I’m guessing you’ve heard of ChatGPT. If you haven’t, you probably don’t go to ESCP, or have been living under a rock for the past couple of weeks, even months.
ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. Just a week after launch, it already had over 1 million users. In January, ChatGPT saw its fastest growth yet, amassing 100 million active users in just about two months.
But have you considered the chatbot’s environmental impact? Probably not. Let’s discover it together.
Let’s start with its carbon footprint. As a machine learning (ML) model, the total life cycle carbon footprint starts from the training process to its use once deployed. As ML models require significant amounts of computing power, they use a great deal of energy.
Using estimations and mathematical calculations, Towards Data Science published a “guesstimate” of the CO2 emissions caused by ChatGPT, taking into consideration the amount of electricity it consumes and the carbon intensity of this electricity. Using the ML C02 Impact calculator, they estimated ChatGPT’s daily carbon footprint to be 23.04 kgC02e, which is 20x what an average human exhales in an average day and 3x what a typical t-shirt emits during its production and sale.
Beyond carbon footprint, electronic waste should also be taken into consideration when considering ChatGPT’s environmental impact. ML development necessitates significant IT infrastructure and hardware—this type of waste can be difficult to recycle.
What does ChatGPT believe about its own impact on the planet? We asked “What is your environmental impact?” and this was its answer:
“As an AI language model, I don't have a direct environmental impact because I don't have a physical presence. However, the hardware and servers that are used to power and host me can have an environmental impact in terms of energy consumption and carbon emissions.
The exact environmental impact of AI language models like myself depends on several factors, including the size and complexity of the model, the number of users accessing it, and the data centers and infrastructure used to host it. However, many companies and organizations that develop and use AI language models are taking steps to reduce their carbon footprint by using renewable energy sources, optimizing their data center operations, and implementing more energy-efficient hardware and software.
Overall, while there is certainly room for improvement in terms of the environmental impact of AI, it's important to recognize that AI technologies also have the potential to help address some of the world's most pressing environmental challenges, such as climate change, biodiversity loss, and resource depletion.”
While the technology’s energy use and carbon footprint are unavoidable, it’s true that AI could play an important role in reducing the environmental impact of businesses and our individual lives. Interested in calculating your own carbon footprint? Check out carbonfootprint.com.
Olivia Gumbel
Comments