Princeton and PPPL test PACMAN, an AI that controls fusion plasma in real time with ~20ms decisions
Dr_Singularity · x · 2026-09-12
Researchers at Princeton and PPPL successfully tested PACMAN, an AI framework for real-time control of fusion plasma.
- Makes control decisions in about 20 milliseconds, fast enough for live tokamak operation
- Goes beyond reactive control: it can predict and prevent instabilities before they occur
- A notable AI-for-Science result in fusion energy control
Related event: Princeton's PACMAN Controls Fusion Plasma in Real Time Within 20ms(3 posts)→
More from Research
- ParetoRSI-Gym benchmarks whether AI agents can recursively self-improve LLMs across domains — Haojin Wang · 2026-10-28
- Stanford's Ψ-0.6 is a unified vision-language world model with adaptive reasoning streams — Stanford · 2026-10-28
- Shanghai AI Lab's OpenESM shows energy-steered models can scale as foundation learners — Shanghai-AI-Laboratory · 2026-10-28
- CellTrack-Bench tests VLMs on microscopic cell tracking, exposing reasoning gaps — biohub · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- DeepMind researcher: all of mathematics will soon be formalizable, with agents hunting proofs — ChrSzegedy · 2026-10-28