If we’re going to co-exist with our technology overlords, we ought to know them a bit better.
Case in point: ChatGPT, the scary-smart artificial intelligence engine capable of answering a breathtakingly broad array of questions, which seems to be the tech world’s bright, shiny object of 2023.
If you haven’t yet tuned in, ChatGPT is a natural language learning engine that can imitate human conversation, remember things you have said to it in the past (better than a lot of humans I know) and correct itself when wrong (ditto). It answers questions in a human-like way, pulling from myriad sources across the digital universe as well as from books, academic journals and who-knows-what-else.
ChatGPT and its scions are here to stay. And, to paraphrase Stewart Brand, we might as well get good at it.
Over the past 60 days — ChatGPT was launched only on Nov. 30 — it has become a source of fascination (and a fun way to burn an hour or two). And it’s generated more than a little concern about the role of AI in our lives, in areas as disparate as education (ChatGPT can essentially write yeoman-quality essays based on a single query), cybersecurity (it can easily write phishing emails and malicious code) and healthcare (it could eventually replace mental health professionals without regard to qualifications or effectiveness).
And it’s just getting started. Because AI programs such as ChatGPT can learn over time, they are literally in their infancy. Think: the internet circa 1996.
So, ChatGPT and its scions are here to stay. And, to paraphrase Stewart Brand, we might as well get good at it.
In that spirit, I recently sat down (well, at least one of us was sitting) with ChatGPT to discuss climate tech and corporate sustainability. I wanted to see how much it knew and how well it could contextualize the broad and complex range of technologies under the climate tech umbrella — everything from clean energy to water treatment to e-bikes to carbon capture — and what it understood about corporate sustainability in general.
The interview has been edited for length, primarily because ChatGPT can be rather verbose. (Any trimming was done of entire paragraphs; the conversation is otherwise 100 percent verbatim.) And, as you’ll see, ChatGPT seems to really, really like five-part numbered lists.
Joel Makower: Let’s start with the basics: Is AI a climate technology?
ChatGPT: Artificial Intelligence can be considered as a climate technology in some cases, but it is not inherently a climate technology. AI can be used to support and enhance various climate technologies and solutions, such as renewable energy, carbon capture and climate modeling. However, AI can also contribute to the problem of climate change if it is used to power resource-intensive activities, or to support unsustainable practices.
Makower: Great. So, how can AI help corporate sustainability professionals be more effective?
ChatGPT: AI can help corporate sustainability professionals in various ways:
- Data analysis: AI can help process and analyze large amounts of data, including energy consumption and emissions data, to identify areas for improvement and track progress towards sustainability goals.
- Supply chain management: AI can be used to monitor the sustainability performance of suppliers and identify opportunities for improvement.
- Predictive maintenance: AI can be used to predict when equipment will fail, reducing unplanned downtime and reducing energy consumption and emissions.
- Energy management: AI can be used to optimize energy use in buildings and industrial processes, reducing energy consumption and associated emissions.
- Carbon footprint calculation: AI can help automate the calculation of an organization’s carbon footprint, making it easier to track progress towards reducing emissions.
Makower: How about the circular economy? Does AI have a role in accelerating circularity?
ChatGPT: AI has the potential to accelerate the transition to a circular economy by:
- Optimizing waste management: AI can help optimize waste collection, sorting and recycling processes to reduce waste and increase resource efficiency.
- Predictive maintenance: AI can help extend the life of products and reduce the need for replacement, thus reducing the production of waste and supporting a circular economy.
- Supply chain optimization: AI can help companies optimize their supply chains to reduce waste, improve resource efficiency and reduce their carbon footprint.
- Product design: AI can help in the design of more sustainable products that can be reused, repaired, refurbished or recycled more easily.
- Predictive analytics: AI can help companies to anticipate demand, reduce overproduction and minimize waste, leading to a more efficient and circular economy.
Makower: There’s been a lot of attention paid to ESG and sustainable finance. What can AI do to help those areas?
ChatGPT: AI can play a significant role in environmental, social and governance (ESG) and sustainable finance by:
- ESG data analysis: AI can help analyze vast amounts of ESG data to support investment decisions and identify sustainable investment opportunities.
- Risk management: AI can help investors identify and manage ESG risks, such as exposure to carbon emissions, water scarcity and human rights violations.
- Impact investing: AI can help investors identify and evaluate investment opportunities that deliver both financial returns and positive environmental and social impact.
- Compliance: AI can assist financial institutions in ensuring compliance with sustainable finance regulations and guidelines, such as the Paris Agreement on climate change.
- Transparency: AI can help increase transparency in the investment process, providing investors with a more complete picture of the ESG performance of companies and projects.
While some hype around AI as a solution to the climate crisis is understandable given its potential, it’s also important to be realistic about its limitations.
Makower: What should professionals watch out for when using AI as a sustainability tool?
ChatGPT: Professionals should watch out for the following:
- Bias: AI algorithms can perpetuate existing biases and lead to unfair outcomes, especially if the training data is biased. It is important to ensure that the AI models used are transparent, interpretable and free of bias.
- Resource consumption: AI algorithms can be resource-intensive, requiring large amounts of energy and computational power. It is important to consider the environmental impact of AI and to use sustainable computing resources where possible.
- Lack of interpretability: Some AI models can be complex and difficult to interpret, making it challenging to understand the basis for their decisions and outputs. This can limit their utility as sustainability tools.
- Data quality: The quality and accuracy of the data used to train AI models is critical. Poor quality data can lead to inaccurate results and incorrect decisions.
- Ethical considerations: AI can have significant ethical implications, particularly in areas such as privacy and decision-making. It is important to consider the ethical implications of using AI as a sustainability tool and to ensure that it is used in a responsible and transparent manner.
Makower: Is AI being overhyped as a solution to the climate crisis?
ChatGPT: While some hype around AI as a solution to the climate crisis is understandable given its potential, it’s also important to be realistic about its limitations and to avoid overhyping its potential. AI is not a silver bullet that can solve the climate crisis by itself, and its impact will depend on how it’s integrated with other solutions and technologies, as well as on broader policy, regulatory and market developments.
Makower: What do you recommend to sustainability professionals to become more comfortable with AI?
ChatGPT: I would recommend the following steps:
- Learn the basics: Start by gaining a good understanding of AI, its potential applications and its limitations. Attend workshops, webinars or take online courses to learn about the basics of AI.
- Network with experts: Connect with experts in the field of AI and sustainability, and learn from their experiences and insights. Attend industry events, and join online communities to expand your network.
- Explore case studies: Study real-life case studies of companies that have successfully implemented AI for sustainability purposes. This will give you a better understanding of the potential benefits and challenges of AI deployment.
- Get hands-on experience: Try working with AI tools and systems to gain hands-on experience. This can be done through internships, projects or side-hustles.
- Collaborate with others: Collaborate with experts in AI and sustainability to co-create solutions that can help companies meet their sustainability goals.
In conclusion, becoming more comfortable with AI requires a combination of learning, practical experience and collaboration with others.
Makower: Will the rise of climate tech have any unintended consequences on the environment or society?
ChatGPT: While climate tech has the potential to bring about positive change, it is important to carefully consider and mitigate any potential negative impacts. For example, the production and use of some clean energy technologies, such as solar panels and wind turbines, can result in the extraction and use of materials that can have negative impacts on the environment, such as the depletion of rare earth metals and increased energy demand. Similarly, the displacement of traditional energy sources such as coal and oil can have economic and social impacts, particularly for communities that have been reliant on these industries for employment and economic stability.
To minimize the potential unintended consequences of the rise of climate tech, it is important to adopt a responsible and integrated approach that takes into account the full life cycle of technology and its potential impacts on the environment, society and economy. This includes considering the environmental impact of manufacturing, deployment and disposal, as well as the social and economic impacts on affected communities.
Makower: We’re in a challenging economic moment. Is climate tech recession-proof?
ChatGPT: Climate tech is a relatively new and growing industry, and as with any industry, it is subject to fluctuations in the economy and market demand. While some aspects of the industry, such as renewable energy and energy efficiency, may be relatively resilient to economic downturns, it is not entirely recession-proof.
For example, during the global economic recession of 2008, the renewable energy sector experienced a slowdown in investment and growth. However, it recovered relatively quickly and has continued to grow in recent years, as governments and companies prioritize investments in clean energy to address the global climate crisis.
Ultimately, the resilience of the climate technology industry to economic recessions will depend on various factors, including government policies, consumer demand and technological advancements.
Makower: Any final advice to corporate sustainability professionals about using AI effectively?
ChatGPT: Here are some final pieces of advice:
- Start small: AI can be complex and challenging, so it’s often best to start with a small pilot project to gain experience and build internal expertise.
- Collaborate with experts: AI can be difficult to implement and understand, so it’s important to work with experts who have experience in the field.
- Consider the data: AI is only as good as the data it’s trained on, so it’s important to ensure that the data used is of high quality and relevant to the sustainability challenges being addressed.
- Prioritize transparency: AI algorithms can be complex and difficult to understand, so it’s important to ensure that they are transparent and that their decision-making processes can be easily explained.
- Align with sustainability goals: AI should be used as a tool to support and enhance sustainability efforts, rather than as an end in itself. Make sure that the AI projects being undertaken align with the organization’s broader sustainability goals.
Makower: Before I let you go, do you ever get tired of people asking you questions?
ChatGPT: As an AI language model, I don’t have feelings or emotions, so I don’t experience fatigue or any other physical or mental states. I am designed to respond to a wide range of questions and provide helpful and informative answers. I am here to serve and assist, so feel free to ask me any questions you may have.
Thanks for reading. You can find my past articles here. Also, I invite you to follow me on LinkedIn, subscribe to my Monday morning newsletter, GreenBuzz, from which this was adapted, and listen to GreenBiz 350, my weekly podcast, co-hosted with Heather Clancy.