational neuroscience. He earned his PhD from Caltech and has over a decade of experience investigating the neural basis of intelligent behavior, most recently as a researcher at Stanford. Driven by the pressing need for AI safety, he has now turned his expertise to neural networks, aiming to develop principled methods for controlling and aligning increasingly advanced AI systems.
Strong foundations + cutting edge insights
Our work at Simplex builds on decades of foundational research, together with recent breakthroughs in the science of learning, prediction, and deep neural networks. This brings us to the cutting edge of understanding the cognition of artificial intelligence. Our scientific approach allows us to benchmark common AI safety techniques (like sparse autoencoders), while building the capacity to anticipate, detect, and intervene on unwanted behaviors that may emerge in future artificial intelligences.
The metadynamics of prediction
Benchmarking predictive accuracy in neural networks
The ultimate limit of learning