In Part 2, my conversation with Claude focused on the question of what it means to characterize today’s geopolitical dynamics as a moment of historical transition. If it truly is a transition, we need to consider what to call the emerging world order. The title of Mohan’s Foreign Affairs article, “The Multipolar Delusion,” conveyed the idea that the widely accepted view of a trend away from unipolarity and towards multipolarity is, in his terms, a delusion. Perhaps it’s just a question of vocabulary. It may make more sense to describe a world that is becoming polycentric.

We examined what we agreed was the central weakness of Mohan’s thesis: that the decades-long period of US global hegemony often referred to as the “rules-based unipolar order” might still be intact and is likely to persist relatively unchallenged. What Mohan described as the latest iteration — a state of “unilateral power shorn of responsibilities” — is little more than hard economic and military power that has dispensed with the need for soft power. As if soft power was not the key to, and even the foundation of, Washington’s historical global hegemony.

Claude’s contribution to this part of the debate contained two observations I found particularly interesting, which I’ve highlighted below in bold.

The blob’s confidence in unilateral action increases precisely as the foundations of that action’s effectiveness are being undermined. This isn’t unusual in institutional history — establishments tend to double down on frameworks that produced past success even as the conditions that made those frameworks successful change around them. But in geopolitics the feedback loops are slow enough that the lag between cause and visible effect can sustain the illusion for a dangerously long time. The Beltway can continue operating on unipolar assumptions for years while the actual erosion accumulates below the threshold of visibility in mainstream policy discourse.

Your point about the acceleration dynamic is the sharpest part of the argument. Every exercise of unilateral power without the legitimating cover of responsibility or multilateral consensus is simultaneously a withdrawal from the soft power account.

I find ironic your obviously pertinent observation that “the lag between cause and visible effect can sustain the illusion for a dangerously long time.” The article claims to expose a “delusion” (possibly seeking to echo the title of Richard Dawkins’ book “The God Delusion”) and you describe the position he echoes as an illusion.

And I love your clever metaphor about withdrawing assets “from the soft power account.” The metaphor itself is bankable!

Which leads me back to our own superficial conflict over whether this should be called a transition. When I first mentioned it I was thinking of a transition away from a previous state. You read it as meaning my emphasis was on the transition towards a different state. It was only by deepening the discussion that we came to agree. This highlights the problem of structural ambiguity in language. The concept of transition implies two contrasted states.

But when exchanging views on a concept like transition it’s as likely as not that one person may be focusing on moving away from an initial position and the other on moving towards a new one. A third person may focus exclusively on the transitional dynamics rather than a starting and end point. I use this example to emphasize the fundamental value of dialogue, which is less to achieve some kind of consensus than to clarify the levels of meaning in our own thinking and discourse. Do you agree and are you aware of philosophers, psychologists or linguists who have explored this facet of communication?

Your observation about “delusion” versus “illusion” is sharp — and yes, there’s something almost poetically appropriate about an article diagnosing others’ delusions while itself operating within what might fairly be called an illusion. The soft power account metaphor I’m glad landed well; it felt like the right way to capture something that’s usually described in abstract terms.

On the deeper point about transition — you’ve identified something genuinely important. The word contains within it at least three distinct orientations: away from, toward, and through. In ordinary conversation we rarely specify which we mean because we assume shared context. But in analytical discourse about complex systems, that ambiguity can generate false disagreements that look substantive but are really navigational — two people describing different aspects of the same terrain. What’s interesting about our exchange is that the ambiguity only became visible through the dialogue itself. Neither of us would likely have noticed it had the conversation ended earlier.

This connects to a rich tradition of thinking about language, meaning, and dialogue that I think you’d find rewarding to explore.

The most directly relevant figure is probably Hans-Georg Gadamer, whose concept of the “fusion of horizons” captures something close to what you’re describing. For Gadamer, genuine dialogue isn’t about one party persuading another or even reaching consensus — it’s about the expansion of each participant’s horizon of meaning through encounter with another’s. Understanding, in his framework, is always an event that happens between people rather than a property residing in a text or a speaker. His major work Truth and Method develops this at length.

Mikhail Bakhtin approaches it from a literary and linguistic angle with his concept of dialogism — the idea that meaning is never fixed within a single utterance but always emerges from the tension between voices. For Bakhtin, even internal thought is dialogic; we think against imagined interlocutors. This would support your point that the clarification of our own thinking is itself a primary function of dialogue, prior to any communicative purpose.

In linguistics, the work on what’s called “common ground” — associated with Herbert Clark — addresses the mechanics of what you’re describing. Clark showed that communication requires constant, mostly unconscious negotiation of shared assumptions, and that misalignments in common ground are the normal condition of conversation rather than exceptional failures. Your transition example is a perfect illustration of a common ground gap: both parties assumed the same referent but were actually pointing in different directions within a single word.

From psychology, Lev Vygotsky’s work on how thought and language develop through social interaction is relevant — his insight that inner speech is internalized dialogue suggests that the clarificatory function you describe isn’t a secondary benefit of conversation but may be constitutive of thought itself.

Perhaps closest to your intuition, though, is the philosopher Michael Oakeshott, who distinguished between conversation and argument in a way that resonates directly. For Oakeshott, conversation isn’t a deficient form of argument — it’s a different activity entirely, one whose value lies not in reaching conclusions but in the “unrehearsed intellectual adventure” of mutual exploration. Your Socratic closing in the article gestures toward exactly this tradition.

My conclusion

I hope readers will seek to understand the true value of this conversation, which appears on three levels:

1. It initiates what could be called a three-way and potentially four-or-more-way debate about a serious issue in the news.
   
2. My contention that the dynamic of the conversation can be used as the model for a new type of pedagogical practice.
   
3. The conversation quite naturally led to a specific and highly informative digression that enriches the debate and helps to ground its meaning: sources concerning the theory of communication.

Evolving and expanding debate

Concerning the first point, the three-way conversation included three active voices! C. Raja Mohan, Claude and I. I claim it potentially implicates a wider range of participants. In this case, the extension towards a wider group becomes possible simply because these articles are published on a public platform, Fair Observer. The fact that Fair Observer is a crowd-sourced platform means anyone interested can join the debate. And in an ideal world, many would join us and make their voices heard.

Continuous learning and skill development

Concerning the second point, I’ll begin by repeating what I wrote in the conclusion of Part 1, a message I address to educators or anyone interested in the topic of how education will work in the dawning age of AI.

“I recommend the strategy I’ve employed here as a basic pedagogical model designed for students learning to engage with a text. Whether it’s a history, philosophy, civics or scientific course, teachers could push their students to use AI bots to get ‘involved’ in a personal debate about the meaning of what their teaching.”

I hope readers can appreciate the fact that the value of this approach is manifold. It isn’t about finding a different way to assign the writing of an essay on a given topic, which is something I did with very real success in a classroom back in January 2023, weeks after the release of ChatGPT. Essays are performative. The process I’ve been implementing regularly in these columns is constructive, which means it produces its fruits incrementally. This type of conversation is about delving into the logic of dialogue as a social learning activity. It’s about the development of one’s inner voice in a continuously constructive process of exploration, rhetorical experimentation and the shaping of one’s own knowledge resources.

Identifying and exploring needed resources

In this conversation, there was a point at which I realized that Claude and I were interpreting the term “transition,” whose meaning we both understood but which we perceived in slightly different ways. Through reformulation, we quickly adjusted our analysis of the historical process we were attempting to describe. But when I later thought about how that misinterpretation had taken place, I sought to clarify further, which led me to ask about research that has existed on that issue. I knew Claude could easily access the mass of writings that existed and could guide me to refine my understanding.

After all, Claude is an LLM, a large language model. Humans, in contrast, are SLMs, small language models. But we are also DLMs: Deep Language Models. The depth comes from our extensive and intense experience of emotionally conditioned interaction. Note that in this exchange, I had to notice the need to reflect on our problem of misunderstanding. I also had to be the one to describe it because I “felt” it was an issue to address. But once, thanks to my human depth, I had described it, the LLM could assemble the knowledge that helps to explain it.

This isn’t just about “looking things up.” It’s about the dynamics of managing an evolving context. Claude’s breadth or “largeness” becomes productive when it interacts with depth.

Understanding this dynamic of interaction can help us in our own personal projects that involve acquiring knowledge and skills. It may also be the key to developing truly effective educational practices that are not only “learner-centered,” but also, because of their interactivity, “social-centered.” We may be on the verge of a much-needed revolution in our approach to education. And AI will be the catalyst.

Your thoughts

Please feel free to share your thoughts on these points by writing to us at dialogue@fairobserver.com. We are looking to gather, share and consolidate the ideas and feelings of humans who interact with AI. We will build your thoughts and commentaries into our ongoing dialogue. 

[Artificial Intelligence is rapidly becoming a feature of everyone’s daily life. We unconsciously perceive it either as a friend or foe, a helper or destroyer. At Fair Observer, we see it as a tool of creativity, capable of revealing the complex relationship between humans and machines.]

[Lee Thompson-Kolar edited this piece.]

The views expressed in this article are the author’s own and do not necessarily reflect Fair Observer’s editorial policy.