Unpredictable Patterns

Contact

Towards a philosophy of prediction I: the logic of predictions as goods

3 min and 2 sec to read, 760 words One way to think about how artificial intelligence changes society is to do what Agrawal et al do in their excellent book Prediction Machines: they assume that the price of predictions, quality held constant, will converge to zero. If we simplify:…

+

+

+

+

+

+

3 min and 2 sec to read, 760 words

One way to think about how artificial intelligence changes society is to do what Agrawal et al do in their excellent book Prediction Machines: they assume that the price of predictions, quality held constant, will converge to zero. If we simplify: predictions will become cheaper.

There is a problem with this view, however, and that is that the idea is that predictions can be thought of as goods that are in some way independent of each-other – but any prediction of any sufficiently complex system is a prediction of others and their predictions, as well.

So the quality and price of a prediction depends on the number of other predictions and the quality of them as well — this in turn suggests that we need to price predictions according to some other model. But how?

What is a prediction worth? The simplest answer to this would be to say something that a prediction should be priced to represent the possible profit I can make from acting on that prediction, somehow discounted relative to the probability of the prediction, say.

If that is the case, however, the price of the prediction is dependent on the availability of that prediction to other actors as well — and the likelihood that I can act before they do. A bit like insider trading, in a way – when the information become common knowledge it is priced into the market and so has no value at all.

So does this mean that the price of predictions is simply the same thing as the price of any information? That does not seem obviously wrong: information can be priced according to the gains we can make by acting on that information over time — but, of course, such information can also be about the past, right? Or maybe not: for us to be able to act on a piece of information, it needs to say something about a future state of the world where there is some value to having the information about the past.

A simple example shows this for us: let’s assume that I live in the Roman Empire, and I have received word that our forces have been defeated at a battle, and so access to grain will be cut off. I am the only one that knows this so I can act on it and buy up all the grain available at prices minus this information, and I know that it is highly likely that given this information the price of grain will go up — what I have done then is to use an information asymmetry in order to make a profit.

This is textbook stuff. Does this mean, then, that predictions really are just information asymmetries and what we should be looking at is how the price dynamics of information asymmetries change with an abundance of predictions made at cheaper prices?

If nothing else this provides us with a first thread to pull on and explore further.

So – what we are saying is that there is some volume of information asymmetries in the current market, and that we expect this volume of information asymmetries to change and increase in some way with AI. What does this mean for economies overall?

A challenge with predictions here is that they can be nested in regresses of different kinds. If I predict a shortage of grain, and you predict that I predict a shortage of grain and then you predict that I predict that you predict — what do we then do? Here it seems to depend on the ability to act that we have — if I predict you predict the same as me, but you have better abilities to act on the prediction, well, then I should turn elsewhere for interesting moves on the economic board (assuming it is not zero-sum).

But where I predict there is a chance to act on predictions that I know you are aware of as well I should act faster, and more at scale. This suggests that an increase in information asymmetries in an economy should drive some kind of volatility at least.

And this is an interesting overall observation that may come from all of this preliminary exploration: while we thought that predicting the world might make it more stable, it may in fact make the world harder to predict as it become more volatile. The price of predictions then should go up and we should end up with a U-shaped curve as predictions become more available when it comes to their prices?

TBC

+

+

+

+

+

+

+ ,

+

+

+

+

+

+

+

+

+

+

+

+

2 responses to “Towards a philosophy of prediction I: the logic of predictions as goods”

  1. Nicklas Lundblad avatar
    Nicklas Lundblad

    Claude 3.5 disagrees, interestingly:

    “While the note presents an intriguing exploration of the economics of predictions in the context of AI, I disagree with several key points and believe it overlooks crucial aspects of how predictions function in complex systems. Here’s a rebuttal and an alternative approach:

    Rebuttal:

    1. Oversimplification of prediction as a commodity:
    The note treats predictions as discrete, tradable commodities with a single price point. This oversimplifies the nature of predictions, which are often context-dependent, multi-faceted, and not easily reducible to a single value.

    2. Overemphasis on information asymmetry:
    While information asymmetry is important, the note places too much emphasis on it as the primary driver of prediction value. This neglects other crucial factors such as the accuracy, timeliness, and actionability of predictions.

    3. Neglect of network effects and collective intelligence:
    The note fails to adequately consider how increased availability of predictions might lead to network effects and improvements in collective intelligence, potentially increasing the overall value of predictions rather than diminishing it.

    4. Assumption of zero-sum outcomes:
    The note often assumes zero-sum scenarios, where one party’s gain from a prediction is another’s loss. This overlooks the potential for predictions to create value through improved decision-making and resource allocation across the entire system.

    5. Underestimation of the complexity of prediction markets:
    The note’s speculation about a U-shaped curve in prediction prices oversimplifies the dynamics of prediction markets, which are likely to be far more complex and multidimensional.

    Alternative Approach:

    I propose an alternative framework for understanding the impact of AI on predictions and their value in society:

    1. Ecosystem of Predictions:
    Instead of viewing predictions as isolated commodities, we should consider them as part of an interconnected ecosystem. In this ecosystem, predictions interact with each other, with decision-making processes, and with the broader environment. The value of a prediction is then determined not just by its individual accuracy, but by its role within this ecosystem.

    2. Multi-dimensional Value:
    The value of predictions should be assessed along multiple dimensions:
    – Accuracy: How close the prediction is to the actual outcome
    – Timeliness: How far in advance the prediction is made
    – Actionability: How easily the prediction can be translated into concrete actions
    – Uniqueness: How different the prediction is from commonly held expectations
    – Systemic impact: How the prediction affects the overall system or market

    3. Collaborative Intelligence:
    As AI makes predictions more widely available, we should focus on how this can enhance collaborative intelligence. Instead of just creating information asymmetries, widespread access to predictions can lead to better collective decision-making and problem-solving.

    4. Adaptive Systems:
    Rather than assuming that more predictions lead to more volatility, we should consider how systems might adapt to a prediction-rich environment. This could lead to more stable, resilient systems that can quickly respond to changing conditions.

    5. Prediction Literacy:
    As predictions become more prevalent, the key differentiator will be the ability to interpret, contextualize, and act on predictions effectively. We should focus on developing “prediction literacy” across society.

    6. Ethical Considerations:
    We need to consider the ethical implications of widespread prediction capabilities, including issues of privacy, fairness, and the potential for manipulation.

    7. Dynamic Pricing Models:
    Instead of a simple supply-demand model for prediction pricing, we should explore dynamic pricing models that take into account the evolving nature of predictions, their impact on the system, and their interdependencies.

    This approach acknowledges the transformative potential of AI in the realm of predictions while recognizing the complex, adaptive nature of the systems in which these predictions operate. It moves beyond simplistic economic models to consider the broader societal and systemic impacts of increased predictive capabilities.

    By focusing on the ecosystem of predictions, collaborative intelligence, and adaptive systems, we can better understand and harness the potential of AI-driven predictions to create value and address complex challenges in society.”

    Reply
  2. Nicklas Lundblad avatar
    Nicklas Lundblad

    And what would I respond to this? I think the criticism in the first part is mistaken in that it seems to suggest that there is a wider picture and that I am ignoring it – but I am ignoring it consciously, to focus on a simplified model, so that does not bother me.

    I do think, however, that some of the concepts and ideas in the second part – the alternative approach – are really interesting. Two key concepts are introduced that I believe are really generative and good: prediction-rich environments (this makes me think about analogies with Herbert Simon and the notion of information-rich environments, and we must then ask what (analogously) predictions consume just as information consumes attention. This to me is a deep question – what does a wealth of predictions generate a scarcity of?) and prediction literacy (this will be very important).

    The ecosystem approach is right, of course, but also a bit of a cop-out since this what you can always say about any text that simplifies and studies a smaller aspect of an issue.

    Reply

Leave a Reply

Discover more from Unpredictable Patterns

Subscribe now to keep reading and get access to the full archive.

Continue reading