"Google DeepMind's AI Discovers Millions of New Materials, Now Faces the Challenge of Production"

Researchers at Lawrence Berkeley National Lab and UC Berkeley are using AI and robotic systems to create and test new materials for potential use in future battery designs. The AI program, GNoME, developed by Google DeepMind, generated designs for 2.2 million new crystals, of which 380,000 were predicted to be stable. The lab's autonomous system successfully created 41 of these materials, validating the AI model and the robotic techniques. The goal is to expand the range of known stable materials and discover new possibilities for solid-state electrolytes, solar cell materials, and high-temperature superconductors.