Energy startup Commonwealth Fusion Systems said Thursday it is working with Google’s DeepMind division to refine — and even improve — the operation of its upcoming Sparc reactor using AI.
The company’s design will simulate the plasma that will burn inside the CFS reactor using specialized DeepMind software known as Torax. They also plan to combine Torax with artificial intelligence models to help CFS figure out the best way to achieve fusion power.
Fusion power promises to deliver vast amounts of zero-emissions electricity from an almost limitless fuel source: water. AI-related companies have been bullish on fusion startups as a source of electricity to power power-hungry data centers. Google seems to be looking at them as potential customers as well.
This isn’t Google’s first foray into nuclear fusion. The tech company partnered with another fusion startup, TAE Technologies, to use artificial intelligence to study how plasma behaves inside TAE’s fusion machine.
There’s a reason Google is returning to the problem: AI may be uniquely suited to make power fusion possible.
One of the biggest challenges facing fusion startups is keeping the plasma inside a reactor hot enough for long enough. Unlike nuclear fission reactions, which are self-sustaining, fusion reactions are difficult to sustain outside of stars like the Sun. Without this kind of mass and gravity, the creature is constantly in danger of dispersing and disappearing.
In CFS reactors, powerful magnets replace gravity to help split the plasma, but they’re not perfect. Reactor operators must develop control software that can allow the device to continuously react to changing plasma conditions.
Techcrunch event
San Francisco
|
27-29 October 2025
The problem is that there are almost too many knobs to turn, certainly more than one human can handle. This is the kind of problem that AI excels at. Experts have cited artificial intelligence as one of the key technologies that have enabled the industry’s remarkable progress over the past several years.
CFS is currently building Sparc, its demonstration reactor, in a suburb outside of Boston. The device is about two-thirds complete, and when completed later in 2026, the startup predicts it will be the first fusion device capable of generating more power than the plant needs to run on its own.
Google said Torax can be used with reinforcement learning or evolutionary search models to find the “most efficient and robust pathways to clean energy production.” The two companies are also investigating whether artificial intelligence can be used to control reactor operation.
In August, Google participated in the $863 million CFS Series B2 round alongside Nvidia. Earlier this year, Google also said it would buy 200 megawatts of electricity from CFS’s first commercial power plant, Arc, which is planned to be built outside Richmond, Virginia. The technology company is also an investor in competitor CFS TAE Technologies.
