Who’s the GOAT of Economics? Tyler Cowen on His New AI Book & More! [Bonus: from double-entry bookkeeping to supply and demand]

The influence of AI on economics:

59:06: I think we will start with small economies – you know take a village of 50 Native Americans up in Alaska – and we'll just gather all the data we have from that Village – we'll start with numbers – but then we'll go around and we'll talk to each person about what they do – their living – their income – what they buy – and we'll take all that and feed it into some supersized meta large language model and we'll have a model of that economy.

now how large we can make those models I'm not sure – but we'll start very small and it will progress – and it will be a fundamentally different way of doing economics – not sure how well it will work – at first it will be attacked but we won't be able to resist – we'll do it I do think we'll learn some things from that.

Why is early economics so poor?

1:29:20: look at 17 century economics it's pretty piss poor – I mean it's barely anything – so the 17th century Salamancans have some basic pieces – the early mercantilists have some basic pieces – but it's still fairly primitive.

there's something about economics that is more counterintuitive than we moderns realize I think – that's my conclusion – but I still find this a big puzzle

On the need for conceptual equipment

Obviously those early thinkers don't have the necessary conceptual equipment. Ideas can be constructed over other ideas, almost layer by layer. There is an inner architecture to thought. We may not understand that architecture at all well, but it is real nonetheless. Just what is required for economics, I don't know.

But I've thought about it a little. In my second piece in the GOAT Literary Critics series I do a quick and dirty comparison between economics and literary criticism. I settle on Malthus as my economist (not realizing that Adam Smith was earlier) because he clearly was worried about the future, worried about the future in a way that was new to the late 18th century. I don't know where that conception of the future came from, but it is new.

Cowen was talking about writing a paper about the conceptualization of pricing. The 17th century writing on the issue was not very good. For example, they don't have a conception of supply and demand. 

That's when rank 3 thought was emerging, to invoke the scheme David Hays and I wrote about in The Evolution of Cognition. There we argue that the early modern conceptual revolution was precipitated by the assimilation of Arabic arithmetic, leading to algorithms (derived from the name of the Arabic thinker, al-Khowarizmi) and effective calculation. It's downstream of that that we get conceptual foundations capable of supporting economic thought. That's where I'd look for the solution of Cowen's problem. 

Double-entry bookkeeping, calculus and other things

It's the next day (Dec. 12) and I've been thinking about these matters, including querying ChatGPT on related matters: Supply and Demand, Equilibrium & Calculus, Exponential Growth, Marginal Revolution, and Double-entry book-keeping. I've also skimmed the Adam Smith chapter in Cowen's book. The focus on time that I had in the literary critics post (linked above), is correct. Change over time is central to economic thinking. 

In his comments, Cowen mentioned Euclid and the calculus as being brilliant and difficult, so what's so difficult about supply and demand? – something like that. Well, math is one thing, applying it to the world in an illuminating way is another. First, you've got to conceptualize phenomena in the world in a way that can accept the appropriate mathematical formalization. Calculus may have been formulated in the 17th century, but it wasn't linked to economics until the 19th. It took Adam Smith and others to get the subject matter into a form that could accept mathematical formulation, no?

So, as I've said above, ideas can be constructed over other ideas, layer by layer. Here's the opening sentence of the Wikipedia article on calculus: "Calculus is the mathematical study of continuous change, in the same way that geometry is the study of shape, and algebra is the study of generalizations of arithmetic operations." What's the order these subjects are taught in school? Geometry, algebra, and then calculus. Why? Because the earlier subject provides conceptual foundations for the latter, no? The study of geometry gets you used to thinking within a formal system. Algebra then applies that to the task of generalizing over arithmetic, thus laying the foundations for the study of continuous change. Layer by layer.

But how do we get to supply and demand? I'm not prepared to give a detailed answer to that question. It's too difficult and I don't have the necessary conceptual equipment, though Hays and I gave some indications of what's needed in The Evolution of Cognition. Here's the question I'd ask myself: What does double-entry bookkeeping have in common with supply and demand? Double-entry bookkeeping dates back to the late 15th century and is a practical discipline. What becomes visible by 'going meta over that practice?

Double-entry bookkeeping is a system for maintaining closure over a set of transactions that grow over time as transactions are added to the list. We've got closure and change over time. Supply and demand change over time. Where's the closure, the dynamic closure? How do supply and demand complement one another in a say similar to the balance of debit and credit accounts in double-entry bookkeeping? How was Adam Smith able to get "on top" of that in the way that previous thinkers could not? How does the famous metaphor of the invisible hand do its work? 

I note that there are various uses to which metaphor is put. Some metaphors are used to explain technical concepts in a non-technical way. Other metaphors are used to explain concepts in the only way the thinker was capable of at the time. Smith's invisible hand is of the latter kind.

On the importance of algorithmic thinking

Let me conclude by quoting a passage from The Evolution of Cognition:

It is easy enough to see that algorithms were important in the eventual emergence of science, with all the calculations so required. But they are important on another score. For algorithms are the first purely informatic procedures which had been fully codified. Writing focused attention on language, but it never fully revealed the processes of language (we’re still working on that). A thinker contemplating an algorithm can see the complete computational process, fully revealed.

The amazing thing about algorithmic calculation is that it always works. If two, or three, or four, people make the calculation, they all come up with the same answer. This is not true of non-algorithmic calculation, where procedures were developed on a case-by-case basis with no statements of general principles. In this situation some arithmeticians are going to get right answers more often than others, but no one can be sure of hitting on the right answer every time.

This ad hoc intellectual style, moreover, would make it almost impossible to sense the underlying integrity of the arithmetic system, to display its workings independently of the ingenious efforts of the arithmetician. The ancients were as interested in magical properties of numbers as in separating the odd from the even (Marrou 179-181). By interposing explicit procedures between the arithmetician and his numbers, algorithmic systems contribute to the intuition of a firm subject-object distinction. The world of algorithmic calculations is the same for all arithmeticians and is therefore essentially distinct from them. It is a self-contained universe of objects (numbers) and processes (the algorithms). The stage is now set for experimental science. Science presents us with a mechanistic world and adopts the experimental test as its way of maintaining objectivity. A theory is true if its conceptual mechanism (its "algorithm") suggests observations which are subsequently confirmed by different observers. Just as the results of calculation can be checked, so can theories.

Not only experimental science, but economics as well.

Appendix: ChatGPT on the analogy between double-entry bookkeeping and supply and demand

I asked ChatGPT to explicate the analogy between double-entry bookkeeping and supply and demand. As you can see below, it did an excellent job, more complete and thorough than I had done. Note, however – and this is very important, I'd already done the (difficult) job of noticing that there is a (worthwhile) comparison to be made. I noticed this possibility shortly after I asked myself: What's so difficult about understanding supple-and-demand? Why was I able to pose that question? Because I knew that double-entry bookkeeping is something that was invented in the late-medieval early modern era and that it would have been common practice in the commercial world at the time thinkers were struggling to conceptualize supply and demand.

What kind of relationship am I implying there? Nothing in particular beyond the fact that double-entry bookkeeping was around. It may or may not have played a direct role in conceptualizing supply and demand dynamics. As ChatGPT pointed out in its response, we're dealing with two different domains, accounting and economics. They may be related, but they are by no means the same. It would take a bit of intellectual imagination to apply the pattern of actions in accounting practice to conceptualizing the relationship between buyers and sellers in the open market. 

* * * * *

In what way is double-entry bookkeeping analogous to supply and demand?

Double-entry bookkeeping and the economic principle of supply and demand are two concepts from different domains—accounting and economics, respectively. While they serve different purposes, it's possible to draw some analogies between them in terms of balancing accounts and market dynamics. Here's an exploration of how double-entry bookkeeping is analogous to supply and demand:

1. Balancing Equations:

In double-entry bookkeeping, the fundamental principle is that every financial transaction involves equal debits and credits, ensuring that the accounting equation (Assets = Liabilities + Equity) remains balanced. This concept of balance is analogous to the equilibrium in supply and demand.
In supply and demand, equilibrium occurs when the quantity supplied equals the quantity demanded in a market. This balance is a key feature of market dynamics, much like the balance in double-entry bookkeeping.

2. Interactions of Forces:

In double-entry bookkeeping, debits and credits are like opposing forces that need to be equal and opposite to maintain balance. Similarly, in supply and demand, there are opposing forces: an increase in supply tends to lower prices, while an increase in demand tends to raise prices. The interaction of these forces results in an equilibrium point.

3. Adjustments and Changes:

In both systems, adjustments are made to maintain balance. In double-entry bookkeeping, adjusting entries are made to ensure that debits equal credits. In supply and demand, changes in market conditions or external factors can lead to adjustments in prices and quantities to maintain equilibrium.

4. Dynamic Nature:

Both double-entry bookkeeping and supply and demand are dynamic systems. They respond to changes over time, and adjustments are made to maintain balance or equilibrium. In bookkeeping, new transactions are recorded, and in economics, market conditions change, affecting supply and demand.

5. Market Clearing:

In economics, the market-clearing price and quantity occur at the point where supply equals demand. This is analogous to the balanced state in double-entry bookkeeping, where debits and credits are equal. In both cases, there is a state of equilibrium that represents a form of balance.

It's important to note that while there are these analogies, double-entry bookkeeping and supply and demand operate in different contexts and serve distinct purposes. Double-entry bookkeeping is a method for recording and managing financial transactions within a business, ensuring accuracy and balance in accounting. On the other hand, supply and demand is a foundational principle in economics, describing the interactions between buyers and sellers in a market.

The analogies drawn here highlight the idea of balance, equilibrium, and the need for adjustments in response to changes. However, it's crucial to recognize the specific contexts and principles that govern each of these concepts in their respective fields.