Princeton Plasma Physics Laboratory

Mm-hmm.

Getting into the story, scientists at Princeton University and the US Department of Energy's Princeton Plasma Physics Laboratory, you can bet that's a house full of geeks, have developed an artificial intelligence system that can control the extremely hot plasma inside a nuclear fusion reactor faster than humans can respond.

The system called, I think this is hilarious, PACMAN, Prediction and Control Using Machine Learning, [laughs] was tested on the DIII-D tokamak fusion facility in San Diego.

The tokamak, Mac, I hope I'm saying that right, uses powerful magnetic fields to contain plasma heated to temperatures hotter than the center of the Sun.

The governor's announcement is linked in the description.

Open Star and PPPL sign a research agreement.

FII member Open Star Technologies and PPPL have signed a memorandum of understanding covering scientific and educational cooperation on levitated dipole fusion.

That's the approach where a superconducting ring floats inside the vacuum chamber and its magnetic field confines the plasma.

This partnership brings PPPL research expertise together with OpenSTAR's development program.

PPPL explores a heat-first route to fusion ignition.

PPPL researchers have proposed a way to reach fusion ignition using less external heating.

What this means in practice is heating the plasma first and then adding more fuel to raise its density.

In today's head flash, AI takes control of Fusion Plasma, personal AI agents hit website blocks, Wikimedia says OpenAI agents edited Wikis, a new cross-domain world model, and Google's compact multimodal embedding model.

Researchers at the U.S. Department of Energy's Princeton Plasma Physics Laboratory and Princeton University built a machine learning framework that controls fusion plasma on millisecond timescales, far faster than a human operator's seconds-long reaction.

Published in Nuclear Fusion, it runs a repeating control loop in about 20 milliseconds, reading live tokamak measurements and letting AI models estimate plasma behavior before controllers act.

across five experiments at a national fusion facility in San Diego.

So I think the private, so General Atomics is certainly like kind of the leader in plasma diagnostics.

They've served various like large scale public devices like ITER, like NSTX at the Princeton Plasma Physics Lab.

Sort of what I see is that the private industry needs something different, that they need a measurement partner that can deliver diagnostics on a business model that works for them, deliver that service, guarantee that that line item of measurement can be completely outsourced to a capable company delivering on their timelines.

And so I think what motivates people to work for a company like Datal is that it...