A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) demonstrates a significant advancement in making AI systems more energy-efficient. The research focuses on reducing the computational power required for large language models (LLMs) during the inference phase, which is when the trained model generates responses. By implementing a novel method that selectively activates only the necessary parts of the neural network for a given query, the team achieved a dramatic reduction in energy consumption—up to 80%—with minimal impact on the model’s accuracy or performance. This breakthrough addresses a major concern in the widespread deployment of AI, as the energy demands of running powerful models contribute to high operational costs and environmental impact. The technique could make advanced AI more accessible and sustainable for a wider range of applications. Read the full article at: https://technologyreview.com/2024/05/15/energy-efficient-ai-breakthrough-mit