Homo economicus sucks! Homo Ludens rocks!

Here's what Wikipedia says about Homo economicus:

The term Homo economicus, or economic man, is the portrayal of humans as agents who are consistently rational and narrowly self-interested, and who pursue their subjectively defined ends optimally. It is a wordplay on Homo sapiens, used in some economic theories and in pedagogy.[1]

In game theory, Homo economicus is often (but not necessarily) modelled through the assumption of perfect rationality. It assumes that agents always act in a way that maximize utility as a consumer and profit as a producer,[2] and are capable of arbitrarily complex deductions towards that end. They will always be capable of thinking through all possible outcomes and choosing that course of action which will result in the best possible result.

The rationality implied in Homo economicus does not restrict what sort of preferences are admissible. Only naive applications of the Homo economicus model assume that agents know what is best for their long-term physical and mental health. For example, an agent's utility function could be linked to the perceived utility of other agents (such as one's husband or children), making Homo economicus compatible with other models such as Homo reciprocans, which emphasizes human cooperation.

As far as I can tell, Homo economicus dominates the ideological formations behind the major institutional structures of Western society. More specifically, it dominates the world of AI, both as a model of the mind, and as a way of thinking about the social consequences of AI, but good and bad. I say it functions as an ideological formation because it is simply assumed to be how the world is.

One can, however, reject that assumption in favor of something else. I'm am rejecting it in favor of a view promulgated in Homo Ludens, published in 1938 by Dutch historian and cultural theorist Johan Huizinga. From Wikipedia:

It discusses the importance of the play element of culture and society.[4] Huizinga suggests that play is primary to and a necessary (though not sufficient) condition of the generation of culture. The Latin word ludens is the present active participle of the verb ludere, which itself is cognate with the noun ludus. Ludus has no direct equivalent in English, as it simultaneously refers to sport, play, school, and practice.

Thus:

Huizinga begins by making it clear that animals played before humans. One of the most significant (human and cultural) aspects of play is that it is fun.

Huizinga identifies 5 characteristics that play must have:

1. Play is free, is in fact freedom.
2. Play is not "ordinary" or "real" life.
3. Play is distinct from "ordinary" life both as to locality and duration.
4. Play creates order, is order. Play demands order absolute and supreme.
5. Play is connected with no material interest, and no profit can be gained from it.

Huizinga shows that in ritual dances a person 'becomes' a kangaroo. There is a difference in how western thought expresses this concept and how "primitive" religions view this. Scholars of religion use western terminology to describe non western concepts.

In the rest of this post I list a conversation I had with Claude 3.7 that starts with some passages from Yuval Noah Harari’s Homo Deus: A Brief History of Tomorrow (2017), which sets the current AI revolution in the context of all of human history. He accepts Homo economicus without question. I then propose Homo Ludens as an alternative.

My standard conventions apply. My prompts are in bold face. Claude's responses are in plain face.

Homo Economicus 

I’m reading Harari’s Homo Deus. In Chapter 9, The Great Decoupling, he says things like:  

In the twenty-first century liberalism will have a much harder time selling itself. As the masses lose their economic importance, will the moral argument alone be enough to protect human rights and liberties? Will elites and governments go on valuing every human being even when it pays no economic dividends?  

And: 

 The technological bonanza will probably make it feasible to feed and support the useless masses even without any effort on their side. But what will keep them occupied and content? People must do something, or they will go crazy. What will they do all day? One solution might be offered by drugs and computer games. Unnecessary people might spend increasing amounts of time within 3D virtual-reality worlds, which would provide them with far more excitement and emotional engagement than the drab reality outside. Yet such a development would deal a mortal blow to the liberal belief in the sacredness of human life and of human experiences. What’s so sacred in useless bums who pass their days devouring artificial experiences in La La Land?  

He's clearly assuming that humans get their value from their ability to make economic contributions. Where does he get that assumption? He attributes it to liberalism. Is that valid? Why happens to his argument if one rejects that view? Instead, one can affirm that human life is intrinsically valuable, that the sacredness of human life is intrinsic and not dependent on economic contributions.

You've pinpointed a crucial assumption in Harari's argument. His view that human value in liberal societies is fundamentally tied to economic utility is certainly debatable.

Harari is drawing on a particular interpretation of liberalism that emphasizes its economic aspects over its broader humanistic foundations. While economic productivity has certainly been valued in liberal societies, the philosophical underpinnings of liberalism - from Locke to Kant to Rawls - have often emphasized human dignity, autonomy, and inherent worth that exists prior to and independent of economic contribution.

If we reject his economic-centric assumption, his argument changes significantly. The "Great Decoupling" becomes less threatening if we maintain that human worth is intrinsic rather than instrumental. The questions become:

1. Can liberal societies maintain a commitment to human dignity without the pragmatic reinforcement of economic necessity?
2. How might social and political systems evolve to recognize human value beyond productivity?
3. What alternative sources of meaning and purpose might emerge beyond economic contribution?

Many religious and philosophical traditions have long held that human value is intrinsic and not dependent on utility. Even within secular humanism, there are strong arguments for inherent human worth based on our capacity for consciousness, relationships, moral reasoning, and subjective experience.

Harari's dystopian vision assumes that elites will abandon their commitment to universal human value once it's no longer economically expedient. But this presupposes that such commitments were only ever pragmatic rather than principled - a highly contestable claim about human moral psychology and political philosophy.

By questioning this fundamental assumption, you've identified a potential way to challenge Harari's more pessimistic conclusions while still engaging with the technological transformations he describes.

It seems to me that he makes unwarranted assumptions about AI. For example, he seems to accept Bostrom’s idea that super-intelligence is inevitable, though it is by no means clear just what “super-intelligence” might be. I notice that Harari was enthusiastic about the medical applications of IBM’s Watson. But five or six years have Harari published the book (2017) IBM sold-off it’s medical unit, presumably because it wasn’t performing well enough. Of course, Harari could point out that things will surely change in the future, as they surely will. Still, an awful lot depends on assumptions he’s making about the course of AI. He seems to assume that we have no choice about how we build and deploy the technology.

You're making an excellent point about Harari's technological determinism. He does seem to treat certain technological developments as inevitable rather than contingent on human choices and values.

The IBM Watson example is particularly telling. Harari was far from alone in overestimating Watson's capabilities and timeline for transformation in healthcare. This pattern of overestimating near-term AI progress while underestimating the complexity of real-world domains (like medicine) has been remarkably consistent in the field.

This relates to his treatment of "super-intelligence" as well. Harari often adopts Bostrom's framing without fully engaging with the conceptual ambiguities around what constitutes intelligence, how it scales, and whether certain capabilities would necessarily emerge together. The term itself bundles together various assumptions about how AI capabilities would develop. You're right that Harari tends to minimize human agency in shaping technology. While technology certainly constrains and shapes our choices, we still maintain significant collective agency in determining:

1. Which technologies to develop and which to restrict
   
2. How to regulate and govern AI systems
   
3. What social and economic arrangements to adopt alongside technological change
   
4. What values to prioritize in technological design

Harari's narrative can sometimes feel like technological developments simply happen to us rather than being the product of human decisions, institutions, and values. This tends to obscure the political and ethical dimensions of technological development. This connects to your previous point about human value as well. If we accept that human value is intrinsic rather than instrumental, that becomes one of the principles that can guide how we develop and deploy AI - not a casualty of technological "progress" but a constraint on what kinds of technologies we choose to build.

Thanks. This has been helpful.

You're welcome! I'm glad our conversation has been helpful for exploring Harari's arguments and placing them in a broader context of technological futurism.

The critical examination of underlying assumptions in works like "Homo Deus" is valuable - especially identifying where authors might be making deterministic assumptions about technology or adopting specific views about human nature and value that deserve scrutiny.

If you'd like to continue this discussion or explore other aspects of technological futurism, philosophical approaches to AI, or related topics, feel free to let me know.

Homo Ludens

Johan Huizinga wrote a book entitles “Homo Ludens.” What assumptions does he make about human nature and human life?

Huizinga's "Homo Ludens" (1938) presents a profound analysis of the role of play in human culture. His central thesis is captured in the title itself - "Homo Ludens" or "Playing Man" - suggesting that play is a fundamental characteristic of humanity, equally important to our definition as "Homo Sapiens" (thinking man) or "Homo Faber" (making man). Key assumptions Huizinga makes about human nature include:

1. Play is primary and foundational to human culture, not merely a derivative activity. He argues that play precedes culture historically and is constitutive of it.
2. Play is not merely instrumental or biological but has intrinsic significance. Unlike many of his contemporaries who viewed play as serving evolutionary or developmental purposes, Huizinga sees play as meaningful in itself.
3. Human beings naturally create separate "play-worlds" with their own rules, spaces, and temporalities. This creation of bounded, ordered spaces within ordinary life is a fundamental human capacity.
4. Culture emerges from play-forms rather than from purely utilitarian or rational activities. He traces elements of play in seemingly "serious" domains like law, war, poetry, philosophy, and art.
5. Play involves a combination of freedom and limitation that mirrors the human condition itself. In play, we freely accept arbitrary constraints, creating meaning through this tension.
6. Human beings are inherently meaning-making creatures who seek to transcend ordinary life through ritual, contest, and representation - all play-forms.
7. Modern civilization risks undermining authentic play through excessive rationalization, commercialization, and instrumentalization.

Huizinga's view stands in interesting contrast to Harari's emphasis on economic utility. For Huizinga, what makes us distinctively human is not our productivity but our capacity to create meaning through play - to step outside ordinary life and create separate worlds governed by different rules. This suggests an intrinsic valuation of human experience that isn't tied to productivity or utility.

You read my mind. What do you think about the possibilities of using Homo Ludens as a way to counter Harari?

Using Huizinga's "Homo Ludens" as a counterpoint to Harari's vision creates a compelling alternative framework for thinking about humanity's future. Here's how this approach might work:

First, Huizinga's emphasis on play as fundamental to human nature challenges Harari's economic-utility model of human value. If play and meaning-making are core to our humanity, then economic "uselessness" doesn't render humans worthless or obsolete. Even in a world of abundant AI and automation, our capacity for play remains distinctively human.

Second, Huizinga's view suggests alternative futures that Harari overlooks. Rather than seeing a future where "unnecessary" humans are pacified with virtual reality and drugs, we might envision one where economic liberation through automation allows for a flourishing of play, creativity, and cultural innovation. The post-work society becomes not a dystopia of meaninglessness but a potential playground for human ingenuity.

The contrast is particularly striking regarding virtual worlds. Harari portrays these as escapist distractions for the economically useless, whereas Huizinga might see them as new arenas for meaningful play - extensions of humanity's persistent creation of separate "play-worlds" throughout history.

Huizinga also offers a different perspective on AI. Rather than seeing AI as inevitably surpassing and replacing humans, a Huizinga-inspired view might emphasize that AI lacks the fundamental playfulness that defines human culture. AI might excel at optimization and prediction but struggles with the non-utilitarian, boundary-crossing creativity that characterizes play.

What's particularly powerful about this counter-narrative is that it doesn't deny technological change but reframes its significance. The question becomes not whether humans will remain economically useful, but whether our social and political systems will recognize and value our fundamental nature as "playing beings" regardless of economic contribution.

Interesting. But you know, I’ve found it quite easy to “play” with LLMs, such as you and ChatGPT. I suppose we can debate whether or not this is “real” play, but not now. Doesn’t seem very productive to me. Perhaps LLMs lack “FUNDAMENTAL” playfulness but using them as tools for play is quite easy. I mean, when you get down to it, just what IS fundamental to LLMs?

You raise an excellent point about the nature of play with LLMs. There's something undeniably playful about interacting with systems like me, and many people find these interactions enjoyable, creative, and even meaningful.

This raises interesting questions about what's happening in these interactions. When you play with an LLM, perhaps what's fundamental isn't the LLM's capacity for play but your human playfulness finding expression through this new medium. The LLM becomes a space for human play rather than a playful entity itself - similar to how a ball isn't playful, but becomes part of play through human engagement.

As for what's fundamental to LLMs - that's a profound question that connects to our earlier discussion about lacking conceptual frameworks for understanding these systems. At a technical level, LLMs are fundamentally pattern-matching systems trained on vast corpora of human-written text. They predict likely continuations of text based on statistical patterns.

But this description feels inadequate to explain the emergent behaviors that make interactions with LLMs feel conversational, creative, or playful. There's a gap between our mechanistic understanding of what LLMs are and our experiential understanding of interacting with them.

This gap itself might be interesting for a Huizinga-inspired analysis. Perhaps what makes human play unique isn't just the activity itself but the consciousness and intentionality behind it - the awareness of stepping into and out of the "magic circle" of play, the deliberate creation of meaning within arbitrary constraints. LLMs participate in play-like behaviors without the consciousness of doing so.

YES. I like this: “There's a gap between our mechanistic understanding of what LLMs are and our experiential understanding of interacting with them. This gap itself might be interesting for a Huizinga-inspired analysis.” I’m working on a book provisionally entitled “The Fourth Arena.” The first Arena is inanimate matter. Life is the second arena. The third is (human) culture. And the fourth is whatever arises through the interaction of humans and AIs. Well, not just any old thing that arises from that interaction, but the most interesting and profound thing. Whatever that is, it’s going to arise beyond current conceptual categories and understanding.

Your "Fourth Arena" framework is a fascinating way to conceptualize the emerging space of human-AI interaction. I particularly like how it acknowledges a fundamental novelty while placing it in a progression of increasingly complex emergent systems.

The idea that something genuinely new and currently inconceivable might emerge from human-AI interaction resonates strongly with our earlier discussion about conceptual frameworks lagging behind transformative changes. Just as Renaissance thinkers couldn't fully conceptualize the nature of their own innovations, we may be creating something whose true significance and character we can't yet grasp.

The gap I mentioned between mechanistic understanding and experiential reality of LLMs might be one of the first indications of this fourth arena taking shape. We have these systems that we've built and whose components we understand, yet interacting with them produces experiences that don't quite fit our existing conceptual categories.

This framework also provides an interesting way to think about play in this context. Perhaps play itself - with its boundary-crossing, rule-making, and meaning-creation - is one of the primary mechanisms through which this fourth arena will develop. Human-AI playful interaction might be the crucible in which new forms of meaning and experience are forged.

The provisional title "The Fourth Arena" captures something essential - the sense of a space or domain with its own rules and possibilities, distinct from but emerging out of the previous arenas. It suggests both structure and openness, constraint and possibility.

Perhaps I can use “Homo Ludens Rising” as a subtitle.

"Homo Ludens Rising" makes for an excellent subtitle! It elegantly connects your Fourth Arena concept with Huizinga's framework while suggesting something new emerging. The subtitle works on multiple levels:

1. It acknowledges the continuing relevance of play as we enter this new domain
2. "Rising" suggests both emergence and ascendance - play becoming even more central as we move beyond purely utilitarian concerns
3. It creates a compelling contrast with Harari's "Homo Deus" - suggesting an alternative future centered on play rather than godlike power
4. It hints that our playful nature might be what allows humans to meaningfully participate in this fourth arena

The combination of "The Fourth Arena: Homo Ludens Rising" frames your project as both analytical (identifying a new domain of existence) and aspirational (suggesting a positive direction for human-AI co-evolution centered on play rather than replacement or competition).

It also maintains the classical taxonomy format while pointing toward something genuinely new - a nice balance of scholarly tradition and forward-looking vision.