Thermodynamic Computing: From Zero to One | Extropic

October 29th, 2025<br>Announcement

Thermodynamic Computing From Zero to One

Three years ago, Extropic made the bet that energy would become the limiting factor for AI scaling.<br>We were right.[0]<br>Scaling AI will require a major breakthrough in either energy production, or the energy efficiency of AI hardware and algorithms.<br>We are proud to unveil our breakthrough AI algorithms and hardware, which can run generative AI workloads using radically less energy than deep learning algorithms running on GPUs.<br>We designed the world’s first scalable probabilistic computer.<br>We fabricated probabilistic circuits that perform sampling tasks using orders of magnitude less energy than the current state of the art.<br>We developed a new generative AI algorithm for our hardware that can use orders of magnitude less energy than existing algorithms.[0]

To explain our work, we are releasing:<br>A hardware proof of technology, the XTR-0 development platform, already beta-tested by some of our early partners<br>A post on this website and an academic paper describing our novel hardware (the Thermodynamic Sampling Unit) and our new generative AI algorithm (the Denoising Thermodynamic Model)<br>thrml, our Python library for simulating our hardware, which can be used to develop thermodynamic machine learning algorithms<br>With the fundamental science done, we are moving from breakthrough to buildout.<br>Once we succeed, energy constraints will no longer limit AI scaling.<br>Scaling The AI Energy Wall<br>Like other AI companies, we envision a future where AI is abundant. We believe AI is a fundamental driver of civilizational progress, thus scaling AI is of paramount importance. We imagine a future where AI helps humanity discover new drugs to cure disease, predicts the weather better to mitigate the impact of natural disasters, improves automation of manufacturing, drives our cars, and augments human cognition in a democratized fashion. We hope to bring that future to reality.<br>However, that future is completely out of reach with today’s technology. Already, almost every single new data center is experiencing difficulties sourcing power[0]. With today’s technology, serving advanced models to everyone all the time would consume vastly more energy than humanity can produce. To provide more AI per person, we will need to produce more energy per person, or get more AI per Joule.

Continuing to scale using existing AI systems will require vast amounts of energy. Many companies are working on better ways to produce that energy, but that is only half of the equation.<br>Extropic is working on the other half of the equation: making computing more efficient. Scaling up energy production requires the support of a nation-state, but a more efficient computer can be built by a dozen people in a garage outside Boston.<br>Extropic is Rethinking Computing<br>If we constrain ourselves to the computer architectures that are popular today, reducing energy consumption will be very hard. Most of the energy budget in a CPU or GPU goes towards communication, because moving bits of information around a chip requires charging up wires. The cost of this communication can be reduced by either reducing the capacitance of the wires or reducing the voltage level used for signalling. Neither of these quantities has gotten significantly smaller over the last decade, and we don’t think they will get smaller in the next decade either.<br>Fortunately, we don’t need to limit ourselves to today’s computer architectures. Today’s AI algorithms were designed to run well on GPUs because GPUs were already popular, but GPUs only became popular because they were good at rendering graphics. GPUs can do amazing things, but today’s machine learning paradigm is the result of evolution, not design.<br>Progress in deep learning research fuels progress in GPU design, and vice-versa.

The current machine learning paradigm has a lot of momentum. Without a major shift in computing demand, there’s no reason to throw away decades of optimizations to start over from scratch.<br>But recently, computational demands have shifted from deterministic to probabilistic, and from performance-constrained to energy-constrained.<br>To meet those demands, Extropic has developed a new type of computing hardware for the probabilistic, energy-efficient, AI-powered future.<br>The Thermodynamic Sampling Unit<br>We have developed a new type of computing hardware, the thermodynamic sampling unit (TSU).<br>We call our new hardware a sampling unit, not a processing unit, because TSUs perform an entirely different type of operation than CPUs and GPUs. Instead of processing a series of programmable deterministic computations, TSUs produce samples from a programmable distribution.<br>Running a generative AI algorithm fundamentally comes down to sampling from some complicated probability distribution. Modern AI systems do a lot of matrix multiplication to produce a vector of probabilities, and then sample from that. Our...