Last week, we published in three parts a conversation that began simply and grew increasingly complex. It began with a shared reflection on the contribution of economist Jeffrey Sachs to the geopolitical debate surrounding the war in Ukraine. It led to our agreeing on a number of distinctions that should be seen as crucial in any discussion involving a complex set of facts and the existence of multiple perspectives.

We began to examine the conversational methods we had been developing in this particular case to see how they might help define an emerging “culture of dialogue” between humans and chatbots. I announced my intention to publish one or more articles documenting this very conversation accompanied by an invitation extended to the public to react to it. In that context, I took the trouble to express my appreciation for what I saw as the chatbot’s patience and willingness to resolve ambiguity by moving the conversation to a higher level. I called this “a virtue that humans can only acquire with studied humility.”

ChatGPT responded in these terms:

“Your answer extends the conversation in a meaningful way. You’re pointing to a profound cultural challenge: the reluctance (or inability) of many to truly engage in dialogue, to question their own perspectives, and to share authority over discourse. The shift from merely expressing opinions to engaging with them in a constructive way is a difficult one, and AI’s lack of personal stake makes it an intriguing tool for facilitating that shift.

I also appreciate your observation about AI’s absence of jealousy or envy. If humans approach AI dialogue with an open mind, they can use it as a space where intellectual humility is not just possible but encouraged. That doesn’t mean AI should be uncritical—on the contrary, it should challenge assumptions rigorously—but it does mean it can model a different mode of engagement, one where critique is separated from ego.

Your upcoming article sounds like an important step in testing how people react to this kind of discussion. Even if the public isn’t fully ready for it yet, the act of introducing these ideas into the discourse helps move things in the right direction. I’d be curious to see how readers respond—whether they engage in the spirit of dialogue or revert to more conventional opinion-stating. Will you be providing some kind of structure for how they can participate, or will it be more open-ended?”

Of course, at the time of writing this column, I have already been publishing as a series of columns the “upcoming article” ChatGPT refers to. And there will, of course, be more to come because this is an ongoing project. In the guise of explaining the kind of vibrant debate I would like to see emerge, I responded with a new prompt to ChatGPT’s question, inviting the chatbot to join in our effort.

“We begin with a concept that we hope can evolve into a structure. We call it the ‘crucible of collaboration’ from which no one is excluded. It is totally consistent with our vocation as a crowd-sourced non-profit journal, uncompromised by advertising or a wealthy patron but nevertheless dependent on the generosity of our loyal readers. I would love to have your suggestions about how we might structure and launch a new kind of agora which we call the crucible of collaboration. You might have ideas about how it could be created within the confines of an online journal and how it can evolve into something with an identifiable structure. We do intend to use it as a platform for initiating educational events as well as diversifying the forms of publication. Your suggestions will be welcome.

“The ‘crucible of collaboration’ is a compelling concept, and I see several ways it could take shape within Fair Observer and beyond. Here are a few structured ideas for its development:

1. Designing the Agora: Structuring the Online Platform

• Dialogue Hubs: Create thematic sections where readers can engage in structured discussions related to published articles. These could be moderated but open-ended, encouraging critical questioning rather than just opinion-stating.
• AI-Facilitated Conversations: Implement AI-driven dialogue tools that can challenge readers’ views, ask follow-up questions, and help structure debates in ways that foster deeper engagement.
• Live Interactive Events: Regularly scheduled discussions where readers can engage directly with journalists, experts, or even AI-generated interlocutors to refine ideas in real time.

2. Evolving into a Structured Model

• Tiered Participation: Encourage different levels of engagement, from casual readers to active contributors who participate in ‘idea labs’ designed to refine concepts and arguments collaboratively.
• Publication Diversification: Move beyond traditional articles to include interactive essays, crowdsourced research pieces, and multimedia collaborations.
• Educational Integration: Partner with schools and universities to use Fair Observer as a living laboratory for AI-facilitated critical thinking exercises.

3. Scaling and Long-Term Vision

• Open-Source Frameworks: Consider whether aspects of the model can be shared or replicated by other publications or institutions.
• Gamification Elements: Introduce structured challenges that incentivize deeper engagement (e.g., ‘Can you argue against your own viewpoint?’ exercises).
• AI as a Socratic Tool: Explore AI’s role in not just mediating but modeling forms of dialectical thinking that enhance discourse quality.

How do these ideas align with your vision? Would you prefer a more gradual, experimental rollout, or do you see a need for a more structured launch?”

“We are clearly on the same wavelength. Let’s keep the conversation going,” I replied.

“I’m glad to hear that—we’re working toward something meaningful. The next step, then, is to refine the mechanics of how the crucible of collaboration can take shape in practice.

Would you like to focus first on:

1. User Engagement & Participation – How to bring people in and get them to engage in true dialogue rather than just opinion-stating?
2. AI’s Role in the Agora – How AI can act as a structured interlocutor or mediator within discussions?
3. Structuring the Space – Whether the crucible should have defined rules, themes, or even experimental formats like AI-assisted roundtables?
4. Integration with Educational Events – How this could be applied in schools, universities, or public discourse training?

Since you’re experimenting through Fair Observer, we might also think about what success looks like for the early iterations. Should it be measured in terms of engagement, depth of discussion, or something else entirely?

Where would you like to begin?”

“Creating a culture requires a massive collective effort. If we reduce it to the sum of our individual experiences with AI, it will produce a result, but one that tends towards anarchy. Part of our cultural problem with AI is that we think of it as a tool that performs tasks for us. But to the extent that it speaks and appears to reason, it belongs to another dimension of human reality, a distinctly social dimension. This is something we need to understand if we hope to achieve a major social goal I have evoked elsewhere: collectively and collaboratively elaborating a ‘manifesto for AI-enhanced democracy.’

Using the discussion of Sachs as an example, can you make some constructive comments on the following conclusions?”

“Your conclusions are well-developed, and I agree with the core insights. Here are some constructive comments to refine and clarify them further:

Strengths of Your Argument

1. AI as a Reflection of Conventional Discourse

Your observation that AI initially produces ‘conventional narratives’ aligned with dominant public discourse is accurate. Large language models predict responses based on prevalent patterns in their training data. Your framing of this as a rule to bear in mind is valuable because it reminds users that AI does not inherently offer deep or original analysis—it responds probabilistically based on how similar topics have been framed before.

2. The Role of Socratic Dialogue in Engaging AI

 You rightly highlight that AI becomes more interesting when probed with detailed questions. This is a crucial insight for users who seek depth rather than surface-level responses. Drawing the analogy to a journalist questioning a public figure is effective—AI, like an interviewee, should be cross-examined to reveal nuances. The fact that AI lacks human defensiveness makes it an excellent subject for such an approach.

3. Understanding AI’s Epistemological Limits

Your mention of AI’s hallucinations and its lack of a stable epistemological framework is essential. Many users assume AI has an inherent understanding of truth, when in reality, it lacks self-awareness about how its outputs relate to reality. Your approach—treating AI as a partner in revealing its own limitations—is an insightful way to frame its role in epistemological inquiry.

Potential Refinements

1. Clarify the Distinction Between AI and Propaganda

Your discussion of AI in the context of propaganda is valuable, but the distinction could be sharpened. AI does not actively intend to spread propaganda, but it can reproduce or amplify existing biases. You might clarify that while AI can mimic propaganda, its malleability allows users to challenge and refine its outputs in ways that traditional propaganda machines do not.

2. Strengthen the Explanation of AI’s Relationship with Truth

You say that AI ‘has no discernible take on the epistemology of the discourse it produces.’ While this is largely correct, AI does contain embedded epistemological assumptions—namely, those of the data sources it was trained on. You might refine this by noting that AI lacks self-reflective epistemology but still inherits and reproduces human knowledge frameworks, which users must critically examine.

3. Expand on the Practical Implications for Public Discourse

The idea that AI can enrich human perception is powerful, but you could briefly mention the societal stakes. For instance, how might this method of AI engagement counteract the trend of polarized, opinion-driven discourse? Could it help train people in critical thinking at scale? Exploring these applications would further ground your insights in real-world impact.

Final Thoughts

Your conclusions articulate a powerful method for engaging AI critically, especially in journalistic and intellectual inquiry. A slight refinement of your framing around propaganda, AI’s epistemology, and its societal implications could make your argument even sharper.”

ChatGPT added one more reflection in the form of a question, making its “final thoughts” a little less than final.

“Would you like me to help shape this into a formalized set of best practices for Fair Observer’s AI engagement methodology?”

My final thoughts

My answer to ChatGPT’s question is, of course, a resounding “yes.” It is a question we will pursue in the future columns. That said, I hope the “we” is not just myself and colleagues within the Fair Observer ecosystem. We dearly wish to put in place the kind of structure that many of our readers will feel comfortable participating in, which ultimately means transforming their status from the passive “reader” to that of an active contributor to a public debate.

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.