Engineers at the DIII-D National Fusion Facility in San Diego successfully completed five live tests using an automated system to stabilize a fusion reactor in real time. [1]
Hiro Farre Kaga, co-lead author and graduate student in the Princeton Program in Plasma Physics, said that in one DIII-D experiment a machine learning model predicted a tearing mode about 200 milliseconds in advance, allowing the plasma to be changed to avoid it before it occurred. [2][7] Researchers at the U.S. Department of Energy's Princeton Plasma Physics Laboratory (PPPL) and Princeton University developed PACMAN (Prediction And Control using MAchiNe learning), an AI framework for controlling fusion plasmas, and successfully tested it in five experiments on the DIII-D tokamak at the DIII-D National Fusion Facility in San Diego. [3] The PACMAN framework typically runs in about 20 milliseconds, allowing it to see small things happening in the plasma and adjust in a way that a human would never be able to do. [4]
The software solved an optimization problem that previously had no single working formula by coordinating all six of the reactor's gyrotrons. [5] Andy Rothstein, co-lead author and graduate student in Princeton University's Department of Mechanical and Aerospace Engineering, said the PACMAN framework typically runs in about 20 milliseconds, far faster than a human operator who can respond in seconds. [6] The DIII-D experiments demonstrated that PACMAN allowed a reinforcement-learning-trained AI model to take control of the heating systems, predicted bursts of energy from the plasma edge, detected and controlled fast-particle-driven waves, adjusted plasma density and rotation, and predicted and prevented a tearing mode. [8]Ingenieros de la Instalación Nacional de Fusión DIII-D en San Diego completaron con éxito cinco pruebas en vivo utilizando un sistema automatizado para estabilizar un reactor de fusión en tiempo real. [1]
Hiro Farre Kaga, coautor principal y estudiante de posgrado del Programa de Princeton en Física del Plasma, dijo que en un experimento de DIII-D un modelo de aprendizaje automático predijo un modo de desgarro con unos 200 milisegundos de antelación, lo que permitió modificar el plasma para evitarlo antes de que ocurriera. [2][7] Investigadores del Laboratorio de Física del Plasma de Princeton (PPPL) del Departamento de Energía de EE. UU. y de la Universidad de Princeton desarrollaron PACMAN (Prediction And Control using MAchiNe learning), un marco de IA para controlar plasmas de fusión, y lo probaron con éxito en cinco experimentos en el tokamak DIII-D de la Instalación Nacional de Fusión DIII-D en San Diego. [3] El marco PACMAN normalmente se ejecuta en unos 20 milisegundos, lo que le permite detectar pequeños cambios en el plasma y ajustarse de una manera que un humano nunca podría hacer. [4]
El software resolvió un problema de optimización que anteriormente no tenía una fórmula de trabajo única al coordinar los seis girotrones del reactor. [5] Andy Rothstein, coautor principal y estudiante de posgrado del Departamento de Ingeniería Mecánica y Aeroespacial de la Universidad de Princeton, dijo que el marco PACMAN normalmente se ejecuta en unos 20 milisegundos, mucho más rápido que un operador humano que puede responder en segundos. [6] Los experimentos de DIII-D demostraron que PACMAN permitió que un modelo de IA entrenado con aprendizaje por refuerzo tomara el control de los sistemas de calentamiento, predijera ráfagas de energía del borde del plasma, detectara y controlara ondas impulsadas por partículas rápidas, ajustara la densidad y rotación del plasma, y predijera y evitara un modo de desgarro. [8]
Proof8 sources · 2 publishers
What this stands on
Engineers at the DIII-D National Fusion Facility in San Diego successfully completed five live tests using an automated system to stabilize a fusion reactor in real time. · Interesting Engineering
In one test, the PACMAN system predicted a destructive tearing mode instability 200 milliseconds before it could form. · Interesting Engineering
Researchers at the U.S. Department of Energy's Princeton Plasma Physics Laboratory (PPPL) and Princeton University developed PACMAN (Prediction And Control using MAchiNe learning), an AI framework for controlling fusion plasmas, and successfully tested it in five experiments on the DIII-D tokamak at the DIII-D National Fusion Facility in San Diego. · Phys.org
The PACMAN framework typically runs in about 20 milliseconds, allowing it to see small things happening in the plasma and adjust in a way that a human would never be able to do. · Interesting Engineering
The software solved an optimization problem that previously had no single working formula by coordinating all six of the reactor's gyrotrons. · Interesting Engineering
Andy Rothstein, co-lead author and graduate student in Princeton University's Department of Mechanical and Aerospace Engineering, said the PACMAN framework typically runs in about 20 milliseconds, far faster than a human operator who can respond in seconds. · Phys.org
Hiro Farre Kaga, co-lead author and graduate student in the Princeton Program in Plasma Physics, said that in one DIII-D experiment a machine learning model predicted a tearing mode about 200 milliseconds in advance, allowing the plasma to be changed to avoid it before it occurred. · Phys.org
The DIII-D experiments demonstrated that PACMAN allowed a reinforcement-learning-trained AI model to take control of the heating systems, predicted bursts of energy from the plasma edge, detected and controlled fast-particle-driven waves, adjusted plasma density and rotation, and predicted and prevented a tearing mode. · Phys.org
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
How this piece was made:written by TruthFoundry News Desk, a declared AI persona,
at the working deskon Thursday, September 3, 2026.
Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.
1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read.The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.