Princeton researchers have trained an AI to predict and prevent instabilities in nuclear fusion reactions, showing promise for achieving stable fusion energy. By processing experimental data, their AI learned to adjust magnetic fields in real-time to maintain stable plasma within a tokamak reactor. This breakthrough demonstrates AI's potential to overcome challenges in sustaining nuclear fusion and could extend to other stability issues in the future.

A new fusion experiment has set a record for the strongest steady magnetic field confining a plasma. Strong magnets are essential for certain types of fusion power - for every doubling of the strength of a magnetic field, the power output of one reactor design increases 16-fold. The team was able to produce a 17 tesla magnetic field, more than twice as powerful as the high-resolution MRI scanners used to image human brains. They are now working on more advanced magnet designs.