A new study published in Nature reveals that researchers have successfully demonstrated a significant improvement in the energy efficiency of a key AI computing process. The team developed a novel photonic chip that uses light instead of electricity to perform matrix multiplications, a fundamental operation in neural networks. This approach reportedly reduced the energy consumption of these calculations by over a thousand times compared to current state-of-the-art electronic chips. The breakthrough could pave the way for more powerful and sustainable AI systems, particularly for large-scale data centers. However, the technology is currently at a laboratory prototype stage and faces challenges in scaling up for commercial production. For the full details, read the complete article at https://technologyreview.com/2024/05/15/photonic-chip-ai-efficiency.