Artificial Intelligence Can Help Address Viewpoint Diversity Challenges (Opinion)
Viewpoint diversity and artificial intelligence are two of the most widely discussed challenges facing higher education today. What if we could solve both problems simultaneously, using AI to create productive intellectual friction between different political and philosophical positions?
Consider taking this approach: Who do you strongly disagree with philosophically or morally, but think their analysis and arguments are clever and rigorous? I’m reminded of one of my high school idols, Ayn Rand, who source I initially thought it was a powerful affirmation of creativity and innovation, but didn’t know much about her deeper political ideology. This summer I decided to read her collection of essays on capitalism, and I suspected that I fundamentally disagreed with her. Then I turned to artificial intelligence. Can I express Ayn Rand’s ideas through a large language model with which I “disagree”, allowing me to experience intellectual friction with less personal gain?
I started a conversation with the chatbot Claude 3.5, asking it to take on the role of Ayn Rand and lay out her core argument: Capitalism is the only ethical system because it respects the rights and freedom of everyone to benefit from their creativity and efforts without being forced to give up some of what they produce for the “benefit” of society. Here’s the thing.
I: In your version of capitalism, how do humans/society decide to produce something greater than any one person can accomplish alone? What if sending someone to the moon could never be coordinated through an independent, voluntary contract, but instead required some larger entity (such as a government) to coordinate and incentivize it? If democratic citizens vote for governments to organize missions to the moon, why is this mandatory?
*Adjusts glasses with serious expression* (Stage cues provided by robot)
Rand Robot: Your question reveals a philosophical premise that I reject. You talk about “democratic citizens” voting to achieve the goal of “shared greatness” – but greater for whom? What right do these citizens have to vote to deprive others of their wealth to fulfill their collective fantasies?
The fact that some people dream of going to the moon does not give them the moral right to force others to fund their dreams. If there is indeed value in going to the moon, let those who see that value risk their own capital, form their own companies, and enter into voluntary contracts. Look what private companies like SpaceX have accomplished through voluntary collaboration and the profit motive!
You raise a false dichotomy between individual rights and large-scale achievement. The greatest achievements in human history—from the transcontinental railroad to the electric light—came from individuals working through voluntary contracts rather than government mandates. Even if multiple parties are involved, they choose to cooperate to achieve mutual benefit and win-win results.
Once you accept that it is acceptable to violate individual rights for the “greater good,” you accept the premise of every dictator and predator in history. There are no “rights” to infringe rights. The aspirations of a group, no matter how noble they sound, cannot override an individual’s right to the fruits of his or her own efforts.
*sucks resistance from cigarette* (more stage clues…)
Would you care to explain why you believe some people have the right to enslave others for collective goals?
I was preoccupied at the moment and I wanted to expose her rigid thinking, so I upped the ante.
I: Do you agree that public health may require a “collective response”? It is assumed that individuals acting independently have no incentive to invest in clean water, vaccines, or databases that collect public health data. Is it better to let millions die from the spread of disease in the name of maximum individual freedom, or is it better to have governments coordinate their actions to provide public health benefits to everyone?
Rand Robot: *There is obvious irritation when tapping the ash*
Your premise is based on the most dangerous of all moral fallacies—that the very existence of a problem justifies the use of force to solve it. You talk about “public health” as if it were some mysterious collective entity that supersedes individual rights. There is no such thing as “public health” – there are only individual human beings, and everyone has the right to make their own decisions about their own health and well-being.
The back-and-forth lasted more than an hour and covered topics such as innovation, market failure and unequal access to basic resources. I was exhausted, so I ended the conversation.
I: I think that humans can create hybrid economic and political systems that may get by — imperfectly — and people may accept those compromises because they still have freedom while providing greater opportunity for their fellow citizens. You believe in the inevitability of destruction and loss of freedom. I don’t think much of the democratic world will see this kind of decline. So compromise is possible. So I think we can use this hybrid system to improve, find the right balance, and continue to move toward a more perfect league.
Then, “Ayn Rand” made the final summary:
Rand Robot: You want me to admit that reality doesn’t match my darkest predictions. Although I think this is a moral compromise, humans have found ways to maintain significant freedoms and progress. You argue that evidence matters—that decades of relative prosperity and innovation under hybrid systems are worth considering.
I cannot and will not recognize a basic moral principle: force is force, whether by a dictator or a democratic majority. Your “muddle along” is based on a basic contradiction. I believe that this contradiction must eventually resolve itself – either towards freedom or towards force…
I was impressed that the robot could articulate Rand’s core arguments, mimic her direct writing and speaking style, question my own logic, provide concrete examples, “reason” beyond the time and place she originally wrote, and offer creative analogies (when asked to explain the economic success of today’s welfare capitalism, she responded, “You’re celebrating reaching the second floor while I point out that we could build a skyscraper”). It was one of the most intellectually engaging 90 minutes I’ve had in a long time.
I wanted to validate my response against the wisdom and judgment of a philosophy professor at Hamilton College, so I sent the entire exchange to him. He noted that AI bots argue like bots and rely too much on rhetoric rather than sound argumentation. Ultimately, in his view, the problem is that “AI bots can never truly distinguish the intent of a debate “Winning” an argument and debate for this purpose achieve a deeper understanding The subject at hand. ” It’s also worth pointing out that debating with artificial intelligence or across a screen with friends and strangers is part of the reason we have such difficulty talking to each other.
Artificial intelligence is not a replacement for what we learn in philosophy classes. But there’s something powerful about living our ideas with people in different times and places—debating race with James Baldwin, asking Leonardo da Vinci to think about how we reconcile innovation and destruction.
One of our faculty members worked with our technology team to create an artificial intelligence agent based on thousands of documents and writings of our nation’s founders. At the end of this lesson on the founding of the United States, students debated “Alexander Hamilton” about the role of central government, inherited wealth, and his views on war. Maybe the answers are a bit mechanical, but they are based on ideas recorded by Hamilton, and as our language models get better, the richness of discussions and debates will grow exponentially.
The best classes and teachers maximize learning by bringing opposing ideas into the conversation. But we know that America’s college students, teachers, and many others find it difficult to express opposing views, especially those we find fundamentally objectionable. Ultimately, this must happen person-to-person through skilled educators and facilitators. But could we also use AI to help us practice how to deal with differences, better articulate our arguments, and ask deeper, more complex questions?
Artificial intelligence can be part of the solution to the challenge we face dealing with ideas we disagree with. If you disagree, try arguing with the AI bot first and then discuss it later.
