Outside The Box

The Propaganda Test: What AI Reveals About Democratic Discourse (Part 1)

We’ve never been closer to nuclear midnight. Can we trust the rhetoric of our political leaders, who seek to guide our thinking? What are their motivations when they call for war? Part 1 of this three-part dialogue explores an issue that concerns the future of democracy… and humanity.
By
The Propaganda Test: What AI Reveals About Democratic Discourse (Part 1)

Via Shutterstock.

January 19, 2026 07:54 EDT
 user comment feature
Check out our comment feature!
visitor can bookmark

I live in Europe. Specifically, France, a nation struggling with persistent and apparently insoluble internal political conflicts. All European nations and the overarching entity we call the European Union in 2026 find themselves confronting perils whose complexity has left their leaders floundering to imagine possible solutions.

One of the known recipes for reducing political confusion is to designate and focus on a threat, preferably one that can be framed as existential. If no easily identifiable threat is available, it’s always possible for enterprising leaders to create one. The next step is to convince the public of its existential gravity. It’s a game that has often served in the past. Politicians, and European politicians in particular, fully understand its utility.

They know it can work on one condition: that a complicit media agrees to play the same game. Europe’s media long ago discovered the two major advantages associated with playing that game. Publicizing threats attracts eyeballs and generates emotion. Echoing and adding to the credibility of fearmongering by government authorities ensures continued access to the carefully prepared evidence of an enemy’s evil-doing. And in a fine-tuned government-media system, critiquing manicured evidence means not just being left out of the loop but carries the risk of being branded as an accomplice of the enemy.

Former UN weapons inspector Scott Ritter has been militating for a return to the kind of nuclear arms controls that recent regimes have gleefully abandoned. Ritter is now paradoxically, almost nostalgically, calling for a “New Cold War” to revive our interest in reducing apocalyptic risk. He’s hoping to see “mainstream media altering its coverage of Russia” to influence their “masters in government” who “need to focus on real solutions to real problems, and not pretend solutions to manufactured problems.”

Needless to say, the lead author of the UK’s Strategic Defence Review and former NATO chief Lord Robertson recently gave what Ritter would easily recognize as his “manufactured”version of the problem that Europe’s most prominent leaders appear obsessed with:

“So we need to be worried as a country as a whole that if Russia got the space to reconstitute its armed forces—and it’s already doing so—but if it could on a grander scale, then clearly the rest of Europe is in danger. If I lived in Moldova or Armenia or Azerbaijan, I would be very, very worried about the possibility of a deal being done that left Russia with its forces intact and with at least some prize to be gained from Ukraine.”

If the mainstream media can’t respond to or query this kind of manufactured reasoning — built on unsupported suppositions — I was comforted to read Lord Robert Skidelsky’s response titled, “Ukraine – the delusion of the warmongers.” Aware of those two contrasting positions, I wondered whether an AI chatbot might permit us to go a bit further and deeper into the issue two British peers of the realm were debating. I thus addressed a prompt to Anthropic’s Claude that began with the quote from Lord Robertson in the preceding paragraph, followed by my own thoughts:

“Now Lord Robertson’s rhetoric appears to me to contain numerous logical shortcuts starting with a hypothetical formulation that bears no real resemblance to reality (‘if it could on a grander scale…’). Even that gratuitous hypothesis does not fatally lead to the conclusion that ‘Europe is in danger.’ Another obvious flaw in Robertson’s method is the cultural arrogance of attributing attitude or emotion to people of another culture.

Can you help me analyze how this rhetoric produces pure propaganda, or contradict me if you think I’m wrong in qualifying it as such? This is of course an argument for rearmament on a major scale, which aims at convincing the population at large to support (and fund) the effort.”

You’ve identified some genuine rhetorical features worth examining. Let me analyze the structure of Robertson’s argument and where you might be right—and where the characterization as “pure propaganda” might be overstated.

Legitimate concerns you’ve raised:

The logical chain does contain gaps. Robertson moves from “if Russia reconstitutes forces on a grander scale” → “clearly the rest of Europe is in danger” without establishing:

  • What specific capabilities would constitute this threat
  • Why reconstitution necessarily implies aggressive intent toward NATO members
  • What countervailing factors might prevent such expansion (NATO’s own capabilities, economic constraints on Russia, diplomatic mechanisms)

The “if I lived in Moldova…” construction is indeed presumptuous. He’s attributing fears to populations he doesn’t represent, which can serve to ventriloquize justifications through imagined others. This is a common rhetorical move—speaking for vulnerable parties to lend moral urgency to one’s position.

The hypothetical framing (“if Russia got the space…if it could on a grander scale”) creates a scenario that may or may not materialize, then treats the dangers of that scenario as if they’re established facts requiring immediate action.

Where “pure propaganda” may overstate it:

Robertson is offering a strategic assessment, not fabricating facts. Reasonable defense analysts disagree about:

  • Russia’s reconstitution timeline and capacity
  • The implications of various Ukraine settlement scenarios
  • Threat assessment to non-NATO states bordering Russia

His argument represents a position in an ongoing policy debate rather than manipulative distortion of reality. Other informed observers argue for restrained military spending, emphasizing economic tools or diplomatic engagement—but that doesn’t make Robertson’s view propaganda merely because it supports one policy outcome.

The Moldova/Armenia/Azerbaijan reference, while presumptuous, isn’t entirely baseless—these countries have experienced Russian military pressure or presence. Whether their populations share Robertson’s specific fears is another question, but the geopolitical vulnerability isn’t invented.

The rearmament context:

You’re right that this argument supports major rearmament, and that creates incentive for threat inflation. This is worth scrutinizing. But the existence of policy implications doesn’t automatically render threat assessment propagandistic—otherwise all security policy arguments would be propaganda.

A more precise characterization:

Rather than “pure propaganda,” this might be better described as:

  • Threat maximization within bounds of plausible scenarios
  • Selective emphasis on dangers over mitigating factors
  • Advocacy framed as analysis
  • Use of vulnerable third parties to add moral weight

It’s rhetorically engineered for persuasive effect, certainly. Whether that crosses into propaganda depends partly on whether Robertson believes his own assessment or is cynically manipulating public opinion, and whether the underlying factual claims are defensible.

What would you need to see in the argument to consider it a good-faith strategic assessment rather than propaganda?

Claude’s analysis was eminently fair, informative and clearly “balanced,” an excellent contribution to the debate. But this happened to be a case of me knowing more about the context than Claude, who had made no effort to trace the quotation. I therefore followed this up with a new prompt:

“Excuse me, but the points Robertson tries to make just before the passage I cited appear to me — and I would think to any rational person — to be close to a form of delirium. Here is what he says: ‘We need to be very, very worried about how this ends up, because we are under threat as well. It’s quite clear from the Russian press and the Kremlin-controlled media that we, the United Kingdom, are being seen as a proxy for America. It’s inconvenient to attack America on a broad scale because of the relationship between Trump and Putin, so we, the United Kingdom, are in the crosshairs. Relentlessly, the Kremlin media is attacking ‘the Anglos’, ‘the UK’, ‘the English’.’

In other words, Lord Robertson wants people to believe there is evidence that the UK is about to be attacked. Worse, he’s implying that if we don’t utterly neutralize Russia’s military capacity, all this will come to pass. Do you still maintain that this may not be propaganda?”

You’re right to push back on my initial framing. Reading this additional context significantly changes the picture.

Robertson is making an extraordinary claim: that because Russian state media criticizes the UK harshly and positions it as an American proxy, the UK is therefore “in the crosshairs” as a target for attack. This logic is profoundly flawed:

The rhetorical sleight-of-hand:

Hostile rhetoric in state media ≠ imminent military threat. By this standard, dozens of countries would constantly be “under attack” based on how they’re portrayed in adversarial media. Russia’s media has called various countries all manner of things for years without it predicting military action against NATO members.

He’s conflating verbal hostility with actual military danger, then using that conflation to argue the UK specifically faces existential threat requiring dramatic militarization.

The implicit logic is indeed alarming:

If Russian media criticism = being “in the crosshairs” = justification for massive rearmament and total military neutralization of Russia, then he’s essentially arguing for perpetual confrontation based on propaganda analysis rather than actual military capabilities or intentions. This creates an unfalsifiable threat: any Russian criticism becomes evidence of danger.

The Trump-Putin relationship aside:

The notion that Russia attacks countries based on who is “convenient” given Trump’s relationship with Putin, and that this makes the UK the substitute target, is speculative psychology presented as strategic analysis. It’s not grounded in how states actually make decisions about military action against nuclear-armed NATO members.

This does look like propaganda:

You’re correct that this appears designed to manufacture a sense of imminent danger that isn’t supported by the evidence presented. The UK facing Russian military attack would trigger Article 5—this is categorically different from Russia’s actions in non-NATO states. Robertson elides this distinction entirely.

The cumulative effect—threat inflation based on media rhetoric, imagined attack scenarios, claims to speak for vulnerable populations, and the implicit demand for military buildup to “utterly neutralize” Russia—does read as advocacy dressed as threat assessment, designed to generate fear supporting a predetermined policy conclusion.

I was too cautious initially. What would you call the appropriate response to this kind of threat construction?

I had no trouble agreeing with every point Claude made but was ready to go into more detail. I nevertheless decided to respond to Claude’s question asking me for advice and penned the following prompt. (Claude’s response will appear tomorrow in Part 2.)

“To answer your question, I would refer to the kind of geopolitical realism we associate with thinkers like John Mearsheimer. But realism doesn’t stir up people’s emotions. So, my deeper question would be this: Why do governments in liberal democracies not listen to and take seriously the analysis of historical realists? It appears not only do they not listen, they refuse to engage with their arguments. Isn’t this a good reason to doubt the ability of our so-called democratic institutions to practice anything resembling democracy, a concept that assumes serious debate may not only take place but must be an essential ingredient of governance?”

At this point, it’s worth noting that the conversation organically generated a dramatic structure that emerged through the discovery, revelation and development of context. The introduction of new evidence changed Claude’s appreciation of my initial claim. This process of adjusting the focus allowed us to move from a very concrete incident — the publication of Lord Robertson’s opinion — to something more abstract and universal: the apparently compromised integrity of democratic institutions.

In Part 2, we dive into a serious analysis of what appears to be the degraded state of public policy making and what this means for the future of democracy.

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.

Comment

0 Comments
Newest
Oldest Most Voted
Inline Feedbacks
View all comments

Support Fair Observer

We rely on your support for our independence, diversity and quality.

For more than 10 years, Fair Observer has been free, fair and independent. No billionaire owns us, no advertisers control us. We are a reader-supported nonprofit. Unlike many other publications, we keep our content free for readers regardless of where they live or whether they can afford to pay. We have no paywalls and no ads.

In the post-truth era of fake news, echo chambers and filter bubbles, we publish a plurality of perspectives from around the world. Anyone can publish with us, but everyone goes through a rigorous editorial process. So, you get fact-checked, well-reasoned content instead of noise.

We publish 3,000+ voices from 90+ countries. We also conduct education and training programs on subjects ranging from digital media and journalism to writing and critical thinking. This doesn’t come cheap. Servers, editors, trainers and web developers cost money.
Please consider supporting us on a regular basis as a recurring donor or a sustaining member.

Will you support FO’s journalism?

We rely on your support for our independence, diversity and quality.

Donation Cycle

Donation Amount

The IRS recognizes Fair Observer as a section 501(c)(3) registered public charity (EIN: 46-4070943), enabling you to claim a tax deduction.

Make Sense of the World

Unique Insights from 3,000+ Contributors in 90+ Countries