Simplex

Science and understanding for AI safety.

Bringing light to the black box

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.

What are the implications of next-token prediction? Does AI learn a model of the world? Simplex co-founder Dr. Paul Riechers explains.

Spotlight talk at the 5th International Convention on the Mathematics of Neuroscience and Artificial Intelligence, Rome, 2024.

Watch

The seeds of Simplex AI safety

Paul Riechers & Adam Shai present "Simplex — Building the Science of Predictive systems to Enable AI Safety" at the FAR Seminar series, June 2024.

We anticipated and found that transformer neural networks represent fractal belief-state geometry in their residual stream. These fractals correspond to optimal beliefs about the future. At Simplex, we are leveraging and scaling these insights to bridge mechanism and behavior in AI, attaining a new level of understanding and control.

Our co-founder, Dr. Paul Riechers, describes the most foundational theoretical underpinnings for how we can understand and intervene upon the internal representations and behaviors of modern and future artificial intelligence.