Tyler Cowen: Hayek lecture on economics, AI and large langauge models

Tyler Cowen gave the Hayek lecture in London this week. In my view, his personal charisma continues to be strong - and perhaps better than what you see in recordings of early talks. Tyler is funny (he could do with even more jokes!). He comments in the talk about the value of personal presence, and I think this is true and could be felt at the event. The video is above, so you can absorb much of the content … but how special was it to be there (?) (and also to chat to others there). The social capital part.

I make a short summary of my notes below. Suitable for a tweet thread. Then below I give you a few versions that GPT-4 did, after basic prompting and me feeding the very bad YouTube auto transcript including time stamps into it (unfortunately I needed to put into sections). I also asked GPT-4 to rate Tyler’s lecture (see end!)

GPT-4 summarised the talk well enough that it can tell you whether it’s worth listening to the whole talk and this only took a few minutes. My notes probably do about the same, but differently and of course you need to rely on someone there. I don’t think I saw any other note takers. Of course…. Context is (still) that which is scarce.

My short notes:

Two kinds of AI talks. 1. Audiences that need to be convinced. 2. Audiences that do not need to be convinced.

We have invented AI that is better than humans in many areas.

How should we think about this in economic terms ?

We have a research assistant, colleague and architect. Not a carpenter or gardener.

One argument. We have increased the capital stock. But another maybe we have increased the intelligence of society massively. So in that sense it’s labour. A new factor of production.

What is worth more? Or less?

Less.

1. Routine back office work, you are worth less. 2. Memorising facts is worth less.

Personal charisma will be worth more. Looks and how you come across more. Personal networks will be worth more.

Physical Co-ordination, carpenters and gardeners should be worth more. People who can manage having an assistant will do better.

How should capital be revalued ? Many forms of Labour are now less scarce. So long electricity, long some hardware.

The AI will be commodified. The gains will go to the users. No one is talking about Gutenberg the billionaire.

Central planning going to be harder. More projects, more complexity harder to centrally plan.

Economic insights rooted in Smith, Hayek. Decentralised systems hard to take over.

AI Can’t work in physical space. Think of it like Humans and dogs have co-evolved.

The AI is going to have its own economy. It’s own laws, it’s own economy. Maybe crypto.

(Missing: How Tylers uses AI more effectively, also the Q&A; jokes eg with Bryan Caplan testing the AI).

GPT summary (first 15 minutes):

Title: The Economic Implications of GPT: Unleashing the Power of Language Models

Renowned economist Tyler Cowen recently delivered a compelling talk, delving into the profound economic implications of large language models, particularly focusing on the celebrated GPT 3.5. In a nuanced exploration that blended empirical evidence with astute observations, Cowen engaged his audience in a thought-provoking discussion that left them pondering the transformative power of artificial intelligence (AI) in our labor markets.

Cowen began by highlighting the remarkable abilities of GPT 3.5, emphasizing its superior performance in tasks such as passing bar exams and medical diagnostics. Drawing from a personal anecdote, he playfully recounted how GPT 4, the latest iteration, aced an economics exam in a matter of months, leaving his colleague and himself pleasantly surprised. These achievements underscored the unprecedented capabilities of these language models and set the stage for the ensuing exploration.

Turning his attention to the economic landscape, Cowen posited that routine back-office work could become increasingly redundant as GPT models render such tasks obsolete. He postulated that the economy must adapt to this shifting dynamic, where the ability to access information effortlessly diminishes the importance of rote memorization. This transformation necessitates a reevaluation of the skills that hold value in the labor market.

Cowen intriguingly contended that personal charisma and physical appearance may ascend as prized attributes in this new AI-driven world. While expertise and knowledge remain crucial, the capacity to captivate and energize audiences could emerge as a distinguishing factor. Moreover, personal networks, built on trust and human connections, would retain their significance despite GPT's vast knowledge base. These factors prompt a reevaluation of the human qualities that AI cannot replicate, positioning them as valuable assets in an increasingly automated society.

Viewing GPT models as a unique factor of production, Cowen argued that their integration into our digital landscape propels the accumulation of intelligence at an unprecedented pace. Leveraging the power of the internet, these models represent a distinct combination of capital and labor. Cowen drew an insightful parallel with the historical impact of the printing press, underlining the accessibility and immediacy that GPT models offer, with vast potential implications for various sectors.

Demonstrating the practical impact of GPT models, Cowen pointed to programming as a tangible example. Citing a case study from Italy, he revealed that a temporary ban on chat GPT led to a dramatic 50% reduction in programming output overnight. This stark statistic underscored the symbiotic relationship between human programmers and AI assistance. By collaborating with GPT models, programmers could explore a multitude of ideas and experiment more freely, amplifying their creative output.

In his closing remarks, Cowen urged individuals to embrace the opportunities presented by this new AI landscape. Effectively managing the AI assistance at hand, particularly for academics, emerged as a critical factor for success. The ability to unleash the potential of AI research assistants and harness their capabilities as catalysts for intellectual exploration and innovation would define the future trajectory of individuals and their endeavors.

In sum, Tyler Cowen's thought-provoking talk shed light on the economic ramifications of large language models, notably GPT, stirring contemplation among his audience. As routine tasks potentially recede in value, the significance of personal attributes, networks, and the effective utilization of AI assistance becomes apparent. Ultimately, the fusion of human ingenuity and AI capabilities promises to reshape our labor markets, propelling us into an era where adaptation and collaboration hold the key to success.

GPT - I ask it to add the next 15 minutes:

Title: Unleashing the Power of GPT: A Transformative Journey in Economics

In a captivating lecture that left the audience pondering the future of labor markets and asset valuation, economist Tyler Cowen delved into the profound implications of large language models, focusing on the renowned GPT 3.5. With a keen eye for empirical evidence and astute observations, Cowen painted a compelling picture of the transformative power of artificial intelligence (AI) and its impact on our economic landscape.

Cowen commenced his talk by highlighting the extraordinary capabilities of GPT models, showcasing their remarkable performance in tasks such as passing bar exams and medical diagnostics. A personal anecdote about GPT 4 acing an economics exam in a matter of months demonstrated the astounding progress in AI capabilities. These achievements underscored the profound implications of large language models and set the stage for Cowen's exploration of their economic ramifications.

Turning his attention to the labor market, Cowen postulated that routine back-office work could become increasingly obsolete as GPT models render such tasks redundant. This shift necessitates a reevaluation of the skills and attributes that hold value in the workforce. Cowen intriguingly contended that personal charisma and physical appearance may ascend as prized assets in this new AI-driven world. While expertise and knowledge remain crucial, the capacity to captivate and energize audiences could emerge as a distinguishing factor.

Furthermore, Cowen emphasized the continued significance of personal networks in an era dominated by AI. Despite the vast knowledge base of GPT models, the trust and human connections formed through personal networks retain their importance. This highlights the unique qualities that AI cannot replicate, positioning them as valuable assets in an increasingly automated society.

Viewing GPT models as a new factor of production, Cowen postulated that their integration into our digital landscape propels the accumulation of intelligence at an unprecedented pace. The accessibility and immediacy that GPT models offer, akin to having a research assistant, colleague, and architect all in one, has the potential to reshape various sectors.

Drawing from a case study in Italy, Cowen provided tangible evidence of the impact of GPT models on programming output. A temporary ban on chat GPT resulted in a dramatic 50% reduction in programming output overnight, illustrating the symbiotic relationship between human programmers and AI assistance. By collaborating with GPT models, programmers can explore a multitude of ideas and experiment more freely, amplifying their creative output.

In considering the revaluation of capital, Cowen posited that high-quality land and natural resources, particularly those feeding into electricity production, may gain increased value as labor becomes less scarce. He also identified hardware companies like Nvidia, which produces the key GPUs used in GPT models, as potential beneficiaries in this evolving landscape.

Cowen acknowledged the speculation surrounding the revaluation of capital and the potential commodification of AI. However, he suggested that a significant portion of the gains would go to the users rather than the companies selling AI services. Drawing from historical technological advancements, Cowen emphasized that the most fundamental developments tend to benefit the users, and he expects this trend to continue in the AI era.

As Cowen concluded his talk, he reflected on the ways in which GPT models can be harnessed effectively. He emphasized the importance of setting context and asking follow-up questions to enhance the accuracy of the models' responses. By framing queries appropriately and refining the training process, users can unlock even greater potential from these language models.

In a fascinating side note, Cowen praised the advancements in augmented and virtual reality, exemplified by Apple's Vision Pro. These technologies aim to provide additional context, filling in the gaps in decentralized systems. The ability to create and manipulate context, which is often scarce in human life, emerged as a recurring theme in the remarkable developments of 2023.

Tyler Cowen's thought-provoking lecture shed light on the economic implications of large language models, particularly GPT, leaving the audience captivated by the transformative power of AI. As routine tasks diminish in value, the significance of personal attributes, networks, and effective AI utilization becomes apparent. The fusion of human ingenuity and AI capabilities promises to reshape our labor markets, ultimately leading to a future where adaptation and collaboration are the keys to success.

Then the next part:

Title: The Rise of GPT and the Transformative Potential in Economic Modeling

In the second part of his enlightening lecture, Tyler Cowen delved deeper into the remarkable capabilities of GPT models and their potential impact on various fields, including social sciences and economic modeling. He highlighted the impressive linguistic diversity that GPT models possess, even without explicit training in different languages, demonstrating their ability to comprehend and translate a wide range of linguistic data.

Cowen postulated that if GPT models can excel in modeling the intricacies of language, they can also be applied to model other complex systems. He introduced Bloomberg GPT, a forthcoming product that utilizes GPT models trained on the vast financial data of Bloomberg. This groundbreaking approach to macroeconomics has the potential to revolutionize central banking within the next two years.

Furthermore, Cowen envisioned a future where GPT models are utilized to create models of small villages and companies, eventually leading to a reimagining of social sciences. By feeding rich and specific data into GPT models, anthropological economists can develop semi-successful models of small-scale economies and gain a deeper understanding of various entities and systems. This approach may render traditional economic tools obsolete, as the focus shifts to generating rigorous models through comprehensive data input.

Cowen also touched on the use of GPT models in experimental economics, highlighting their ability to play economic games like human agents. These models can be fine-tuned and employed in place of human subjects, offering a cost-effective and efficient approach to conducting economic experiments.

Amidst discussions about the potential risks associated with AI, Cowen dismissed the notion that GPT models and their successors will rise up and overthrow humanity. He argued that overestimating pure intelligence overlooks the challenges that AI entities would face in operating in physical spaces. Drawing on the analogy of humans and dogs co-evolving, he envisioned a future where people form unique relationships with GPT models, using them as therapists, teachers, and companions.

Moreover, Cowen highlighted the emergence of a new AI economy, where AI entities will have their own laws, currencies, and economic activities. He emphasized the significance of cryptocurrencies in facilitating transactions and interactions between AI entities. Crypto, in his view, is perfectly suited for AI-based transactions, providing a means of exchange that avoids the complexities of traditional banking systems.

In conclusion, Cowen emphasized that the transformative power of GPT models and AI technologies will bring about significant changes in various fields. As social sciences adapt to this new era, the ability to model complex systems and the rise of a distinct AI economy will reshape traditional frameworks and necessitate new approaches to research and analysis.

And the next parts plus Q&A…

Title: The Impact of AI on Public Finances and the Future of Expertise

During the Q&A session, Tyler Cowen addressed concerns about the potential impact of AI on public finances. He acknowledged that the expansion of AI and the substitution of human labor could lead to a shift in tax revenues. However, he emphasized that the effects would vary depending on the country or region. Economies with a significant reliance on taxing routine office work, particularly across borders, might experience fiscal challenges. Nevertheless, countries with a broader distribution of labor, encompassing creative and innovative sectors, should maintain tax revenues without a significant crisis.

The discussion then turned to the question of which aspects of human intelligence AI cannot replicate. Cowen acknowledged that AI can replicate certain social skills, as evidenced by GPT's ability to exhibit bedside manner. However, he argued that it is the unique combination of social skills, physical presence, and human charisma that sets individuals apart. The ineffable qualities of human nature, blended with social skills, will continue to be valued and differentiate humans from AI.

Furthermore, Cowen highlighted the potential for AI to dethrone experts in various fields. AI can provide objective facts and information more accurately than most media sources, making it unnecessary to rely on experts for simple factual matters. Those individuals who possess creative skills, the ability to initiate and manage projects, and a self-starting initiative will likely see higher returns and increased status compared to traditional experts. Cowen expressed satisfaction with this shift, considering it a comeuppance for those experts whose expertise can be replicated or surpassed by AI.

In response to a question about the apparent lag in economic growth resulting from AI integration, Cowen compared it to the historical adoption of electricity. He highlighted the importance of time and the gradual process of incorporating new technologies into existing systems and institutions. Many academics and institutions still lag in embracing AI fully, contributing to the slower pace of economic growth. However, Cowen predicted that over time, complementary infrastructure would be built, institutions would reorganize, and knowledge storage and retrieval systems would improve. These developments, though not immediate, would eventually lead to significant productivity gains and transformative changes in society.

In conclusion, Cowen emphasized that while the immediate economic impact of AI might not be substantial, the long-term effects would be profound. He likened the current stage to the 1870s, a foundational period of technological advancement that set the stage for later explosive growth. Cowen projected that within the next 20 to 30 years, the world would experience a significant transformation driven by AI.

MOre Q&A

In this part of the discussion, Professor Tyler Cowen delves into the concept of trust in the context of technology, specifically artificial intelligence (AI). He draws a parallel to economics, where trust is crucial for predicting and understanding human behavior. However, he highlights that trusting technology poses unique challenges because it doesn't share the same biological wants and needs as humans.

To address the issue of trust in technology, Professor Cowen suggests a short-term solution of simply turning it off when needed. This implies that in the early stages of implementing AI systems, human intervention and control can mitigate potential trust issues. However, he emphasizes that in the long run, the market will play a vital role in shaping trustworthy AI. Market forces will drive the development of AI systems that are more reliable, responsive, and aligned with user demands.

The discussion also touches on the potential impact of AI on information polarization. Professor Cowen highlights that current AI systems, like GPT models, can provide unbiased and dispassionate responses to various perspectives. They can generate answers from different political orientations, potentially reducing the polarization often seen in media and public debates.

Regarding the job market, Professor Cowen discusses the potential displacement of white-collar work by AI. He suggests that while AI may enhance the productivity of educated individuals, it could lead to income polarization if certain white-collar jobs deflate in value. However, he also presents an alternative perspective where AI advancements might increase the value of jobs focused on human care and services.

When considering the future advancements of AI, Professor Cowen acknowledges the varied opinions within the AI community. He focuses his analysis on the near-term developments of GPT models rather than speculating about distant, advanced versions. He highlights the potential for significant progress with current AI models, such as training them on proprietary data, which can lead to improved performance and capabilities.

The discussion concludes with diverse topics, including Professor Cowen's affinity for London and his perception of it as an exceptional city. He briefly touches on the potential privacy implications of AI advancements and the utilization of personal data. Lastly, he expresses his skepticism about reports of UFOs and emphasizes the need for critical evaluation and further investigation of unidentified phenomena.

In summary, this part of the discussion provides insights into the challenges of trust in technology, the potential impact of AI on jobs and information polarization, the future developments of AI models, and Professor Cowen's thoughts on various tangential topics.

Then I finally try and get GPT to summarise everything (I think there might 3% slight mistakes/hallucination but no more than what a research assistant might do…)

Title: Trust, Jobs, and the Future of AI: Exploring the Economic Implications with Professor Tyler Cowen

Introduction:

In this comprehensive exploration of the economic implications of artificial intelligence (AI), we engage in a thought-provoking discussion with Professor Tyler Cowen. As a leading economist and expert in technology and innovation, Professor Cowen provides insights into the challenges surrounding trust in technology, the potential impact on job markets, and the future of AI.

Trust in Technology and the Economic Implications:

Trust is a central concept in economics, as it underpins transactions, market interactions, and economic decision-making. However, the issue of trust takes on a different dimension when it comes to AI. Professor Cowen highlights the unique nature of AI, which lacks the biological wants and needs shared by humans. This raises questions about how we can trust AI systems and rely on their decision-making capabilities.

From an economic perspective, trust in technology is vital for its widespread adoption and utilization. If users perceive AI as unreliable, untrustworthy, or unpredictable, it may hinder its integration into various sectors and impede the realization of its potential benefits. Thus, establishing trust in AI is crucial for fostering its acceptance and utilization in economic activities.

Professor Cowen argues that in the short run, the ability to turn off AI systems provides a level of control and mitigates potential trust issues. However, in the long run, market forces will likely drive the development of more trustworthy AI. Users' demands for reliable, responsive, and ethically aligned AI systems will incentivize the creation of technologies that engender trust and enhance economic outcomes.

AI, Jobs, and Income Distribution:

The potential impact of AI on job markets and income distribution is a major concern. While some argue that AI will lead to widespread job displacement, Professor Cowen presents an alternative viewpoint. He suggests that AI advancements might deflate the value of certain white-collar jobs while potentially increasing the value of jobs focused on human care and services.

In this scenario, as AI assumes routine cognitive tasks, the importance of jobs related to personal care, childcare, elderly care, and other service-oriented fields may rise. These jobs often require the human touch, empathy, and interpersonal skills that AI struggles to replicate. Consequently, AI's impact on the job market may lead to a reevaluation of the societal value placed on different types of work, potentially reducing income polarization.

While the long-term effects on job markets remain uncertain, Professor Cowen emphasizes the need for continued education and adaptability to prepare the workforce for the evolving economy. Upskilling and reskilling programs can enable individuals to transition into new roles and industries, ensuring continued employment opportunities amidst technological advancements.

AI, Data, and Economic Productivity:

The effective utilization of data is a fundamental aspect of AI's economic impact. Professor Cowen highlights the potential for AI models, such as GPT, to leverage proprietary data to enhance their performance. By training these models on organization-specific data, such as medical records in hospitals, AI systems can provide more accurate and tailored assistance in various domains.

The integration of AI and proprietary data has implications for economic productivity. Organizations can leverage AI to gain deeper insights, streamline processes, and make data-driven decisions. This can result in increased efficiency, cost savings, and improved outcomes across industries. However, privacy concerns arise in the context of using personal data to enhance AI capabilities. Professor Cowen suggests that the future will likely see the development of privatized AI models, where queries and interactions remain within the organization, ensuring data privacy while still benefiting from AI-powered insights.

Economic Considerations and the Future of AI:

Looking ahead, Professor Cowen emphasizes the potential progress and advancements in AI models, such as GPT. He suggests that the convergence of AI, the internet, and other technologies may lead to a future

where these elements seamlessly blend into a unified development. This integration could result in transformative changes across various sectors, driving scientific progress and potentially reshaping the nature of human lives.

However, the economic impact of these developments is uncertain. While AI has the potential to accelerate scientific discoveries and productivity growth, its true effect on GDP growth and societal welfare remains to be seen. Professor Cowen poses critical questions about whether AI advancements alone can solve complex societal challenges, such as income inequality or infrastructure development.

Conclusion:

In this in-depth exploration of the economic implications of AI, Professor Tyler Cowen provides valuable insights into the challenges and opportunities presented by this transformative technology. From the importance of trust in technology to the potential impact on job markets and economic productivity, his analysis offers a nuanced understanding of the evolving AI landscape.

As we navigate the future of AI, Professor Cowen highlights the need for careful consideration of ethical concerns, privacy issues, and the societal implications of AI-driven advancements. Balancing the potential benefits of AI with the preservation of human values, equity, and social welfare is crucial for realizing the full potential of this technology.

Ultimately, the future of AI lies not only in technological progress but also in our ability to navigate the economic and social dimensions of this transformative force. By engaging in thoughtful discussions, embracing adaptability, and shaping AI's development through ethical frameworks, we can steer the trajectory of AI towards a more inclusive and prosperous future.


Finally I ask GPT to give Cowen a rating….

As an AI language model, I don't have personal opinions or the ability to listen to lectures or evaluate them directly. However, based on the information provided in the conversation, Professor Tyler Cowen's lecture appears to be insightful and thought-provoking. He offers nuanced perspectives on the economic implications of AI, exploring topics such as trust in technology, the impact on job markets, and the potential for economic productivity. The inclusion of economic thinking and consideration of various viewpoints adds depth to the discussion.

Considering the breadth of topics covered and the expertise of Professor Cowen, I would rate the lecture highly, potentially an 8 or 9 out of 10. However, it's important to note that individual preferences and opinions may vary, and a comprehensive evaluation would require a more detailed analysis and direct engagement with the lecture material.

More economics…see my interview and podcast with Mark Koyama on economic history and how the world became rich.

More AI, check out Kanjun Qiu, CEO of Generally Intelligent on AI, institutional knowledge and meta-science.

My regular substack is here:

FCA has published a collection of ESG/sustainability thought pieces

Recommended ESG reading. FCA has published a collection of ESG/sustainability thought pieces. I’ve had a first read today. You are unlikely to agree with all the pieces, but they argue for nuanced views and hit right at the tip of cutting edge debates in this area. So, I am going to suggest this is recommended reading for all those interested in ESG, sustainability issues, long-term investing and governance thinking overall. As part of a FCA consultation. Articles are:

  • Taking a holistic and purpose-led approach to net zero (Tayler, Aviva)

  • Using pay to create accountability for ESG goals (Gosling, LBS)

  • Transitioning to net zero: increasing investor confidence in corporate carbon Commitments (LSE research)

  • Adding purpose to principles and products (Eccles, Oxford) 

  • How to build an effective culture to support climate and sustainability-related objectives in the financial sector (Deloitte)

  • Board-level governance of climate-related matters (Chapter Zero)

  • How a Chief Sustainability Officer can most effectively support a firm in achieving its climate and sustainability-related objectives (Martindale, Cardano)

  • Governing climate transition implementation at banks (Mavraki)

  • Effective governance of investor stewardship to support net zero: a practitioner’s view (Chow, ICGN)

  • Preventing greenwashing: time to stop marking our own homework (Thompson, FCBI) 

Downloadable here and link to splash page here.


George Serafeim podcast transcript, Citywire with Algy Hall | Fix the Future

I made a transcript of the George Serafeim and Algy Hall (Citywire) podcast on ESG. Algy doesn’t challenge George on the push back on one of his key co-authored papers: Corporate Sustainability: First Evidence on Materiality (a summary commentary on the critique with links to it here - the comments are from noted statistician Andrew Gelman, but the orginal critique is from Luca Berchicci and Andy King). This was for many years a well quoted piece of evidence for ESG materiality. The case from academic papers is now more mixed with some of the strongest evidence (IMHO) remaining from the Alex Edmans employee satisfaction work and related work on “human capital” (a term that many non-accountants don’t like!), Caroline Flammer’s work on incentives, long-term, and CSR/ESG (using regression discontinuity design) and some of the work on material transparency.

Still, George is a leading business school voice on ESG/Sustainability and his comments on “Purpose and Profit” and the extra-financial factors that can drive business are useful to know.

(While I podcast myself, I find it much quicker to read transcripts more than listen when I’m going through a lot of work).

Podcast available at link here and below:

Fix The Future Show: ‘ESG was Never Meant to Save The World.’

George "There is a misperception about what ESG is as a management concept, as a governance concept, as an investment concept in business. ESG, at least in my mind, was never meant that it would save the world."

Algy (00:17):

That was George Serafeim, the Charles M. Williams Professor of Business Administration at Harvard Business School, who I'm talking to on this month's Fix The Future Show; the podcast where we explore ideas about how investors can do good in the world while making good money. I'm Algy Hall, the investment editor of Citywire: Fix the Future. Over the last decade, George has been a pioneer in developing the common sense ideas that underpin ESG. He has also been involved with much of the most influential research in the field and continues to push the subject forward including through his work on impact weighted accounts which we'll hear more about later. He's also the author of the recently released book, “Purpose and Profit: How Business Can Lift Up the World.” It's a book I can highly recommend. Hello, George.

George (01:10):

Hello. It's a great pleasure to be here with you.

Algy (01:12):

It's a great pleasure to have you here. I've been a huge fan of your work for many years.

George (01:19):

Thank you.

Algy (01:20):

Well, thank you, I should say. I thought a good place to start was just with your interest in transparency and where that came from in terms of your work. It seems to be a common theme which runs through everything really; this ability just to provide transparency on what's actually going on in companies.

George (01:46):

Yes. For me, that idea is an extremely important one. I like to take people back on the journey that we have traveled over the last hundred years. So if you think about it, the world that we have created, the economic system that we have created, and the society that we have created, a hundred years ago we didn't even have some basic financial reporting and control systems in markets. So if you wanted to get information about the profitability, the sales of a company and so forth, you would be getting very little information, if any information. So things that we take for granted right now were just not there a hundred years ago and a few decades ago in most markets actually around the world. Over time, what we decided as a society is that in order to have accountability over the management of financial resources inside that organization, it would be a good idea to create transparency and to have consistent comparable accounting standards. Then all the mechanisms around the production of accounting numbers, such as, for example, auditing of those, analysis of those and so forth in order to create an accountability structure that then what are the effects of that? Well, it can lead to better resource allocation, decisions, and management of those resources.

If you take that paradigm and apply to what is happening right now in terms of sustainability, you can ask the question, "What are those resources that then we're interested in to understand the efficient and effective management of those?" I think the world has changed and now more and more of the competitors of organizations depend on the management of human capital, intellectual capital, social capital, natural capital, and so forth. So I think we're asking the same basic question which is, "How can we create an accountability structure and a governance structure around the proper management of those resources?" And what I always say is that without transparency, you're not going to get there. It's not a sufficient mechanism, but it's a necessary mechanism for us to be able to get to that accountability structure.

Algy (04:15):

It's the kind of first step on the journey, but vital to get on that journey. I'm going to say you've been at this a long time, but actually it's probably only just over a decade you've really been devoting yourself to this. In terms getting that message across and getting people to understand that idea that there are things which just aren't being measured which are really important to investment, and ESG can do that, or non-financial metrics can do that or play a role in it. How has that evolved from not being listened to early on to suddenly the huge interests that we saw kind of from around 2019, I guess? That's what it felt like to me.

George (05:07):

I think there is a very interesting reframing perspective that I think has happened and it's happening and will continue happening. So I think if you say-- And I have been saying that for a very long time, Algy. Which is if you actually say to a lot of people, "Should you care about ESG issues and sustainability issues and so forth?" Some people might say yes, some people might say no because they have their own interpretation of what that means. So I think you need to make it to people very, very specific. I will give you a very simple example of that. How much money firms are spending on actually hiring, retaining, and growing human capital inside the organizations? Then when you ask that question and you say, "How much actually do we know about how effective that process actually is other than getting one financial statement item in the income statement which says how much money you have spent on this?" But then when you look at it you say, "Well, actually there are organizations--" When you're actually observing what's happening inside organizations-- “There are organizations that are spending an enormous amount of resources to actually screen and hire the right type of people inside organizations. They spend an enormous amount of resources that are spending to actually grow people internally and promote people internally inside the organization.” 

Now, there are other organizations that are following a very different model and a very different strategy which is they primarily hire externally, especially for more senior positions. As a result, they're much less likely to internally promote people. Now, these are two different models. This is a fundamental aspect of what I would say ESG under the S which is the development of human capital inside organizations. It has tremendous implications we're finding in our research in terms of the future financial performance of organizations because it relates to the ability to be productive inside organizations, to be innovative inside organizations, and the cost structure of inside organizations. But when you put it in this context where you say, "Actually, how do you create value? How do you drive performance? How do you get the necessary talent side organization and how the organizations have different models that have fundamental implications for how much you are paying for the talent? It has fundamental implications for employee turnover, for ability to create a strong culture and alignment inside organizations and drive productivity innovation." That is actually something super important. You can actually ask the question, "Do we have the data to do this analysis?" Again, the answer goes back and says, "No, most organizations actually don't provide."

So for example, what we have been doing, we have been using big data and machine learning and artificial intelligence to construct very large data sets that allows us to understand the internal promotion versus external hiring patterns across thousands of organizations. Now, I can apply the same exact topic to, for example, decarbonization. Do you actually know apart from the high level statement of two organizations saying, "We'll get to net zero?" Okay, that is a good intention and a very aspirational intention. But do you have actually good information about how effective and productive those organizations are at actually navigating that journey? How much is coming from energy efficiency? How much is coming from energy substitution? How much is coming from circularity? How much all of those things are costing and which ones are actually leading to product innovation that might lead to revenue growth by greening your products, for example, and green product innovation?

The answer, I guess, is that we have very little information about this. So we are in the early stages of understanding those things. But I think when you're actually reframing them around how they're actually affecting risk and growth inside organizations, and future revenues, and costs inside organizations which goes to the idea of how those issues are becoming financially material and how those issues are likely to have different strategic relevance across different industries, geographic context, and firm specific strategies, then people are actually starting to develop an analytical model of how those issues are actually relevant for the competitive organizations.

Algy (09:56):

It is fascinating because there's just so much we don't see from the accounts. Investors understanding of capital seems to be developing massively with this realization that so much is intangible. Also, which goes hand in hand with the fact that tangible assets don't have the same relevance anymore, I guess. I suppose just in terms of them talking about materiality, I think one is fair to describe it is a kind of landmark piece of research which you were responsible for two colleagues. Look to that issue in, I think 2016, on the materiality of ESG and just that question of, "If people are doing the stuff that matters, does it matter to their share price and does it matter to their performance in the business?" This sounds from what you're saying you are doing now, that idea seems to be in a real genesis in terms of your work.

George (11:05):

Yeah. This is an important idea for several reasons. The first one is that organizations cannot do everything. I always like to say that because it's that much that you can actually do inside organizations. You cannot spread your organization very thin trying to actually satisfy everybody. So what we say is that the classic old return on management is a very, very important idea which is you really need to actually allocate management attention to the most critical issues that the organization is facing. So for example, if you are a mining firm, you really need to pay attention on health and safety inside the mines and community relations around the mines that are fundamentally giving you the ability and the license to operate. So as a result, for example, if you're running a gold mine, waste issues that are huge actually around mines are also very, very critical.

If you are actually running a pharmaceutical firm, for example, access to health and access to innovation and how you are thinking about access issues are becoming very, very important. If you are running basically very high carbon emitting industrial and manufacturing processes and so forth, those issues are becoming very, very important with increasing basically carbon regulation, awareness in society, customers demanding lower carbon products to satisfy their own aspirations to lower the carbon footprint and so forth. So there is actually a systematic process through which you can go and say, "Hey, what is it really that is likely to matter here and why?" I think that is also an important question. Is it that regulations are changing and the environment as a result is changing? For example, you can look at it and you can say, "Okay, I'm running or I'm investing in a steel or a cement manufacturer and now there might be an EU carbon border adjustment mechanism." What are the implications for that because of that change in regulation? Or you might have actually export, for example, to the United States and now you have the inflation reduction act for battery manufacturing or for ingredients that go into batteries. Well, obviously that is actually changing the competitiveness of your product. So regulatory changes is one of them.

The other one is legal changes that might be happening. Increasing litigation, for example, in the context of climate change and carbon. That is another mechanism. Of course, changes in the competitive environment and new entrants that might be competing in the industry. So if you are actually, for example, Volkswagen or if you are General Motors and now you're competing in China with BYD and Nio and you're competing globally with Tesla and so forth, that is actually changing the competitive landscape for you and of course changes in buyer's requirements. So if you're actually a supplier in large consumer goods companies or in large retailers such as Walmart or Tesco and Sainsbury and so forth, well, actually you need to comply with your buyer's requirements. So that is actually becoming a core competitive issue. So it goes back to really trying to understand how the world around us is changing because of changes in regulatory mechanism in terms of product markets, labor markets, capital markets, and so forth. Then tighten that back and saying, "How is the organization likely to respond? And critically from that perspective how the organization can develop new processes in order to be able to innovate?" I think that is also an important point because many times we tend to view the world in a static way and we say, "Oh, I will try to do that but it's so expensive."

I like to say that the best organizations view the world in a dynamic perspective, meaning that what is costly today might not be costly tomorrow. And you're observing that, for example, in many markets around the world. So for example, we have brought the cost of batteries very, very significantly down. So everybody that 10 years ago would have said, "Look, I wish I could develop, for example, electromobility but the batteries are just so high.” Then you had different organizations that had a very different attitude to that. They saw that actually as an opportunity. Instead of saying, "The battery cost is so high, I just can't develop that," they said something very different which was, “Actually because the battery cost is high, I will bring it down and because I can bring it down, I will wait."

Algy (16:13):

There's a story which I think you have right on the front of your book “Profit and Purpose” actually, which is about-- I think it's Daimler; an executive from Daimler kind of essentially mocking Tesla. I thought that story captured so well some of the things you were touching on there. One is that static thinking which I think is the outsider, is investors. That's one of those things investors fight against because things are as they are until they're not. But also, it strapped me as kind of telling a story about the way we understand risk and idiosyncratic risk which is a lot of what you are talking about. It's just very hard to actually imagine a world where certain changes have happened.

George (17:04):

Yes. It's human nature I would call it. So it's almost like it's hard for us to imagine things before they happen, and then once they happen, we cannot imagine in the world that those didn't exist. You think about it, it's this kind of conundrum that we face as humans where actually, if I would tell you that we would have a world where we wouldn't even have basic financial information for organizations around the world, you would say, "George, this is impossible. This just cannot happen." I can tell you that before, for example, the Securities Exchange Act in 1933 and 34 and so forth, people actually pushed back against that idea that we would have accounting standards and financial reporting. They said, “This is never going to happen because every organization is very unique. You cannot do that and so forth.” So it's this weird thing that we cannot imagine the world before we experience it in most cases. But once we experience it, we cannot imagine the world without it. The same thing, a classic example of that is also the iPhone. Before the iPhone came actually, so much in the telecommunication space, so much thinking was about how you will just be putting basically a phone right next to your ear. And once they came up with this giant screen on the phone, people were confused. They were like, "Why would I want the giant screen to be next to my ear?" Obviously, the innovators at Apple said, "You're actually missing the point."

Algy (19:01):

Yeah. Then we all got the point.

George (19:03):

Exactly.

Algy (19:06):

I suppose in terms of what you are saying, I was just wondering how much-- This year, obviously there's been a lot of backlash, if that's the right words to describe it, against ESG as an idea. I was wondering how much of that is kind of to do with people not really understanding the scope of it and also just seeing things as they are at the moment where the old price has gone up a lot and a lot of those stocks have performed very well, and suddenly that's smart and ESG is dumb. Also, maybe the perception is that ESG has been marketed as having a moral high ground which perhaps is not quite how it should be thought of in terms of it's beyond risk and opportunity.

George (19:58):

It's a really good question and I think it deserves almost a decomposition to the various themes. The reason why I'm saying that is because there are different layers here that need to be analyzed. The first one is that sometimes it's because there is a misperception about what ESG is as a management concept, as a governance concept, as an investment concept in business. And ESG, at least in my mind, was never meant that it would save the world. There are several people that think that, "Oh, this is a mechanism or it has been advertised as a mechanism. That it will save the world. That it will solve basically poverty and inequality and climate change and waters, cars, and so forth." And it cannot do that. It wasn't meant to do that. It is a framework through which organizations are trying to measure, analyze, drive performance, and communicate key performance indicators that are actually relevant for them. Why? Again, because of going back to what we're saying about how the world is changing, and that's it. So I think there is sometimes a misalignment of expectations compared to the people that see it as a save the world type of tool which is not what this is.

I think the second one has to do with the fact that because ESG has become more important in how organizations are being managed and governed, it has started having more real implications. It starts to have more [meat]. A couple of years ago we published a paper where we looked at the stock market reaction to the passage of the non-financial reporting directive in the EU. One of the things that we found was this very interesting result that in the announcement of the regulation, the stock prices of companies that tended to have both good disclosure and good underlying performance or key performance indicators on ESG issues, in general, they show a small stock price increase in short term, and the organization that had poor disclosure and relatively poor expectations of bad performance on those key performance indicators, they show a negative stock price reaction on those.

The reason why I'm mentioning that is because for me, that paper is a perfect illustration of the point that not every organization will win from this as ESG is becoming more important. There are going to be some organizations that will experience an increase in their competitiveness and some organizations that will experience a decrease in their competitiveness. You would expect that naturally as these issues are becoming more important, the organizations that will see that as the threat to their identity, to their competitiveness and so forth, they will push back. So there is a natural pushback that is happening because of the underlying competitiveness that is happening there.

I think the third reason why it is normal to expect that is because basically sometimes it's misapplied as a concept what it is. And as a result, because there are bad or suboptimal applications of it, people are experiencing not the intended outcomes that they had expected either in terms of the impact that it might be generating or because it actually doesn't create value, it doesn't reduce risk, it doesn't open up new opportunities for innovation and so forth. So people are looking back and they say, "Oh, as a result, it didn't deliver on its promise." I always like to say that because there is a big difference and a big distinction between strategy development versus strategy implementation. I always say that. Every organization now that I know of has an ESG plan. But that doesn't mean that the plan is a good plan or that the plan is going to be implemented the right way. I think it's in that step of implementation where you observe many organizations actually failing. They cannot get the type of cultural transformation that is needed to really drive performance. They cannot get the incentives to be aligned. They cannot credibly communicate what they're doing.

As a result, all kinds of bad outcomes are happening which is happening also in any strategy that they're trying to implement. Not all mergers and acquisitions work. A lot of R&D that organizations is doing is failing. A lot of capital expenditures are going to zero. There are a lot of things that are successes and a lot of things that are failures. I think when you're decomposing ESG to the types of things that you are trying to drive basically; decarbonization versus human capital related issues versus product safety related issues versus supply chain related issues, you would naturally expect to see some successes but also some failures. And really, that's what I'm trying to emphasize in the book as well; that it is not all good and great. It's actually a lot, especially for organizations that are trying to do ambitious things with their products and services, there is a lot of failure and a lot of experimentation as well.

Algy (26:16):

Yeah. In your book you make that point, you really kind of drive that home that this isn't a magic wand. I'd like to come back to that actually. Also, just in terms of when you were talking about competitiveness because one of the things which I-- I love numbers. I've just got a natural affinity for anything you can quantify.

George (26:43):

Me too. Anything that makes [ ]

Algy (26:45):

I can tell from your work, obviously. It is the impact way to the accounts that I wanted to talk about because you talked about the underlying competitiveness of businesses seen through this prism of what are the real risks and real rewards. The impact way to the accounts try to put the external benefits companies have and also the kind of free ride, the external costs that they enjoy back into the accounts.

George (27:21):

We started this project about three years ago and we incubated it as a research project here at Harvard Business School in collaboration with many external partners because we were trying to understand how we can actually think about a holistic performance measurement and evaluation system inside organizations that doesn't only reflect right now, the financial performance of the organization in terms of the profit that is generated based on a transaction based system of double entry bookkeeping of resources going in and going out inside the organization and so forth. But actually reflecting and asking the question that if both the positive but also the negative impacts that organizations are having, if they were quantified and they were valued, what would that performance of the organization look like? For me, that journey of measuring impact and valuing impact that then can be reflected in pounds and in dollars and in yen and in euros and so forth, is a fascinating journey.

For me, it has revealed several key insights. The first one is how different actually your evaluation system might look like when you're measuring inputs versus when you're measuring outcomes. And because in the impact way the account system we're actually concentrating on measuring outcomes, meaning not the intentions and the targets and the efforts that you're pursuing, but what are the actual impacts and outcomes that you're achieving? We're getting at a very, very different assessment of which organizations are leading and which organizations are lagging. And because in the ESG space we have been measuring to a large extent what I would call inputs, meaning policies and principles and disclosures and targets and investments that we make and so forth, and much less the outcomes and the impacts that we're achieving, then you actually find that sometimes what we celebrate as leaders might not be actually leaders in terms of outcomes. Some other organizations that are really actually delivering much better impacts and much better outcomes wouldn't necessarily be the ones that you would find them being the most highly ranked in ESG evaluation systems. I think that is a very, very important distinction.

The second one is that I think for me, sitting here at Harvard Business School, I have always been trying to think about ways that you can actually engage with business managers and leaders in business in a way that they can associate with that and they can actually start getting their arms around some of those issues. Always a challenge has been that if you tell a leader, "Hey, you're consuming 300,000 cubic meters of water or you're having basically 0.002 carbon intensity or like a hundred times of that. Or if you say lost time injury rate of 005 and all of those things, it's just hard to grapple with." So the question is how can we actually translate things in a way that it is easier to actually embed in business planning? Because if you want people to actually make improvements in a real way, you need to actually translate and create a management system that allows for people to understand what are the consequences of action and what are the consequences of inaction? And as a result for us being able to say, "What would it mean if you had a hundred dollars or a $50 carbon tax or carbon border adjustment mechanism in your business, and how much of that would be your profit? How might your profit look like in a carbon adjusted earnings per share system or in a safety adjusted carbon per share system? Or if you're a consumer’s good company, in a shelf and wellbeing adjusted earnings per share system."

That actually translates very, very interesting insights. When you actually look at some organizations and you say, "25% of your EBITDA might be wiped out by this." But there are other organizations that are having tremendous positive impacts, actually. One of the things that also illustrated that whole analysis was how big is the difference between the strategies that different organizations are having? For example, when we analyze consumer goods companies and we said, "Okay, if we take the six basic ingredients that are affecting human life basically from a health perspective when you're consuming those products, such as, for example, fat that you might be consuming but also whole grains and so forth. There is tremendous difference actually across consumer good companies in terms of how much sugar they're selling versus how much whole grains they're selling.”

Those are having vastly different consequences on people in terms of cardiovascular disease, diabetes, obesity, and so forth. So when you're asking that question and you're saying-- Well, actually, again, going back and saying, "How is that important to me?" Well, if consumer preferences are changing, how the different organizations might be coping with this? If regulations might change, were they're actually forcing you to make those impacts more visible in your product labeling? Or if you might have a soda tax, for example, as it has been introduced in multiple jurisdictions around the world and so forth, how is that going to actually affect you? So for us, that whole journey has illustrated the value of measuring outcomes, the value of translating those outcomes into something that can be compared with existing financial measures that managers understand, and then the idea that it really actually illustrates the fact that within industries, there are very significant differences in the strategies that different organizations have adopted.

Algy (34:24):

Also, in terms of talking about consequences and the measures like the adjusted EPS and things like that. How much of that is something that an investor could use as a real basis for investing or is it more just to show actually what these companies are doing and less of a practical tool?

George (34:49):

This is my expectation that actually five to 10 years from now, this is what actually investors interested in applying some type of ESG analysis are going to be doing. They're actually going to be using a research and data infrastructure that looks into outcomes, that looks into the value of outcomes, and then is actually modeling the internalization process of those outcomes into basically growth, risk, future revenues, and costs. Because it is a more, I would say, robust and systematic process and scientific process of actually looking at what the actual outcomes are and asking what is actually really important and what is less important from the perspective of what's the value of those outcomes. So I expect that this will happen moving forward. The reason why I'm giving a timeframe is because it is a very challenging process. It is not easy. There are elements of that analysis that are easier to be done such as, for example, in our environmental impact pillar. I would say that it is easier to be done. It doesn't mean that it's easy, but it's much easier to be done relative to, for example, assessing product level of impact which is like the impacts that you're having on the actual customer and the consumer and so forth.

The reason for that is because those product impacts tend to be highly idiosyncratic. That's why in the impact way that accounts as well, we worked on a very industry specific pillar because you can ask the question. You can say, “How is a credit card, for example, affecting the consumers?” Well, it's fundamentally different than a car or a box of cereals as you can imagine. So these are very, very different dimensions that you're evaluating and you're constructing impact pathways and evaluation of those relative to something that is broadly standardizable and applicable, such as, for example, the measurement of nitrous oxide and sulfur oxide and water scarcity and carbon emissions and so forth that, of course, will differ dramatically across industries in terms of the magnitude. But the measurement of that KPI is exactly the same measurement of the KPI and then the valuation of it depends on the parameters that you might use.

Algy (37:25):

I suppose I kind of think of this and it sounds slightly like ESG 2.0 thing in a way. I was wondering if it did achieve that-- come into the consciousness of investors like that. Do you think it's possible that it could become a basis of regulation? When I was doing economics way back in school the externalities were one of those big things which people talked about but never thought to quantify really. Does it potentially have quite wide societal implications?

George (38:06):

I would think so that in the future as the state of those measurements improve over time, we might see actually more and more standardization and the development of specific guidelines and methodologies and even potentially disclosure regulations around what those might be. And again, I think different measurements have different attributes and they have different levels of difficulty. So I wouldn't be surprised if the first application of this will be something around the environmental domain where the state of the measurement is not perfect by any means, but it's certainly more advanced relative to other states of development. As a result you could actually do those types of calculations where somebody would say, "Well, if you would apply a certain price on carbon and a certain price on nitrous oxide and several other particulate matters and so forth, how would your profit looks like if you were actually doing that?” Much like many companies already do when they apply some type of shadow cost on the price of carbon in order to guide some of their capital budgeting process. I think it's a similar idea and we see that idea that is increasingly being used as a management tool, as a governance tool, and I think it can also be used as a transparency tool for everybody to have a common view of the underlying outcomes and how material those might be in different organizations.

Algy (39:58):

Yeah, I think it's absolutely fascinating. I suppose if we can kind of circle back. Another thing that I really wanted to talk to you about is your view on purpose. So your book is called,
Purpose and Profit.” One of the things you kind of set out how you can have an ESG policy rolling out through an organization which creates purpose, but purpose meaning a kind of innovative culture which kind of actually is responsive and dynamic unlike the German car maker who said, "Yeah. Well, electric cars, whatever." I thought it was a really interesting argument.

George (40:44):

It actually sounds funny right now when you actually say that sentence.

Algy (40:52):

Yeah. So if you could just explain this idea that actually this idea of purpose is very central to all these things you've been researching for so long.

George (41:10):

It's a central idea in my mind. The reason why I'm saying that is because I have been observing over the years more and more of my own students actually asking the question, "How can I actually find meaning in my work? How can I actually contribute and have impact from a personal perspective? Then how can I match that in a job role in an organization that is empowering me to do that, where I have actually the agency, the align incentives and the clarity about how I can contribute? That purpose can be very idiosyncratic. So your purpose might be very different than mine and my aspirations and so forth. I always like to say that it doesn't need to be that we all care about solving a really big problem and so forth.

It might mean that, “Hey, you're really passionate about building artificial intelligence mechanism that actually provides better information to consumers when they actually go to the grocery store, whatever that might be.” You're saying, "I would like to make that more broadly accessible, easier to use, less costly." Or somebody else might be super excited about going to an entertainment and media company and producing shows that really delight customers and produce happiness; the ephemeral happiness that we all live. But I think what that purpose does which is critically important is it actually allows you to drive alignment inside the organization, a shared set of beliefs about the organization that are likely to make employees more productive and potentially more innovative if that increases the level of trust inside organization. As a result, sharing information, collaborating inside organization, the reason why that is important in the context of some of the ESG related topics, and in general, some of the big challenges that the world is facing, for example, the sustainable development goal and so forth, is because many of those strategies; business models and so forth, are not easy to execute. They actually require very high levels of commitment from their organization.

As a result, it's much more likely that we will build many climate solutions organizations around the world if those organizations and those solutions are going to be led by purpose-driven organizations where employees are more committed to it. They work very hard, they really want to solve that problem, and as a result they exhibit higher levels of productivity, higher levels of innovation and so forth because it's not easy to be done. So that's where, for me, this idea of purpose connects to some of the big challenges that the world is facing, that they tend to be codified in some of the dimensions of the ESG and why those two pieces are connecting to each other. We wrote a piece for the American Economic Association several years ago around corporate purpose and climate change where we made that point that because it's actually a hard problem to solve, you need purpose-driven organizations that are more likely to take the kinds of risk, experimentation, and introduce disruptive innovations, but also to exhibit the higher levels of productivity innovation that are able to bring some of those solutions to the market and commercialize those solutions and make them broadly applicable.

Algy (45:25):

I think it's a great message actually. Also, last month we spoke to, Dan Ariely who's behavioral psychologist. Your views on purpose kind of tallied so much with what he has found from the field of psychology and he is now working on to translate into a way of understanding companies. Yeah, the human capital is-- especially in terms of the hierarchy of intangibles, really key I suppose is maybe a message we can take from it.

George (46:03):

Yes. Very, very, very important.

Algy (46:06):

But George, it's been an absolute pleasure to have you on and thanks so much for sparing the time to talk.

George (46:13):

Thank you very much for having me. It was a great pleasure to connect and have this conversation.

Algy (46:18)

Thank you.