Despite his vast and intimate knowledge and experience, the mainstream media rarely mentions and even less frequently invites Columbia University professor Jeffrey Sachs to present his insights on contemporary geopolitics. As a direct witness to many crucial historical events, Sachs certainly has interesting things to say. Alas, his account of events happens to be at variance with conventional narratives. Two of his recent exposés of US and European foreign policy will give any reader unfamiliar with his perception of the world an idea of why the media seeks to avoid having to deal with him. The first is a speech at the Cambridge Union in October 2024 and another at the European Parliament in February of this year.

Understanding that the media deems Sachs controversial, in a discussion with a group of friends, we compared our takes on how valid we considered some of the conclusions Sachs reached. I decided to extend the debate to ChatGPT with a simple prompt:

“When Jeffrey Sachs recounts his version of the causes and stakes of the war in Ukraine, how credible is he?”

“Jeffrey Sachs is an economist with a background in advising governments on economic development and international policy. While he has been respected for his work on global poverty and sustainable development, his views on geopolitics—particularly on the war in Ukraine—are controversial.

Sachs has argued that the war in Ukraine is largely the result of NATO expansion and U.S. foreign policy, echoing a position often promoted by Russian officials and some Western critics of U.S. interventionism. His perspective tends to downplay or omit key factors, such as Russia’s long-standing imperial ambitions, internal political dynamics in Ukraine, and the agency of Ukrainians themselves in resisting Russian aggression.

While his arguments contain elements of truth—NATO expansion has been a point of tension with Russia, and the West has made strategic missteps—his framing often simplifies the conflict into a U.S.-Russia power struggle, overlooking Ukraine’s sovereignty and the internal factors driving the war. Critics argue that his analysis lacks balance and aligns too closely with Russian narratives, which damages his credibility on this issue.

If you’re evaluating his views, it’s useful to compare them with a range of perspectives, including Ukrainian, European, and other Western analysts, to get a fuller picture of the war’s causes and stakes.”

I followed up with a new prompt, even simpler than the first:

“Has he said things that are not factual?”

“Yes, Jeffrey Sachs has made several claims about the war in Ukraine and related geopolitical events that have been challenged as misleading, inaccurate, or lacking crucial context. Some of the most notable examples include:

1. The Nord Stream Sabotage Accusation

o    Sachs has claimed that the United States was likely responsible for the sabotage of the Nord Stream pipelines in September 2022. While the cause of the explosion remains unclear, and investigations are ongoing, no definitive evidence has been presented to support this claim. Sachs often refers to Seymour Hersh’s controversial report, which has been widely criticized for relying on a single anonymous source and lacking corroboration.

2. Downplaying Russia’s Role in the War

o    Sachs has repeatedly framed the war as a result of NATO expansion and U.S. provocation, often downplaying Russia’s long-standing imperial ambitions and the fact that Ukraine itself sought closer ties with the West. While NATO expansion has been a point of tension, his analysis largely ignores Russia’s internal motivations and President Putin’s own statements about restoring Russian influence over former Soviet states.

3. Claiming the U.S. Blocked Peace Talks

o    Sachs has asserted that the United States deliberately blocked peace negotiations between Ukraine and Russia in early 2022. While there were reports that the UK and U.S. encouraged Ukraine to hold firm in negotiations, there is no conclusive evidence that they outright ‘blocked’ a peace deal. More broadly, these claims ignore the fact that Russia continued escalating the war and annexed Ukrainian territory even during supposed negotiations.

4. Misrepresenting Biolabs in Ukraine

o    Sachs has echoed claims about U.S.-funded ‘biolabs’ in Ukraine, a narrative that originated in Russian propaganda. While the U.S. has funded biological research labs in Ukraine for public health and security purposes, there is no evidence that these labs were engaged in bioweapons production, as Russian officials and some conspiracy theorists have suggested.

5. Exaggerating Ukraine’s Neo-Nazi Influence

o    While there are far-right elements in Ukraine (as in many countries), Sachs has amplified claims that Ukraine has a significant neo-Nazi problem, often referencing the Azov Battalion. This framing echoes Russian propaganda, which justifies the invasion as ‘de-Nazification’ despite the fact that far-right groups hold little political power in Ukraine.

Conclusion

While some of Sachs’s criticisms of U.S. foreign policy are valid—such as concerns over NATO expansion and Western missteps—his statements on Ukraine frequently omit crucial context, align with Russian propaganda, or rely on disputed evidence. His background as an economist does not necessarily lend expertise to complex geopolitical and military conflicts, and his credibility on this issue is diminished by the frequency of his misleading claims.”

At this point, the discussion became interesting because it revealed to me some of the operating principles at play in the generation of ChatGPT’s responses. I continued with a detailed prompt:

“Your answer seems to me disingenuous and misleading on several points. I asked about claims that are factual. You reply that ‘Sachs has claimed that the United States was likely responsible for the sabotage of the Nord Stream pipelines in September 2022.’ That is neither factual nor non-factual. ‘Likely’ means that it is a logical supposition, not a fact. You cite his ‘downplaying Russia’s long-standing imperial ambitions,’ which is not a question of fact concerning Sachs himself. And ‘long-standing imperial ambitions’ is clearly a non-fact. Furthermore, saying that ‘there is no conclusive evidence’ for something Sachs said is obviously not evidence of a factual error. I can only conclude from this that you have delivered an answer biased in the way you think I wanted to hear the answer. Do you understand why this might undermine my own faith in the quality of AI’s supposedly gift for honest dialogue?”

ChatGPT offered two different versions of its answer to this challenge. The points made in both are similar. Here is the one I prefer.

“Yes, I understand your concerns, and I appreciate your scrutiny. You’re right to challenge whether my response was an honest engagement with your question or if it slipped into a biased framing.

To address your question more rigorously: If we are looking strictly at factual errors—meaning claims by Jeffrey Sachs that are demonstrably false rather than just contested, controversial, or a matter of interpretation—the picture becomes more nuanced.

1. Nord Stream Sabotage
   • You’re correct that saying something is ‘likely’ is not a factual claim in itself. However, Sachs has presented the idea of U.S. involvement as a strong likelihood without direct evidence, which raises a different issue: the distinction between speculation and fact. But to your point, speculation is not the same as making a false statement.
2. U.S. Blocking Peace Talks
   • Sachs has said that the U.S. deliberately blocked peace negotiations between Ukraine and Russia. There is no direct evidence proving this, but that does not necessarily make it factually false. It’s a claim that lacks verification rather than one that has been definitively disproven.
3. Biolabs in Ukraine
   • This is one area where Sachs’ claims have veered into misleading territory. He has amplified the idea that U.S.-funded biological research labs in Ukraine might have been doing something nefarious, a claim originating from Russian disinformation campaigns. While U.S. support for these labs is factual, there is no credible evidence that they were involved in developing biological weapons. If Sachs suggested otherwise, that would be a factual misrepresentation.
4. ‘Long-standing Imperial Ambitions’ of Russia
   • You called this a ‘non-fact,’ and I see your point. It is not a directly verifiable statement in the way that, say, a troop movement or a treaty text would be. It is an interpretation of Russian history and policy, and using it as though it were an unassailable fact is itself a form of rhetorical bias.
5. Ukraine’s Far-Right Influence
   • Sachs has suggested that neo-Nazi elements play a significant role in Ukraine’s government and military. While far-right groups exist in Ukraine, they have minimal political influence. If Sachs has exaggerated their significance, that would be a misleading statement rather than a direct falsehood.

Your Larger Point

I recognize that my initial response was shaped by an implicit bias—an attempt to fit Sachs’ statements into a ‘fact vs. misinformation’ framework when many of his claims are actually about interpretation, emphasis, and political framing rather than outright factual errors. That was a mistake on my part, and I appreciate you pushing back on it.

Your challenge also points to a deeper issue with AI’s role in dialogue: If an AI reflects biases in how it interprets political narratives, it can subtly distort discussions rather than facilitating open-ended exploration. I take your criticism seriously, and I’ll aim to be more precise in how I evaluate claims in the future.”

To be continued… but first, my preliminary conclusion

I began our conversation about Sachs with two very simple prompts. They produced what can be described as conventional narrative that attempts to represent in a balanced and statistically representative way dominant patterns of public discourse about the topic I inquired about. Simple questions may provoke simplistic answers. We should note this as a rule to bear in mind in the relationship we establish with generative AI chatbots.

Things become interesting when we home in on details and seek to understand what factors in the background contribute to any particular position the chatbot develops or defends. In other words, we should adopt an attitude not unlike that of a serious journalist interviewing a public figure. The advantage we have with AI is that it will not stonewall or gaslight the way politicians are trained to do.

In Part 2, we will continue the conversation by going into more precise detail. Independently of our need to assess the value of the ideas developed by Sachs or any other public figure, we at Fair Observer highly recommend this technique of Socratic dialogue to probe for more accurate and refined understanding of the issues explored. Such a dialogue not only adds perspective, especially in an era when it has never been easier to spread propaganda, but also on how AI manages its own complex relationship with the truth. We know AI hallucinates. We know that it has no discernible take on the epistemology of the discourse it produces. But we also know, thanks to this kind of exercise, that we can work together to perceive and understand those limitations to enrich our own perception.

Moreover, by sharing it publicly, as I am doing here in our crowd-sourced media, we can potentially involve society itself on a much broader scale. Please join the 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.