A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) demonstrates that large language models (LLMs) can significantly accelerate the process of robot design and simulation. The research shows that LLMs can generate viable robot body plans and control systems for specific tasks, such as walking across a flat surface, by iterating through design proposals and simulations. This approach, which leverages the models’ ability to process vast amounts of text and code, automates a traditionally time-consuming and manual process. The work highlights the potential for AI to act as a co-pilot in the creative and engineering phases of robotics, though human oversight remains crucial for final validation and practical implementation. Read the full article: https://technologyreview.com/2024/10/15/robots-llm-design/