In this course, you learned about energy and the electric grid as they relate to computing infrastructure and carbon emissions. You learn how model training inference, especially when it comes to LLM can have a significant carbon footprint. But you also got familiar with key factors and decisions that impact how large or small this footprint is. And you got to try out one strategy for carbon aware and ML development, training models and locations that are powered by a high amount of carbon-free energy. I think it's really exciting that you can make a positive difference on the environment as a developer, and that by making changes and how you code and design and ML applications, you can tangibly impact your environmental footprint. One example, if you're looking for a place to start contributing now, the Electricity Maps app is actually open-source, and there's even a process for adding a new regional grid if you noticed that your location was missing. I hope this is just the beginning of your carbon-aware journey. There's so much more to explore in the space and increasingly illuminating research and I can't wait to see what carbon-aware applications you build next.