Mark Zuckerberg Teaches Us the TMKK of Game Theory

Why is Llama open sourced?

We’ll get to the answer in a bit, but just in case you need help understanding what Llama is:

Llama (Large Language Model Meta AI) is a family of autoregressive large language models (LLMs), released by Meta AI starting in February 2023.
On April 18, 2024, Meta released Llama-3 with two sizes: 8B and 70B parameters. The models have been pre-trained on approximately 15 trillion tokens of text gathered from “publicly available sources” with the instruct models fine-tuned on “publicly available instruction datasets, as well as over 10M human-annotated examples”. Meta plans on releasing multimodal models, models capable of conversing in multiple languages, and models with larger context windows. A version with 400B+ parameters is currently being trained

So what, you might say. There’s the OG ChatGPT, there’s Claude, there’s Gemini… so one more comes along. Ho hum.

Well, if you say that, you’d be very, very wrong.

Why would you be wrong?

Because of this:

In contrast, the most powerful LLMs have generally been accessible only through limited APIs (if at all), Meta released LLaMA’s model weights to the research community under a noncommercial license

Why does this matter? Because, as our good friend Claude explains:

“The release of the Llama model by Meta under a noncommercial license is a significant development in the field of large language models (LLMs) and artificial intelligence more broadly. Here’s why it matters:

  1. Accessibility: Before this, the most powerful LLMs were usually kept secret by the companies that made them. For example, OpenAI’s GPT-3 model could only be used through a paid interface, like a vending machine you put money into to get a result. By releasing Llama’s “model weights” – essentially the knowledge the AI has learned – Meta has allowed researchers and hobbyists to experiment with and build upon a cutting-edge language model. It’s like they’ve given away the recipe for a powerful tool, not just limited access to using the tool itself.
  2. Democratization of AI: Restricting access to top LLMs meant that only a handful of big corporations could really use this powerful technology. Imagine if only a few factories could use electricity. An open-source model changes the game significantly. It empowers way more people to explore creative uses of language models and lowers the barriers to innovation in this space. It’s like the difference between a few people having libraries versus everyone having access to all the books.
  3. Cost: Using LLMs through paid interfaces can get expensive quickly, putting them out of reach for many. It’s like having to rent a supercomputer every time you want to use one. With access to the model weights themselves, people can run the model on their own computers, dramatically reducing costs. This opens up experimentation to students, researchers, startups and others with limited budgets.
  4. Customization: When you can only access a model through an interface, you’re limited to pre-defined uses, like ordering off a set menu at a restaurant. Having the actual model provides much more flexibility to tailor and fine-tune it for specific applications and domains. This could lead to an explosion of niche language models customized for particular industries or use cases – imagine a model specifically trained to understand and generate legal jargon, or one tuned for writing poetry.
  5. Reproducibility and Transparency: In scientific research, it’s crucial to be able to reproduce results. Using an API is like a black box – you can’t see how the model works under the hood, you just get the output. With the model weights, the exact workings of the model can be scrutinized, enabling more robust research and understanding of how these models function. It’s like being able to examine the engine of a car instead of just looking at the exterior.

Model weights are the key to how a language model works. They’re essentially the “knowledge” the model has learned during training. In a neural network (which is what most modern language models are), the weights are the strength of the connections between the neurons. These weights determine how the model responds to a given input, like how a brain’s neural connections determine a person’s response to a question. By releasing the weights, Meta has provided the “source code” of their model, allowing others to understand how it works, modify it, and use it for their own purposes.

While the noncommercial license does place some limits on how Llama can be used (you couldn’t start a company selling access to it, for example), the release of the model is still a major shift in the AI landscape that could have far-reaching effects on research, innovation, and accessibility of this transformative technology. We’re likely to see a proliferation of new applications and rapid progress in natural language AI as a result.”

You don’t just get the dish to eat, as Claude puts it, but you get the recipe so that you can try and recreate (and modify) the recipe at home. Not all of us have specialized cooking equipment at home, but those of us who do can get cooking very quickly indeed.

Speaking of cooking, have you seen this excellent series from Epicurious called 4 Levels? Chefs of varying expertise (home cook to the pros) are invited to cook the same dish, but with varying levels of expertise, ingredients and equipment.

Source

That’s what the 8 billion, 70 billion and 400 billion parameter models are all about. Same idea (recipe), but different capabilities and “equipment”.

But why do this? If Gemini, Claude and ChatGPT are giving away basic versions for free and premium versions for 20 USD per month, then why is Meta not just giving away all versions for free… but also giving away the recipe itself?

Because game theory! (Do read the tweet linked here in its entirety, what follows is a much more concise summarization):

  1. You can get janta to do the debugging of the model for you.
  2. If social debugging and optimization of models makes AI so kickass that AI friends can replace all your friends, then who owns the technology to make these friends “wins” social media. Nobody does, because janta is doing the work for “everybody”. So sure, maybe Mark bhau doesn’t win… but hey, nobody else does either!
  3. The nobody else does point is the really important point here, because by open sourcing these models, he is making sure that Gemini, Claude and ChatGPT compete against everybody out there. In other words, everybody works for Mark bhau for free, but not to help Mark win, but to help make sure the others don’t win.

The economics of AI is a fascinating thing to think about, let alone the technological capabilities of AI. I hope to write more about this in the coming days, but whatay topic, with whatay complexities. Yay!

All this is based on just one tweet sourced from a ridiculously long (and that is a compliment, believe me) blog post by TheZvi on Dwarkesh’s podcast with Mark Zuckerberg. Both are worth spending a lot of time over, and I plan to do just that – and it is my sincere recommendation that you do the same.

The Quest for Peace

In opening the Peace Speech, he called peace “the most important topic on earth.”
Yet he noted that “the pursuit of peace is not as dramatic as the pursuit of war, and frequently the words of the pursuers fall on deaf ears.” Here is a dismaying truth: the most important topic on earth may fall on deaf ears! We are hardwired for drama, for competition, for the struggle to survive. Even when we cooperate, we often do it for the benefit of our own group—so our group can be stronger than the others. Kennedy himself took advantage of this inclination: when he called space the ultimate frontier, an adventure for all humanity, he motivated Americans in part by declaring that America would be first in space, thus appealing to our competitive nature. Global cooperation is more elusive than cooperation within clans, families, tribes, and nations. How do we mobilize attention to and efforts at cooperation on a global scale, when the challenge is not “us” versus “them”? Kennedy made progress in this direction, by emphasizing our common humanity and the mutual benefits of cooperation. We can use his example, his ideas, and his oratory as we struggle to achieve global cooperation in our time.

Sachs, Jeffrey. To Move The World: JFK’s Quest for Peace (p. 179). Random House. Kindle Edition.

I’ve ben thinking about this passage, on and off, for much of this year. If you think about it, this is at once an uplifting and a depressing passage.

Why uplifting? Because it talks about “the most important topic on earth”: peace.

Why depressing? Not just because the words of the pursuers of peace fall on deaf ears. But because we are able to understand, upon reflection, that we are hardwired for drama, for competition, and for the struggle to survive. Of which the first (drama) is an advantage when harnessed well, and the second (competition) is a feature and not a bug. These days we call it gamification and write papers about it.

But politicians the world over, and of all hues, tend to use the last of these to further their own ends. And in the long run, it is usually at great cost to society. I am talking of the struggle to survive. Utilizing the rhetoric of the struggle to survive to drive a political narrative is all well and good. But when we paint “our” struggle to survive as the struggle for survival of our group, it becomes a zero sum game. As Sachs puts it, even when we do cooperate, we often do it for the benefit of our own group, so that our group can be stronger than the others.

Cutting into an airport security line is a zero sum game, in which we want our group (our family, for instance) to be stronger than the others. Ditto for lane cutting in a traffic jam. Ditto for any political movement in any country of your choice.

Global cooperation really and truly is difficult when the challenge is not “us” versus “them”. Getting votes from “our” team is much easier not when you define “us”, but when you other “them”. That is, it is often easier and more profitable to define who we are not (we ain’t them!) than to spend time on defining who we are.

I’ve said it before and I’ll say it again: perhaps the most important lesson in economics is to realize that life is a non-zero sum game. This is true at the individual level, at the level of the family, the state, the nation, and all other hierarchies and groupings we choose to come up with.

It is also, unfortunately, the hardest lesson to internalize and apply, and it doesn’t make for a great political campaign. Far easier, and cheaper – at least in the short run – to identify and vilify the other. Unfortunately, the more you create ever smaller groups of “us”, the more fractured and separated we end up being in the long run.

Global cooperation in our time?

I would love it, but I’m not holding my breath.

Ajay Shah on Inheritance Taxes in India

… if you’re looking for the TL;DR, he says They Have Been, Are And Will Be A Very Bad Thing For India:

In India, estate duty was present from 1953 to 1985. The rates could be very high, as much as 85 per cent, but in practice collection was small. It was abolished by Rajiv Gandhi. Taxes on the estate or of inheritance are present in many advanced economies. On average, in the 24 countries of the Organisation for Economic Co-operation and Development (OECD) where these are found, they account for 0.5 per cent of tax revenues. It seems like a lot of complexity to suffer, in public administration, in return for a small amount of tax revenue.  
The prospect is even less appealing with wealth tax. This was introduced in India in 1957. As of 2012-13 it generated Rs 800 crore. It was abolished in 2015. It is present in four OECD countries and generates a negligible amount of tax revenue.  

So the data tells us that both taxes haven’t done much to raise revenue, and both have been abandoned because they haven’t generated enough revenue.

That’s empirics. What about the underlying theory?

  1. As he points out, incentives matter. The problem with too high a level of taxation is that you incentivize folks to either work less (yikes!)…
  2. … Or put in place measures to reduce their tax burden. Time their gifts to their children in such a way that the wealth stays with them for as long as possible, and is then transferred just before their passing, in effect.
  3. Or, of course, simply exit stage <insert pun of your choice depending on your preference>. Hello Dubai, Sri Lanka, or more exotic locales in the far beyond.

As he puts it, this is really all about growth v. redistribution all over again:

Lant Pritchett says that 99 per cent of the variation in the poverty rate across countries is explained by one number: The median income. If we want to change the poverty rate, the number to focus on is the median income. All the redistributive efforts of the state, through taxes, social programmes, etc sit in the residual 1 per cent (of the variation of the poverty rate which is not explained by the median income) and come at the price of reduced growth of the median income. The emotions of envy, of resentment, of takers rather than makers, should be excluded from public life.

And any economist (myself included) will tell you – or should, at any rate – that growth is of paramount importance for India. As it is, indeed, for any developing (or whatever the politically correct nomenclature is these days) nation today.

So what gives? Why do we still allow the emotions of envy, of resentment, of takers rather than makers to rule over public life?

  1. Because we do not think of life as a zero sum game, more’s the pity
  2. Because politicians may not like us economists, but by god they get game theory
  3. Because Alesina and Rodrik, now what to do.

And above all, what I relief it was to read and get to talk about an economic analysis of the problem at hand. These things are going out of fashion, I tell you, so hajjar thank yous to Ajay Shah!

What If I’m Wrong, Among Other Things

He passed away earlier this week, and a good place to begin learning about him is from his Wikipedia entry.

Go brew a cuppa

… and go through this thread when you have about an hour or so of nothing else to do. Some things you should savor, not consume.

How People Are Using GenAI

https://hbr.org/2024/03/how-people-are-really-using-genai

In addition to the hundred here, here are my use cases that I think aren’t in the list. Apologies if I missed some overlap!

  1. Translating Marathi documents into English, and vice-versa
  2. Cheating on Duolingo exercises (sue me, why don’t you :P)
  3. Summarizing academic papers in a way that suits my academic and professional background, and giving me a rating (1-10) about whether I should take the time and trouble to read it myself
  4. News-reading companion. I ask AI to adopt a cheery outlook and play devil’s advocate to my grim and negative takes
  5. Generating better prompts – I feed my prompts into AI and ask it to make ’em better and more thorough

What are your hatke use cases?

H/T: Navin Kabra’s excellent newsletter. Do subscribe.

The Conversation About Inheritance Taxes that I Would Like to Have

Are machines dystopian, or are humans dystopian? Asking for a blog post.

I am going to give this prompt to a very capable LLM. I would like you to critique this prompt, and let me know how it can be made better. Point out what is missing in terms of the comprehensiveness of my framework, as well as any details I may have missed out on. Optimize for the LLM giving an answer that holistically addresses the problem I am thinking about. We are not as interested in generating an answer to the problem as we are in generating a way to think about the problem. What the problem is will become clear upon reading my prompt. Also rate my prompt (for the parameters we’ve spoken about) on a scale of 1 to 10, where 1 is a poor prompt, and 10 is an excellent prompt. Please give me your reasons for the points I score, and reasons for points you have deducted.

“There has been a lot of controversy recently about whether India should, or should not have, an inheritance tax. I would like you to build out for me a framework to think through the issue. While doing so, I would like you to have a persona that has deep expertise in the global history of public finance, taxation laws, development economics, political economy and welfare economics. I would also like you to be well versed in the history of India’s taxation laws, and in India’s political economy. I would like you to assume that I am a very curious person, but with very little knowledge of economics, theoretical or applied. I like detailed explanations, but in simple English. I would like the framework to contain the following aspects, and please note that I plan to ask the LLM these questions sequentially, with plenty of scope for discussion, pushback and clarification after each question has been answered:

  1. Are there principles that underlie taxation for any economy? If yes, what are they? If not, what should a list of such principles look like?
  2. Within these principles, which will presumably be generic and applicable to all kinds of taxes, what principles might apply to inheritance taxes specifically?
  3. Should an inheritance tax be taxed while the money is still in the account(s) of the deceased individual, or the inheritor’s account? What would be better? For whom would it be better? The person being taxed or the entity doing the taxing?
  4. How should one think about the desirability of having an inheritance tax for an economy? Should it be a function of the number of people in an economy? Or their age? Or their inheritance laws?
  5. Should the state capacity of that economy have a bearing on the issue? That is, it might be all well and good to take from the rich, but does the state have the ability to spend that money effectively?
  6. Should inheritance taxes be a function of how thorough income tax laws are? For example, the higher the number of loopholes in the income tax act, the better the case for an inheritance tax is my line of thinking – is this justified?
  7. What is the history of the development of the theory surrounding inheritance taxes? What about the theory as applied to different geographies, different time periods, and countries with differing stages of development?
  8. Have countries enacted laws with sunset clauses? Why or why not?
  9. Have countries experienced Laffer Curve type problems upon implementation of inheritance taxes? How have these problems been detected, and how have they been dealt with?
  10. Based on our conversations so far, give me your top five “for” and top five “against” arguments for an inheritance tax in India today.”

Here’s Claude’s answer:

“Here’s my critique of your prompt:

Strengths:

  1. Comprehensive coverage: Your prompt covers a wide range of aspects related to inheritance taxes, including principles, implementation, history, and country-specific considerations.
  2. Persona specification: You provide clear guidelines for the LLM’s persona, which should help generate responses tailored to your needs.
  3. Sequential questioning: Breaking down the prompt into sequential questions allows for a structured and focused discussion.
  4. Encouraging discussion: You leave room for discussion, pushback, and clarification, which can lead to a more engaging and informative conversation.
  5. Specific to India: Focusing on India’s context helps narrow down the scope and generates more relevant insights.

Areas for improvement:

  1. Clarity on the target audience: While you mention that you have little knowledge of economics, it would be helpful to specify your background and the purpose of this framework (e.g., personal curiosity, policy-making, academic research).
  2. Prioritization of questions: Consider ranking the questions based on their importance or relevance to your understanding of the issue.
  3. Comparative analysis: You could include a question about comparing inheritance tax policies and their outcomes across different countries, especially those with similar characteristics to India.
  4. Societal impact: Consider adding a question about the potential social and distributional effects of inheritance taxes, such as wealth inequality and social mobility.
  5. Feasibility and alternatives: You could ask about the feasibility of implementing an inheritance tax in India given its current economic, political, and administrative context, and explore potential alternatives or complementary measures.

Missing aspects:

  1. Economic impact: Include a question about the potential economic consequences of an inheritance tax, such as its effects on savings, investment, and capital formation.
  2. Tax evasion and avoidance: Address the issue of tax evasion and avoidance strategies that may arise with inheritance taxes and how to mitigate them.
  3. Interaction with other taxes: Explore how inheritance taxes might interact with other forms of taxation, such as income, property, or gift taxes.
  4. Public opinion and political feasibility: Consider asking about public sentiment towards inheritance taxes and the political challenges in implementing such a policy.

Rating: 8/10

Reasons for the score:

  • Comprehensive coverage of key aspects
  • Clear persona specification and sequential questioning
  • Encourages discussion and focuses on India’s context

Points deducted:

  • Lack of clarity on target audience and purpose
  • Missing aspects related to economic impact, tax evasion, interaction with other taxes, and public opinion

By addressing these areas and incorporating the missing aspects, your prompt could be further strengthened to generate a more holistic and nuanced framework for thinking about inheritance taxes in India.”

Run with this framework, and please feel free to modify it and improve upon it. Please use this framework to have a discussion with an LLM about inheritance taxes. It’s the kind of discussion our ancestors were capable of having re: public policy issues.

Also, feel free to copy and improve upon the framework itself – run your prompts through an LLM to see how you can make your thinking about an issue better.

There is a discussion to be had about how the price, income and substitution effects are at play when it comes to spending time talking with folks online, or spending it talking to LLM’s, but I’d rather not go there for now.

I’ll say this much though: I’m usually quite favorably disposed to the substitution effect.

Harmunia Mode.

Is an inheritance tax a good idea or a bad idea?

Well, it depends.

What does it depend on?

It depends on whether you are a Congress supporter or a BJP supporter.

What else does it depend on?

It depends on whether you are answering this question in 2024, 2019 or 2014.

What does it not depend on?

Economic analysis.

I have read innumerable tweets/messsages today about the inheritance tax. Or death tax. Or estate tax. These are tweets and messages from economic analysts, politicians, think-tankers, journalists and policy makers.

Every single discussion has been about who has said what about inheritance taxes, and when.

Not a single discussion has been about an economic model that underpins the rationale for or against the inheritance tax.

  • What is it about India’s tax buoyancy that justifies (or doesn’t justify) an inheritance tax?
  • What about her demography? Does that have a role to play?
  • What about the loopholes in the Income Tax Act? Do they have a role to play?
  • What about her direct and indirect tax collections?
  • What about threshold limits for imposing such a tax?
  • How and why have other countries done it? Can we learn from their mistakes? Can we learn from their successes?
  • What are the alternatives?
  • If we do implement it, do we keep it in perpetuity?
  • How much money do we potentially raise if we implement it?
  • What might be the downsides?
  • How do we judge the quality of implementation if we implement it?

But no, let’s see who said what and when, call each other names, and prove that we are right and they are wrong. That’ll show them. Bloody losers. It’s because of folks like them that India is what it is today.

https://help.twitter.com/en/using-x/x-advanced-search

Do you want to play the game yourself, and show to members of your tribe how you were right and they were wrong? Click on that link, learn how to search on Twitter by date and by handle, and prove how Your Side Alone Speaks The Truth.

If, on the other hand, you are interested in, y’know, actual economic analysis, allow me to recommend Atkinson-Stiglitz and Diamond-Mirrlees, both from the 1970’s. It’s been a while since I’ve read them, and it’s not a topic I’ve ever particularly enjoyed, but I assure you that these are good places to begin.

But Twitter takedowns are faster and more fun, so there’s that.

As for me and what I think, I think that not only was Amit Varma right about the IPL, but if you ask me, he’s right about the harmunia too.

Optimizing for Delight

Here, take a look at this video:

As the video makes clear, the icon looks “sad and old” if you don’t use Duolingo for a while. The more you use it (and the more regularly you use it), the “younger” it will look.

This, if you want to be a grumpy, cantankerous cynic, has nothing to do with anything. If, on the other hand, you want to be a person who appreciates delightful little touches full of whimsy and wonder, this is just wonderful.

This, and other delightful little experiences woven into the Duolingo app, are due to the “Delight” team:

As the post makes clear, Duolingo wasn’t (and isn’t) optimizing for any specific metric – no change was expected in “their numbers”. Duolingo was (and is) optimizing for delight, plain and simple.

And, it turns out, optimizing for delighting your customers tends to work well for “your numbers”. Or to copy a much better turn of phrase, delight facilitates learning in ways one cannot anticipate.

There’s an important lesson in there for those of us working in education. Get your processes right, have a solid foundation, provide a good experience and make sure your academic processes are rigorous.

But do make sure that somebody, somewhere, is optimizing for delighting your customers.

What Are You Optimizing For, The MKBHD Edition

There is this thing called the Humane Pin. Maybe you’ve heard of it?

Humane, Inc. (stylized as hu.ma.ne) is an American consumer electronics company founded in 2018 by Imran Chaudhri and Bethany Bongiorno. The company designed and developed the Ai Pin, which started shipping in April 2024.

And by all accounts, if you haven’t heard of it, you aren’t missing much. It’s been panned widely in the press, and for a variety of reasons. In this case, in fact, don’t depend on me to provide a link. Just run a search for a review of the product, and click on pretty much any review that you like. Chances are that the review will say that it isn’t worth buying – for now, at any rate.

But one particular review, by MKBHD, has gone viral. We’ll get into the why of it, but for now, take a look at the review:

This review got the attention of lots of folks on Twitter, including this person:

I usually embed tweets, rather than post screenshots. So why a screenshot today? Because:

It is worth flagging that Vassallo sells a Gumroad course on Twitter growth, so there is a non-zero chance he crafted this post to get engagement whether or not he actually felt strongly about MKBHD’s review (and it worked).

(Note that I copied the screenshot from the same blog this quote is from).

Incentives matter, children. Not every take on Twitter is genuinely held. Some folks just crave the attention. That may or may not have been the case here, but ol’ Thomas really should be your friend here.

MKBHD responded with both a video and a tweet. Now this tweet I don’t mind embedding:

Marques is crystal clear about who he is optimizing for. He isn’t optimizing, he says, for pleasing product companies, or advertisers, or anybody else. He is optimizing for giving his viewers his honest recommendation and feelings about a product. The more he does this, and the better he gets at doing it, he is saying, the more he is likely to be rewarded for it.

And it’s not like I’m an expert at the YouTube game (and that’s an understatement, trust me) – but I would think 18 million subscribers means he’s doing kinda ok. Not bad.

TMKK?

No matter what you choose to do in life, ask yourself this one question ad infinitum:

What Are You Optimizing For?

The clearer you are about the answer to this question, the easier your job is. You don’t even have to trust me on this one – MKBHD says so!

John Gruber put it best:

There’s cool, and then there’s cool.