My exclusive interview with ChatGPT about AI, climate tech and sustainability

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:

1. 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.
2. Supply chain management: AI can be used to monitor the sustainability performance of suppliers and identify opportunities for improvement.
3. Predictive maintenance: AI can be used to predict when equipment will fail, reducing unplanned downtime and reducing energy consumption and emissions.
4. Energy management: AI can be used to optimize energy use in buildings and industrial processes, reducing energy consumption and associated emissions.
5. 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:

1. Optimizing waste management: AI can help optimize waste collection, sorting and recycling processes to reduce waste and increase resource efficiency.
2. 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.
3. Supply chain optimization: AI can help companies optimize their supply chains to reduce waste, improve resource efficiency and reduce their carbon footprint.
4. Product design: AI can help in the design of more sustainable products that can be reused, repaired, refurbished or recycled more easily.
5. 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:

1. ESG data analysis: AI can help analyze vast amounts of ESG data to support investment decisions and identify sustainable investment opportunities.
2. Risk management: AI can help investors identify and manage ESG risks, such as exposure to carbon emissions, water scarcity and human rights violations.
3. Impact investing: AI can help investors identify and evaluate investment opportunities that deliver both financial returns and positive environmental and social impact.
4. Compliance: AI can assist financial institutions in ensuring compliance with sustainable finance regulations and guidelines, such as the Paris Agreement on climate change.
5. 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:

1. 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.
2. 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.
3. 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.
4. 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.
5. 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 a