IBM has unveiled a prototype chip with 100 billion transistors packed into a fingernail-sized area—double the density of its 2021 state-of-the-art design. The achievement could extend Moore's Law by roughly a decade and enable faster, more energy-efficient computing across multiple applications.
Why it matters: This breakthrough directly impacts the trajectory of AI hardware capabilities and power efficiency, two critical factors determining the viability and cost of next-generation machine learning systems.