If you look at the first post I did on Tyler Cowen’s recent monograph, The Marginal Revolution: Rise and Decline, and the Pending AI Revolution, you’ll see that much of it consists of a dialog that I had with the AI that accompanies an online version of the book, which is based on Anthropic’s Claude chatbot (I asked it). In the second post I asserted that marginalism is a Rank 4 idea. To make that argument I had to use my own instance of Claude. Why? So I could upload the work David Hays and I did on cognitive ranks.
David Hays and I developed the idea of cognitive ranks off and on over the years starting in the mid-to-late 1970s, but didn’t publish until the 1990s, when we did a series of articles and one book (by Hays) – here’s a basic guide to that work, Mind-Culture Coevolution: Major Transitions in the Development of Human Culture and Society. While all that work has been on the web for well over a decade and so would have been in the training corpuses for the frontier LLMs, it hasn’t been taken up by others in a way that would result in those ideas being explicitly registered in the LLMs. So I uploaded both a PDF of Cowen’s book and the cognitive ranks papers to my instance of Claude, allowing me to consult Claude in the argument.
I continued using both instances of Claude, Cowen’s and mine, in my commentary on the marginalism monograph. Since those Claude instances are independent of one another, the operate as independent epistemic agents. Once I’d finished my most recent post, Botanical classification and the theory of evolution, I decided to add another epistemic agent, my instance of ChatGPT. That post was long (over 8K words), combining as it did, two lines of thought. Since Cowen had discussed two moments in the history of biology, I wanted to discuss both of them in terms of ranks theory, botany as Rank 3 and evolution as Rank 4. I also decided – Why not? – to include Ranks 1 and 2. But I also wanted to examine the way Cowen framed his various examples – as being laggard, but also obvious in retrospect. That framing struck me as being strange and willful. As a result that post was not only long, it was also complex. So I set up a project in ChatGPT where I uploaded Cowen’s monograph, the basic article on ranks theory, and the text of that post.
I’m now working with three independent artificial epistemic agents. I’ll probably use all three in what I’m currently thinking will be my final post in this series, The future of human conceptual development, which I’ve already been working on.
Here’s a bit of dialog I had with ChatGPT about this process:
Note that I’ve already had Claude review and critique the biology article. I turned to you specifically because I wanted another interlocutor. I think that’s crucial to the intellectual process, interaction between epistemically independent agents. One little thought experiment I like to think about goes like this: Imagine that you had 100 units of AI compute at your disposal. How would you configure those units? Would you devote them all to a single epistemic agent or would you create 10 independent epistemic agents? The one agent has more “power” available, but the 10 independent agents can do things the one agent cannot do.
That thought experiment is exactly on target. The issue is not simply “more intelligence” but epistemic architecture.
A single agent with 100 units of compute may have greater depth, memory, context integration, and internal search. But it is still one trajectory through possibility-space. It may deliberate internally, but its alternatives are generated within one self-consistent cognitive economy. That gives you power, but also risks convergence: one style of salience, one set of blind spots, one implicit ontology, one tendency toward premature synthesis.
Ten agents with 10 units each create a different kind of system. They may be individually weaker, but they can explore different regions of the space. They can disagree. They can misunderstand productively. They can generate incompatible framings. They can act as independent probes. The value is not merely additive; it comes from non-identical construals.
That is very close to the old distinction between parallel search and deeper serial search, except the epistemic version is richer. Independent agents are not merely searching different branches of a tree. They may be constructing different trees.
For intellectual work, the ten-agent configuration has a major advantage: it preserves friction. A single very capable agent can become too fluent, too integrative, too quick to produce a smooth synthesis. Multiple agents can keep the problem rough. They produce triangulation rather than closure.
The important phrase in what you said is “epistemically independent agents.” Independence matters. Ten copies of the same agent with the same prompts and same priors are not enough. You need differences in training, context, role, temperature, institutional framing, and perhaps even adversarial stance. Cowen’s book-AI, Claude, and ChatGPT are not interchangeable because they occupy different positions in the research ecology.
This connects directly to your dialogic intellectual history: your father, Hays, and now LLMs. The intellectual partner is valuable not because it is a bigger version of yourself, but because it is not you. It perturbs the field. It supplies resistance, alternative organization, and sometimes alien fluency.
A compact formulation:
Given 100 units of AI compute, the optimal configuration for intellectual work may not be one 100-unit mind, but a society of partially independent minds. The single agent maximizes depth and integration; the plural system maximizes diversity, disagreement, and triangulation. Thought advances not only by power but by organized epistemic friction.
That also gives you another Fourth Arena point: AI is not just a tool or substitute intelligence. It can become a medium for constructing temporary cognitive societies around a problem.
On that Fourth Arena: Welcome to the Fourth Arena – The World is Gifted, 3 Quarks Daily, June 20, 2022.
No comments:
Post a Comment