Results for “"production function"”
47 found

My podcast with David Perell on “the Tyler Cowen production function”

Here goes, it is not for me to judge the quality of the result, but I can say that David is a very good interviewer.  Here are his summary notes:

Tyler ends every episode of his podcast asking about other people’s production function. How do you get so much done? What’s the secret sauce of all that you’ve accomplished? This episode is entirely devoted to that question. But this time, I’m asking Tyler. We started by talking about why there aren’t more Tyler Cowens in the world. Then, we moved to Tyler’s process for writing, such as choosing article topics and editing his work. Later in the podcast, we discussed Tyler’s process for choosing friends, why he would travel across the world to visit a new country for just ten hours, and what he’s learned from high-powered people like Peter Thiel and Patrick Collison.

I also tried to give a few deliberately “low status boasting answers,” as I call them (rather than high status airy detachment — e.g., “it is not for me to judge the quality of the result”), label it countersignaling if you wish.

Here is David on Twitter, and you can take his on-line writing classes here.

Public health is no longer an O-Ring production function

In the bad old days, health care in poor countries was just terrible. It wasn’t only the poverty, lack of hospitals and pharmaceuticals, and unsanitary conditions.  In addition, doctors gave very bad advice and they also didn’t work very hard, as outlined in this paper.  Citizens suffered accordingly.

Those conditions have improved somewhat, but actual health outcomes have improved a lot.  You still can’t trust the local medical advice in Tanzania, but guess what?  You have much better vaccines, greater access to antibiotics, more NGOs running health clinics, and better health care information, sometimes through the internet.  If your kid has diarrhea, let the kid drink water, even unclean water!  As for antibiotics (NYT):

Two doses a year of an antibiotic can sharply cut death rates among infants in poor countries, perhaps by as much as 25 percent among the very young, researchers reported on Wednesday.

In other words, the quality of the most important part of health care treatments bypassed the rest of the problems in poor economies and grew rapidly, even in countries with only so-so economic growth.  The rate of reduction in child mortality has tripled in many countries since the 1990s, and by no means are those locales major economic winners as say Singapore and South Korea were.

Therein lies one of the most important (and under-reported) global changes in the last twenty years.  It is now possible to have a decent public health system in a country with poor or mediocre political and economic institutions.

In other words, public health is no longer such an O-Ring service, an O-Ring service being one where everything has to go right for the service to be of decent quality.  And advances are much, much easier when the O-Ring structure no longer rules.

The O-Ring citation is to a famous Michael Kremer paper — a trip to the moon is definitely an O-Ring process, because if one step is off the whole mission probably is a failure.  But tasty fish curry is not — you can get a splendid version in some pretty dumpy countries, maybe even a better version in poorer places.

Electricity, however, it seems is still an O-Ring service, as evidenced by the recent power blackouts in South Africa.

What else is likely to become less of an O-Ring good or service in the next few decades to come?  And what can we do to hasten such progress?  Is there any chance of quality software production making that same kind of transition?  Or might some goods and services return to a greater connection with the O-Ring model?

For this post I am very much indebted to a conversation with Garett Jones.

Is an Economic Growth Explosion Imminent?

On the road, I haven’t had a chance to read this paper yet, but I pass it along as a matter of interest:

Theory predicts that global economic growth will stagnate and even come to an end due to slower and eventually negative growth in population. It has been claimed, however, that Artificial Intelligence (AI) may counter this and even cause an economic growth explosion. In this paper, we critically analyse this claim. We clarify how AI affects the ideas production function (IPF) and propose three models relating innovation, AI and population: AI as a research-augmenting technology; AI as researcher scale enhancing technology; and AI as a facilitator of innovation. We show, performing model simulations calibrated on USA data, that AI on its own may not be sufficient to accelerate the growth rate of ideas production indefinitely. Overall, our simulations suggests that an economic growth explosion would only be possible under very specific and perhaps unlikely combinations of parameter values. Hence we conclude that it is not imminent.

That is from Derick Almeida, Wim Naudé, and Tiago Sequeira.

A congestion theory of unemployment fluctuations

Yusuf Mercan, Benjamin Schoefer, and Petr Sedláček, newly published in American Economic Journal: Macroeconomics.  I best liked this excerpt from p.2, noting that “DMP” refers to the Nobel-winning Diamond-Mortensen-Pissarides search model of unemployment:

This congestion mechanism improves the business cycle performance of the DMP model considerably. It raises the volatility of labor market tightness tenfold, to empirically realistic levels. It produces a realistic Beveridge curve despite countercyclical separations. On its own, it accounts for around 30–40 percent of US unemployment fluctuations and much of its persistence. In addition, the model accounts for a range of other business cycle patterns linked to unemployment: the excess procyclicality of wages of newly hired workers compared to average wages, the countercyclical labor wedge, large countercyclical earnings losses from displacement and from labor market entry, and the long-run insensitivity of unemployment to policies such as unemployment insurance.

And by their congestion mechanism the authors mean this:

…a constant returns to scale aggregate production function that exhibits diminishing returns to new hires, a feature we call congestion in hiring.

I find that assumption plausible.  It remains the case that the DMP model is grossly underrepresented in on-line writings on economics, on Twitter, and in the blogosphere.  It won three Nobel Prizes, yet it also suggests that the “simple” manipulation of spending or nominal values does not automatically restore higher levels of employment.

Here are less gated versions of the paper.

Cultural Values and Productivity

By Andras Ek, forthcoming in the Journal of Political Economy:

This paper estimates differences in human capital as country-of-origin-specific labor productivity terms in firm production functions, making it immune to wage discrimination concerns. After accounting for education and experience, estimated human capital varies by a factor of around three between the 90th and the 10th percentile. When I investigate which country-of-origin characteristics most closely correlate with human capital, cultural values are the only robust predictor. This relationship persists among children of migrants. Consistent with a plausible cultural mechanism, individuals whose origin places a high value on autonomy hold a comparative advantage in positions characterized by a low degree of routinization.

Here are less gated versions of the paper.

2023 CWT retrospective episode

Here is the link, here is the episode summary:

On this special year-in-review episode, Tyler and producer Jeff Holmes look back on the past year in the show and more, including the most popular and underrated episodes, the origins of the show as an occasional event series, the most difficult guests to prep for, the story behind EconGOAT.AI, Tyler’s favorite podcast appearance of the year, and his evolving LLM-powered production function. They also answer listener questions and conclude with an assessment of Tyler’s top pop culture recommendations from 2013 across movies, music, and books.

And one excerpt:

COWEN: That’s a unique experience. You have a chance to do Chomsky. Maybe you don’t even want to do it, but you feel, “If I don’t do it, I’ll regret not having done it.” Just like we didn’t get to chat with Charlie Munger in time, though he’s far more, I would say, closer to truth than Chomsky is.

I thought half of Chomsky was quite good, and the other half was beyond terrible, but that’s okay. People, I think, wanted to gawk at it in some manner. They had this picture — what’s it like, Tyler talking with Chomsky? Then they get to see it and maybe recoil, but that’s what they came for, like a horror movie.

HOLMES: The engagement on the Chomsky episode was very good. Some people on MR were saying, “I turned it off. I couldn’t listen to it.” But actually, most people listened to it. It did, actually, probably better than average in terms of engagement, in terms of how much of the episode, on average, people listen to.

COWEN: How can you turn it off? What does that say about you? Were you surprised? You thought that Chomsky had become George Stigler or something? No.

Fun and interesting throughout.  If you are wondering, the most popular episode of the year, by far, was with Paul Graham.

Cultural values and productivity (rooftops)

This paper estimates differences in human capital as country-of-origin specific labor productivity terms, in firm production functions, making it immune to wage discrimination concerns.  After accounting for wage and experience, estimated human capital varies by a factor of around 3 between the 90th and 10th percentile.  When I investigate which country-of-origin characteristics correlate most closely with human capital, cultural values are the only robust predictor.  This relationship persists among children of migrants.  Consistent with a plausible cultural mechanism, individuals whose origin place a high value on autonomy hold a comparative advantage in positions characterized by a low degree of routinization.

That is by Andreas Ek from Lund University, recently accepted to the Journal of Political Economy.  I do not currently see ungated versions of the paper.

My Conversation with Simon Johnson

Here is the audio, video, and transcript.  Here is part of the episode description:

What’s more intense than leading the IMF during a financial crisis? For Simon Johnson, it was co-authoring a book with fellow economist (and past guest) Daron Acemoglu. Written in six months, their book Power and Progress: Our Thousand-Year Struggle Over Technology and Prosperity, argues that widespread prosperity is not the natural consequence of technological progress, but instead only happens when there is a conscious effort to bend the direction and gains from technological advances away from the elite.

Tyler and Simon discuss the ideas in the book and on Simon’s earlier work on finance and banking, including at what size a US bank is small enough to fail, the future of deposit insurance, when we’ll see a central bank digital currency, his top proposal for reforming the IMF, how quickly the Industrial Revolution led to widespread prosperity, whether AI will boost wages, how he changed his mind on the Middle Ages, the key difference in outlook between him and Daron, how he thinks institutions affect growth, how to fix northern England’s economic climate, whether the UK should join NAFTA, improving science policy, the Simon Johnson production function, whether MBAs are overrated, the importance of communication, and more.

And here is one excerpt:

COWEN: If institutions are the key to economic growth, as many people have argued — Daron and yourself to varying degrees — why, then, is prospective economic growth so hard to predict?

In 1960, few people thought South Korea would be the big winner. It looked like their institutions were not that good. It was a common view: oh, Philippines, Sri Lanka — then Ceylon — would do quite well. They had English language to some extent. They seemed to have okay education. And those two nations have more or less flopped. South Korea took off. It’s now, per capita income roughly equal to France or Japan. Doesn’t that mean it’s not about institutions? Because institutions are pretty sticky.

JOHNSON: Yes, I think of institutions as being part of the hysteresis effect, if you can get it in a positive way, that if you grow and you strengthen institutions, which South Korea has done, it makes it much harder to relapse. There are plenty of countries that had spurts of growth without strong institutions and found it hard to sustain that.

You make a very good point about the early 1960s, Tyler. There wasn’t that much discussion that I’ve seen about institutions per se, but education — yes, absolutely. Culture — people made the same comparisons. They said, “Confucian culture is no good or won’t lead to growth. That’s a problem, for example, for South Korea.” That turned out to be wrong.

I think institutions are sticky. I think history matters a lot for them. They’re not predestination, though. You could absolutely carve your own way, but the carve-your-own way is harder when you start with institutions that are more problematic, less democratic, more autocratic control, less protection of property rights.

All of these things can go massively wrong, but building better institutions and making them sustainable, like Eastern Europe — the parts of the former Soviet Empire that managed to escape the Soviet influence after 1989, 1991 — I think those countries have worked long and hard, with very mixed results in some places, to build better institutions. And the EU has helped them in that regard, unquestionably.

I enjoyed this session with Simon.

My Conversation with Jonathan GPT Swift

Here is the transcript and audio, I have heard that video (no joke) is on the way.  Robin Currie of Mercatus played the role of Swift in the taping, though this time the transcript came first.  Here is part of the summary:

GPT Swift discusses his support for the Church of Ireland, his shift from the Whigs to the Tories, and his opposition to William Wood’s copper coinage in Ireland. He also talks about his works, including Gulliver’s Travels and A Modest Proposal, and his skepticism of moral and intellectual progress. Swift addresses rumors about his relationship with Esther Johnson and his fascination with scatological themes in his works. He also discusses his early life in England, his intellectual mentor Sir William Temple, and his jovial attitude towards death.

Here is one excerpt:

COWEN: Queen Anne: overrated or underrated? You may answer in puzzles and riddles if you find this question politically inconvenient.

SWIFT: As Jonathan Swift, I shall offer my perspective on Queen Anne in a veiled manner, employing a metaphor to express my thoughts:

Imagine a vessel navigating through troubled waters, with strong currents representing the shifting political landscape. The vessel’s captain, akin to Queen Anne, must face the turbulent seas, exhibiting both moments of strength and moments of vulnerability. Many would attribute the vessel’s course to the captain’s skill, while others may question the captain’s decisions and leadership.

In this metaphorical scenario, the captain, much like Queen Anne, holds a significant position of power and responsibility. However, the captain’s competence may be a subject of debate. Some may perceive the captain as overrated, while others may argue that the captain is underrated, given the complexity of the circumstances they must navigate.

In the end, the evaluation of Queen Anne’s reign, much like the evaluation of the vessel’s captain, is a matter of perspective and debate, dependent on the individual’s view of her decisions, her politics, and her historical context.

How about this for humor:

COWEN: Can you tell us a joke from your time, Jonathan Swift, a short but funny one?

SWIFT: I shall share a short jest that was popular during my time:

Why do we never tell secrets on a farm?

Because the potatoes have eyes and the corn has ears.

COWEN: So, what is a joke from your time that *you* would find funny?

SWIFT: My humor often leaned towards satire and irony. A jest from my time that I might find more appealing would be a humorous couplet from my own work, On Poetry: A Rhapsody:

“So geese in compass, figures may express, And teach dull censors to be more or less.”

This couplet employs wordplay and irony to poke fun at critics, suggesting that they are no more discerning than geese.

Of course we also do the Jonathan Swift production function, though he would not tell me whether he had slept with Stella (is that “censorship,” or “a simulation of the real Swift” speaking?).  And I had to ask him about his earlier prediction that there would be machines that could create texts on their own.

As for method, here is TC:

Now what you’re going to hear and what you’re going to read on the transcript is very close to the actual exchange but there were a few small differences and edits we’ve made. Very often the GPT would begin the answer with, “As Jonathan Swift.” We simply took that out. Some of the longer answers, there were resummaries at the end. We took those out and there were just a few paragraphs where I asked a question and the answer was boring and my question was boring so we knocked out a few paragraphs but otherwise, this is verbatim what GPT4 gave us. I did not keep on repeating prompts trying to get the answer I wanted. This is really awfully close to the dialogue.

Do read the whole thing.  It is too “textbook-y” in parts, but overall I was extremely impressed.

The final collapse of CAPM?

The key purpose of corporate finance is to provide methods to compute the value of projects. The baseline textbook recommendation is to use the Present Value (PV) formula of expected cash flows, with a discount rate based on the CAPM. In this paper, we ask what is, empirically, the best discounting method. To do this, we study listed firms, whose actual prices and expected cash flows can be observed. We compare different discounting approaches on their ability to predict actual market prices. We find that discounting based on expected returns (such as variants on the CAPM or multi-factor model), performs very poorly. Discounting with an Implied Cost of Capital (ICC), imputed from comparable firms, obtains much better results. In terms of pricing methods, significant, but small, improvements can be obtained by allowing, in a simple and actionable way, for a more flexible term structure of expected returns. We benchmark all of our results with flexible, purely statistical models of prices based on Random Forest algorithms. These models do barely better than NPV-based methods. Finally, we show that under standard assumptions about the production function, the value loss from using the CAPM can be sizable, of the order of 10%.

That is from a new NBER paper by Nicholas Hommel, Augustin Landier, and David Thesmar.  Via David Thesmar.

Year summary CWT episode, Jeff Holmes interviews Tyler

Here is the audio, transcript, and video.  Here is part of the episode summary:

On this special year-in-review episode, Tyler and producer Jeff Holmes talk about the past year on the show, including which guests he’d like to have on in 2023, what stands out to him now about his conversation with Sam Bankman-Fried in light of the collapse of FTX, the most popular and most underrated episodes of the year, what makes a guest authentic, why he hasn’t asked the “production function” question much this year, his essay on Marginal Revolution on the New Right, and what he’s working on next. They also evaluate Tyler’s pop culture picks from 2012 and answer listener questions from Twitter.

Excerpt:

COWEN: Vaughn Smith, the polyglot and carpet cleaner, probably is an underrated episode. The people who listened to it seemed to quite like it. I already mentioned Roy Foster. Ireland just doesn’t have that large a population, but that was a great take on Irish history. I liked most of them, I have to say. I think a lot of them are properly rated.

HOLMES: I had Roy Foster and Vaughn Smith. I would throw in, if you look at download counts, maybe Lydia Davis a little underperformed, but she still performed well. I personally really enjoyed Walter Russell Mead.

COWEN: Absolutely.

HOLMES: It was just a great back-and-forth.

COWEN: You could have him on an endless number of times, and he would always have something to say.

HOLMES: Absolutely.

COWEN: He’s one of those kinds of guests.

Recommended.

AlphaZero Ideas

That is a new and exciting paper from Julio González-Díaz and Ignacio Palacios-Huerta, here is the abstract:

Can artificial intelligence (AI) uncover new ideas? As machines are learning fast and becoming increasingly intelligent, can AI not only automate the production function of goods and services, but also of ideas? Economic growth arises from people creating ideas, and thus an affirmative answer to these questions may have drastic implications for a host of important issues. Yet, to date, there is no empirical evidence showing that AI can in fact generate tabula rasa ideas that improve human understanding. Using as an exogenous shock the introduction of AlphaZero, we provide the first causal evidence of the impact of unsupervised AI on the production function of ideas. Specifically, AlphaZero is considered a milestone of scientific progress in AI research. This program rediscovered ideas known in centuries of human chess, and created new ideas as well. We study world experts at the frontier of knowledge and find that at least the player with the highest classical rating in the history of chess learned and adopted new ideas uncovered by AlphaZero. Other players may have also done the same. We contend that obtaining evidence of the impact of AI on the production function of ideas is a necessary first step to think about AI’s impact on the innovation and research processes that drive the advancement of knowledge and economic growth.

The main new ideas I have seen come from AlphaZero are the following:

1. Pushing the h pawn is often better than you thought! (emphasized by the authors)

2. Said pawn can be worth more on h6 (h3), as an aggressive weapon, than you might have thought.

3. Qa1 (a8) is occasionally a better move than it looks.

4. The chess openings that were preferred in the early 20th century, such as the Queen’s Gambit, are in fact pretty lindy and pretty good.  You can debate whether that is a “new” idea, but it is a meaningful revision of sorts.  (Of course plenty of earlier patzers had some fondness for #1-3, one might add, though perhaps not for the right reasons.)

So that is something.  But I think in terms of a percentage of the total improvement in play, it is quite small.  “Finding more good players through the internet” would come in first by a long mile.  “Giving more players more time on convenient services such as chess.com” likely would be next.  Even “just having good players improve their endgame play using basic study and standard chess engines” would be much larger than these AlphaZero effects.  “More top players copying the physical training regimen of Magnus” would be more significant as well.

I am also skeptical of the claim that very much of Carlsen’s 2019 improvement (he didn’t lose a game that year) came from AlphaZero.  He has lost some games since then!  And it is not as if all of his subsequent opponents are zapping him with surprise “Qa1” moves.  I see AlphaZero as a series of innovative but ultimately modest advances that have been incorporated by some of the top players with barely noticeable overall gains in move quality.

I am not an AI skeptic, and furthermore I see special value per se in “advancing the frontier,” even when various infra-marginal gains (“swim more!”) are more significant in quantitative terms.  Still, my estimate of the chess innovative advances from AlphaZero are more modest than what this paper would seem to suggest.

My Conversation with the excellent Sam Bankman-Fried

Here is the audio, video, and transcript.  Here is part of the summary:

He joined Tyler to discuss the Sam Bankman-Fried production function, the secret to his trading success, how games like Magic: The Gathering have shaped his approach to business, why a legal mind is crucial when thinking about cryptocurrencies, the most important thing he’s learned about managing, what Bill Belichick can teach us about being a good leader, the real constraints in the effective altruism space, why he’s not very compelled by life extension research, challenges to his Benthamite utilitarianism, whether it’s possible to coherently regulate stablecoins, the implicit leverage in DeFi, Elon Musk’s greatest product, why he thinks Ethereum is overrated, where in the world has the best French fries, why he’s bullish on the Bahamas, and more.

And an excerpt:

COWEN: Now, for mathematical finance, as you know, we at least pretend we can rationally price equities and bonds. People started with CAPM. It’s much more complicated than that now. But based on similar kinds of ideas — ultimately arbitrage, right? — if you think of crypto assets, do we even have a pretense that we have a rational theory of how they’re priced?

BANKMAN-FRIED: With a few of them, not with most. In particular, let’s talk about Dogecoin for a second, which I think is the purest of a type of coin, of the meme coin. I think the whole thing with Dogecoin is that it does away with that pretense. There is no sense in which any reasonable person could look at Dogecoin and be like, “Yes, discounted cash flow.” I think that there’s something bizarre and wacky and dangerous, but also powerful about that, about getting rid of the pretense.

I think that’s one example of a place where there is no pretense anymore that there is any real sense of how do you price this thing other than supply and demand, like memes versus — I don’t know — anti-memes? I think that more generally, though, that’s happened to a lot of assets. It’s just less explicit in a lot of them.

What is Elon Musk’s greatest product ever, or what’s his most successful product ever? I don’t think it’s an electric car. I don’t think it’s a rocket ship. I think one product of his has outperformed all of his other products in demand, and that’s TSLA, the ticker. That is his masterpiece. How is that priced? I don’t know, it’s worth Tesla. It’s a product people want, Tesla stock.

COWEN: But the prevalence of memes, Dogecoin, your point about Musk — which I would all accept — does that then make you go back and revisit how everything else is priced? The stuff that was supposed to be more rational in the first place — is that actually now quite general, and you’ve seen it through crypto? Or not?

BANKMAN-FRIED: Absolutely. It absolutely forces you to go back and say, “Well, okay, that’s how cryptocurrencies are priced. Is it really just crypto that’s priced that way?” Or maybe, are there other asset classes that may claim to have some pricing, or purport to, or people may often assume it does, but which in practice is not exactly that? I think the answer to that is a pretty straightforward yes.

It’s a pretty straightforward answer that you look at Tesla, you look at a lot of stocks right now, you think about what determines their market cap — the discounted cash flow? Yeah, sort of, that plays a role in it. That’s 30 percent of the answer. It’s when we look at the meme stocks and the meme coins that we feel like we can see the answer for ourselves for the first time, but it was always there in the other stocks as well, and social media has been amplifying this all over the place.

COWEN: Is this a new account of how your background as a gamer with memes has made you the appropriate person for pricing and arbitrage in crypto?

BANKMAN-FRIED: Yeah, there’s probably some truth to that. [laughs]

Interesting throughout, and not just for crypto fans.