The Neuron: AI Explained AI Is Helping Build the Power Source It Desperately Needs (Brandon Sorbom w/ Commonwealth Fusion Systems)
7 snips
Mar 3, 2026 Brandon Sorbom, co-founder and Chief Science Officer at Commonwealth Fusion Systems, builds fusion power with high-temperature superconducting magnets. He explains tokamak design, why HTS magnets changed the game, and how AI speeds plasma control and digital-twin simulations. Manufacturing scale-up, real-time control with reinforcement learning, and timelines for Q > 1 are also explored.
AI Snips
Chapters
Transcript
Episode notes
Triple Product Explains Fusion's Long Timeline
- Fusion progress tracked by the triple product (temperature × density × confinement time) and historically advanced steadily but needed a threshold to become a product.
- Sorbom compares the triple product progress to Moore's Law and explains why reaching net energy requires crossing that threshold.
Prove Production Before You Scale A Machine
- Validate manufacturing at scale, not just one-off prototypes, to turn lab success into a buildable product.
- Sorbom says installing the first Spark magnet proved production risk retired and enabled an assembly-line approach for 18 magnets.
Why Fusion Is Inherently Safer Than Fission
- Fusion is fundamentally different and safer than fission because it is 'default off' — the plasma cools and extinguishes if confinement fails.
- Sorbom contrasts fission chain reactions with fusion's temperature-controlled process that stops almost instantly if plasma touches the wall.