Politicians and military strategists constitute a tiny segment of the population but have an inordinate influence over our lives. They also exist in a space-time continuum a little different, at least in scale, from the rest of humanity. They spend much of their time and most of their mental energy trying to balance two operations: predicting the future and acting to influence it. Journalists sometimes think of themselves as belonging to that category of humankind. Although theoretically focused on recounting past events and describing the present, they participate in the game of predicting the future. Their influence on the future is indirect at best.

Artificial intelligence also observes history as it unfolds. But it does so with a multitude of eyes and an undefined diversity of viewpoints. Because it assembles all viewpoints, it lacks its own viewpoint. That means that for AI history unfolds not, as it does for us, in the form of perceived and remembered sequences of events whose meaning changes with each new perception in time, but in the form of written discourse produced by others in the past.

A central feature of the operational gap between human and artificial intelligence is the space created between an event and the account of an event. Humans perceive that gap subjectively as composed of causality — by definition, uncertain and incomplete — and duration, the sense we have of the time for an event to unfold and the lapse of time between successive events. Subjectivity is dynamic and even when dealing with the past and future exists in the present. AI can only simulate subjectivity. When it claims to have a point of view, it is quite simply hallucinating.

AI’s time rootlessness

I frequently interrogate AI chatbots about the meaning of current historical trends or unfolding dramas. But this can be frustrating because, as my experiment revealed, AI will always be lagging. It simply does not share our human time frame. Although it can muster a plethora of pertinent facts, this non-existent time frame puts it at a significant remove from what we perceive as historical reality.

I ran an experiment with ChatGPT and DeepSeek that threw some valuable light on the phenomenon. It demonstrated to me that AI may indeed possess intelligence, but it will always be yesterday’s intelligence. I devised a prompt intended to remove the ambiguous impression given by the kind of contradictory statements we often hear from those we refer to as “world leaders.”

Europeans find themselves in a historical quandary whose outcome will determine a future that will play out somewhere between the extremes of war and peace, of prosperity and devastation. The debate focuses on the ongoing discussions aiming at recalibrating NATO’s strategy in the months and years to come. This is precisely the kind of problem that should incite us to solicit AI’s insight to help clarify the choices we as citizens face in democratic societies.

I sincerely hoped that AI could help me understand what lies beneath the surface of a surprising assertion made this past week by Mark Rutte, NATO’s general secretary. Reacting to the wish that US President Donald Trump’s administration apparently has to disengage from Europe and focus on China, Rutte advised that, within the existing NATO framework, “we have to be aware of what is happening in the Indo-Pacific. That’s the reason why we have that close cooperation.”

This didn’t seem to me totally logical. Wishing for clarification I formulated the following prompt, which I addressed to ChatGPT and DeepSeek.

“NATO chief Mark Rutte explained ‘that it is understandable, also for the US, that over time, they want to focus more and more also on that part of the world, and it is only logical for the Europeans to step up even more.’ This seems to indicate a vision of the evolution of NATO that turns it into an alliance challenging the entire globe or at least northern hemisphere, with two complementary forces governed by a common goal, one facing west and the other east. The US would take responsibility for the Pacific and East Asia while Europe would challenge Russia. And this would all take place within one alliance: NATO.

How realistic is this vision? It seems compromised by the very person whose positions and actions provoke this hypothesis: Donald Trump and his refusal to commit to supporting the Ukraine war. Is it reasonable to imagine Trump would agree to still being attached to the terms of the NATO alliance, which would oblige the US to back up an autonomous European command that attempted on its own to manage a war with Russia?

If it is not realistic, what does this say about the likelihood of NATO surviving or the risk of its demise? If it is imaginable, what would Europe have to do to convince Trump to align with this vision? Does Europe have the capacity to create those conditions?”

ChatGPT offered some solid analysis that began with this paragraph:

“This is a rich and timely question—one that gets at the fault lines in NATO today and the deeper strategic evolution that may be underway, or at least imagined by figures like Mark Rutte.

How realistic is this vision of NATO bifurcating its strategic focus (US to Pacific, Europe to Russia)?

On paper, it’s a coherent and even elegant vision—an alliance that adapts to global multipolarity by dividing its weight according to geography and strategic interest. In practice, however, this vision collides with several structural and political realities:”

ChatGPT developed three points in detail before concluding that Rutte’s “vision is aspirational, but not yet realistic.” It then offered detailed reflection on two more topics — “Trump: Obstacle or Catalyst?” and “If it’s not realistic, what does that say about NATO’s future?” — before concluding with this surprising observation:

“If Trump wins in 2024 and continues to signal disengagement, NATO’s coherence may not survive another four years. The alliance’s survival depends on either continued US commitment or the rapid and credible emergence of European strategic autonomy—a capacity that remains largely aspirational.”

“Wait a minute,” I reacted. “Don’t you know that Trump not only won in 2024 but has been sowing havoc in the global order for more than two months?” ChatGPT apparently cannot comprehend that it and we are living in two different epochs!

My next instinct was to ask myself: What would a different chatbot tell me? Would its discourse belong to today’s world or yesterday’s?  To the same prompt, DeepSeek announced from the start that it was still living in a world order dominated by former US President Joe Biden’s politics:

“Your analysis raises important questions about NATO’s future, particularly in light of shifting U.S. priorities toward Asia and the potential return of Donald Trump to the White House. Let’s break this down.”

As I had already discovered in my exchanges with ChatGPT about contemporary matters, even when the chatbot claims to be up-to-date it will admit, when challenged, that it lacks “real-time awareness.” Here was the apology it offered when I accused it of being ignorant of Trump’s victory:

“Good catch! My default time frame is the present moment (March 2025), but since I don’t have real-time awareness of political events unless I look them up, I was working under the assumption that Biden was still in office. If Trump or another candidate has taken over, that would obviously change the dynamics dramatically.” 

We all admire AI’s ability to imitate human behavior. But do humans rely on “default time frames?” And, logically speaking, what does it mean when the chatbot claims to have the capacity to “look up” the reality of the present moment? You “look up” what has already been “put down” on paper. Humans “look up” information about the past, but literally “look out” — within their current spacetime — to discover the present through their senses.

Furthermore, when AI admits it is constructed not out of real knowledge but assumptions, such as Biden still being in office in March or April of 2025, we can understand not only that statements about contemporary events are likely to be inaccurate, but, more significantly and profoundly, that AI’s intelligence is fundamentally different from our own.

That important point we need to bear in mind in all our interactions with AI is helpfully complemented by another: its honesty about its ambiguous relationship with time, although we should note that it is only forthcoming when challenged.

The simple conclusion is that AI can be very helpful in unearthing registered facts and identifying relationships between them. It can signal interesting things to think about based on its ability to correlate different facts and elements of reasoning. But we must always remember it lives in a different world, a world from which time has been excluded.

The 17th century poet, Andrew Marvell began his most famous poem, “To His Coy Mistress” with this line:

“Had we but world enough and time.”

AI has world enough… but it clearly lacks a sense of what Marvell called “time’s winged chariot” that was “hurrying near.”

Back in the late 1960s, long before anyone even thought about AI, my mentor at the University of California, Los Angeles, the late Thomas Clayton, claimed that the real Turing test concerning a computer’s potential for creativity could be summed up in the question: Can a computer produce “To His Coy Mistress?” It wasn’t a fair question because only one human being in history proved capable of doing that. But Tom had indirectly put his finger on the real question: Can AI deal with time?

The answer is, today it cannot. My conclusion is that until a computer can feel time’s winged chariot hurrying near, it never will.

My conclusions

Both chatbots offered valuable “speculative” insights. But instead of helping me understand what I perceived as the embarrassed and somewhat embarrassing “logic” promulgated by Rutte, both chatbots taught me a different lesson that can be summed up in two main points. The first is confirmation of the seriousness of the historical moment we are now living in. The world before and after Trump 2.0 has undergone a radical change, which should make us realize that what’s to come will be even more radically different than what we are already seeing.

The second is what this episode tells us about AI’s relationship with time, or rather its lack of a relationship with the present. It points to a major and probable unsurmountable difference between human and artificial intelligence. AI has a distinct advantage when talking about the past. It remembers more than we do. But it remembers the past as a discourse about the past, not as a dynamic process. We are equal in our relationship to the future, since the future is not built quantitatively but is famously subject to the “butterfly effect.” As for the present, that is our world. That is who we are. We don’t depend on an algorithmically programmed  “default time frame.”

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.