[Formatting note: the text of my questions appears in italic. ChatGPT’s answers appear in regular script but indented. My comments appear in normal script.]

Governments and the media appear to have adopted a new mission: to skew the meaning of words as a means of limiting citizens’ ability to think for themselves. The US House of Representatives offered a stirring example of the trend. I decided to ask ChatGPT this compelling question.

“Now, with a war going on in Gaza in which both sides appear guilty of atrocities, it has become utterly abusive to characterize any criticism of Israel, its politics and the action of its military as anti-Semitism. But that is exactly what’s happening. There have been examples in the recent past of shaming any pointed criticism of what is clearly an aggressive nation in its region that has put in place a regime and a set of laws in contradiction with the principles associated with democratic liberalism. But does it make any sense in any of our democracies to shame and censor criticism of a political entity? Isn’t that the opposite of the kind of vibrant debate without which democracy cannot function?”

Here was AI’s level-headed answer.

“It is true that the ongoing conflict in Gaza has been a contentious issue, with both sides being accused of atrocities. However, it is important to note that criticism of Israel’s policies and military actions is not inherently anti-Semitic. In fact, many Jewish people themselves have been critical of Israel’s actions in the region.

It is important to have open and honest discussions about political entities and their actions, as this is a cornerstone of democracy. Censoring or shaming criticism of a political entity is not conducive to a healthy debate and can lead to a lack of accountability.

It is also worth noting that there have been instances where criticism of Israel has been met with backlash, including accusations of anti-Semitism. However, it is important to distinguish between legitimate criticism and hate speech.

In conclusion, it is important to have open and honest discussions about political entities and their actions, without resorting to censorship or shaming. This is essential for a healthy democracy and for holding those in power accountable.

Why is AI so unfailingly preachy?

When dialoguing with ChatGPT, it’s difficult not to be distracted by what is clearly a feature of its algorithm: never ending an analysis without some moralizing sentiment usually introduced by “it is important to…”. In this case, the locution appeared in two successive sentences. Apparently, AI coders feel that a language model must be empowered to instruct users about what is good or bad, rather than allow them to discover such distinctions on their own. In this case, I happened to agree, which should have been obvious anyway.

I went on to give some specific historical context.

“Congress, nevertheless, passed a law declaring that ‘anti-Zionism is antisemitism.’ All but one Republican and more than half of Democrats supported it. Is this a sign that the political class dominated by two parties no longer sees the basic principles of democracy, to say nothing of the first amendment, as necessary to the exercise of government in the US? Does it also mean that rational thought and critical thinking are being suppressed?”

ChatGPT provided me with some solid context before weighing in on my concerns.

“The US House of Representatives recently passed a resolution that equates anti-Zionism with antisemitism. The resolution was introduced by two Jewish Republicans in the House, Max Miller of Ohio and David Kustoff of Tennessee, and was supported by all but one Republican and a substantial minority of Democrats.

It is important to note that this resolution is non-binding and does not carry the force of law. However, it has been criticized by lawmakers, advocates for Palestinians and progressive Jewish groups, who say the measure could restrict free speech rights in the country.

It is concerning if the political class is suppressing rational thought and critical thinking, as these are essential components of a healthy democracy. However, it is important to note that the resolution is not a law and does not have the force of law. It is also worth noting that criticism of Israel’s policies and military actions is not inherently anti-Semitic, and many Jewish people themselves have been critical of Israel’s actions in the region.

In conclusion, while the resolution passed by the US House of Representatives is concerning, it is important to distinguish between legitimate criticism and hate speech. It is also important to have open and honest discussions about political entities and their actions, without resorting to censorship or shaming. This is essential for a healthy democracy and for holding those in power accountable.

I couldn’t help feeling that ChatGPT was trying to reassure me with a kind of “boys will be boys” argument concerning the deliberations in Congress, dismissing their importance because they don’t have the force of law. I continued with another question.

What then does this say about the values of the elected political class in the US? Does it tell us they are more interested in power and lobbyists’ support than in democracy itself?

“The recent resolution passed by the US House of Representatives that equates anti-Zionism with antisemitism has been criticized by lawmakers, advocates for Palestinians and progressive Jewish groups, who say the measure could restrict free speech rights in the country. While it is concerning if the political class is suppressing rational thought and critical thinking, it is important to note that the resolution is non-binding and does not carry the force of law.

It is important to have open and honest discussions about political entities and their actions, without resorting to censorship or shaming. This is essential for a healthy democracy and for holding those in power accountable. The United States of America is founded on the principles of liberty, equality and democracy, which are the three most common political values shared by all Americans. These values establish the freedom of our actions, but only if those actions are not detrimental to the freedom of other people. No two people are the same, but they should always be treated equally in the light of the law.

It is important to remember that the political class is not a monolithic entity, and there are many lawmakers who are committed to upholding the principles of democracy and free speech. However, it is also true that the political class is influenced by powerful lobbies and special interest groups, which can sometimes lead to policies that are not in the best interests of the people.

In conclusion, while the recent resolution passed by the US House of Representatives is concerning, it is important to distinguish between legitimate criticism and hate speech. It is also important to have open and honest discussions about political entities and their actions, without resorting to censorship or shaming. This is essential for a healthy democracy and for holding those in power accountable. The values of liberty, equality and democracy are the cornerstone of American political culture, and it is important to uphold these values in all aspects of governance.

Here we can see that AI has no qualms about endlessly repeating itself, especially its moralizing passages, something rational humans tend to avoid when they sense that it may get on the nerves of their interlocutor. I see this as an example of ChatGPT failing the Turing test. It sounds human but doesn’t act human. It never seems to call into question its own conclusions. It’s true a lot of people do the same thing, but not those who take rationality seriously.

It seems to me that the commercial model of AI we may now access contains at its core an instruction worth debating: that its discourse be designed for the specific purpose of telling people what they should think about the issues they appear curious about.

That means that today’s AI is built for a certain kind of soft propaganda. This should worry us. In this particular case, I was happy to see ChatGPT resonate with my own reasoning. But is that just a matter of chance? It convinces me that I’m right. But what if I’m wrong? AI’s conclusions appear designed to shut down, rather than expand, my own critical inquiry.

Can we begin to imagine a generation of AI imbued with the intellectual humility that might allow it to express its agreement or disagreement without claiming to possess the authoritative truth and repeating it endlessly?

*[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.]

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