We are building AI to discover the rules governing the physical world, from the movements of a single molecule to the operation of complex machinery and the behaviour of entire planetary systems. Our ambition is for it to uncover physics that humans have not yet discovered.
Every experiment, every observation and every simulation captures something about how the universe works. We believe AI can learn from this growing record to uncover relationships that have remained beyond our reach, and use each discovery to make the next one possible.
We call this approach Spectral Intelligence. It is the foundation of our ultimate goal, the Universal Spectral Model: AI that learns the structure of change, recognizing the principles shared in the physical world and using that knowledge to understand systems it has never encountered - from those familiar to humanity, to those beyond the boundaries of current knowledge.
This model will discover increasingly general principles from its experience, so what it learns about one system could unlock an understanding of another, connecting areas of science and engineering that we study separately today.
This would give us a new means of scientific discovery: AI that can uncover new physical laws and help us turn that understanding into technologies we do not yet know how to build.