ChatGPT

Multiple Intelligences: A New Idea about A Forty-Year-Old Idea

By Howard Gardner © 2023

It’s been forty years since I first introduced the notion of multiple intelligences (MI) in my book Frames of Mind. A lot has been said about this idea, much of it by me, and in many ways, I’ve moved on to other concerns. And yet, I recently noted something about myself—and that in turn, led to an idea about MI which is new to me, and, perhaps, to others as well.

Even those of us who explicitly endorse the idea of multiple intelligences are often overheard claiming that someone is “intelligent,” “smart,”….or, less thoughtfully, as “dumb,” “dull,” or “not too swift.” I plead “Guilty—with extenuating circumstances.” What’s going on here?

One possibility is that this reveals an unconscious default to the idea of a single intelligence (“g” for general intelligence) as manifested by scoring well on a standard psychometric instrument like an IQ or SAT. But I propose another possibility. Rather, without quite realizing it, those of us who use such phrases are actually valorizing the particular intelligence—or set of intelligences—that we believe this person has—or that we ourselves have.

Yo-Yo Ma - World Economic Forum, Davos 2008 (Source: World Economic Forum from Cologny, Switzerland,Wikipedia)

A few examples:

  • When we refer to a great cellist (like Yo-Yo Ma) or a great soprano (like Renee Fleming) as “smart,” it’s not that we are referring to how well that person scores on an IQ or SAT test. Instead, we might have in mind how quickly and how well that person picks up a new piece of music; or how well he or she analyzes a classical (or popular) work; or how the performer adjusts to the different conditions in various performance halls or with diverse ensembles.

  • When we refer to a great tennis star (like Arthur Ashe), or a great gymnast (like Simone Biles) as “smart,” we are unlikely to be referring to their grades in school. Instead, we might have in mind how quickly and how well that athlete adjusts to new weather conditions, new opponents, new rules of the game, an unexpected compliment, or an unfair criticism.

  • When we refer to a U.S. Senate majority leader or a House of Representatives Speaker as “smart,” we are not referring to their class rank in college. Instead, we might be referring to how the person manages to secure the votes needed to get a controversial bill passed or, depending on the circumstances, blocked…or how to position themselves vis-à-vis the media, reporters, cartoonists, or polls.

Even within the academy, this contextual use of the term smart prevails. Historians look for signs of intelligence that are quite different from those noted by economists, linguists, literary critics, biologists, mathematicians, or physicists. Scholars rarely comment in illuminating ways on the capacities of those working in fields remote from their own. We could say that a recognition of multiple forms of intelligence is spread throughout the academy, even among those who purport to believe in a singular intelligence, or IQ.

And so on—you can invent your own examples—whether from the ranks of clinical practitioners or weather forecasters or religious leaders or shop clerks. Nearly all of us are likely to continue using words like “smart” and “dumb,” or “clever” and “dull,” but we need to pick apart the field of reference of these words and make clear what we mean—and that requires the exercise of our personal intelligences!

Stepping back, after decades of pondering these issues, I identify three separate insights:

  1. Human beings have a range of intelligences and we may, and sometimes do, change the ones that we valorize and why we valorize them.

  2. Any intelligence can be used benevolently or malevolently; considered in themselves, intelligences are value-neutral. As masters of the German language, both the poet Goethe and the propagandist Goebbels had considerable linguistic intelligence, but they used it to very different ends. As human beings, we should be judged not by the intelligences that we happen to display and deploy but rather in which way we—and others—invoke them.

  3. Even those of us who continue to use the words “smart,” “intelligent,” or “brilliant” need to stop, reflect, and recognize which of the intelligences we are actually valorizing—and why we do so.

And of course, the advent of ChatGPT and other Large Language Instruments will compel us to continue reflecting on these issues.

Reference

Gardner, H. Frames of mind: The theory of multiple intelligences. New York: Basic Books, 1983.

For comments on this essay, I thank Shinri Furuzawa, Annie Stachura, and Ellen Winner.

Chat GPT: First Musings

Howard Gardner © 2023

How will ChatGPT—and other Large Language Instruments—affect our educational system—and our broader society? How should they?

I’m frequently asked questions like these—and they are much on my mind.

Something akin to ChatGPT—human or super-human levels of performance—has long been portrayed in science fiction: I’m familiar with the American, British, French, and Russian varieties. But few observers expected such excellent performance so fast, so impressively, so threatening (or enabling)—depending on your stance.

As suggested by historian Yuval Harari, we may be approaching the end of the Anthropocene era.

We can anticipate that large language instruments—like Open AI’s ChatGPT and DALL-E—will continually improve.

They will be able to do anything that can be described, captured in some kind of notation. Already they are able to conduct psychotherapy with patients, write credible college application essays, and create works of visual art or pieces of music in the style of well-known human creators as well as in newly invented styles. Soon one of their creations may be considered for the Nobel Prize in physics or literature, the Pulitzer Prize for musical composition or journalism.

Of course, superior AI performance does not—and need not—prevent human beings from engaging in such activities. We humans can still paint, compose music, sculpt, compete in chess, conduct psychotherapy sessions—even if AI systems turn out to outperform us in some or most ways.

Open AI introduced ChatGPT 3 in 2020 and DALL-E in 2021

We can also work in conjunction with AI programs. A painter may ask DALL-E to create something, after which the painter may alter what the program has furnished. A researcher may present ChatGPT with a hypothesis and ask the system to come up with ways to test that hypothesis—after which the researcher can carry out one or more of these approaches herself. Such activities can alternate, going back and forth between the human provision and the computational program.

We fear what could go wrong—and rightly so. AI systems like ChatGPT have not undergone a million-plus years of evolutionary history (including near extinction or sudden vaults in skill); such recently devised systems do not inhabit our planet in the same way that the hominid species has. They are not necessarily—and certainly not existentially—afraid of cataclysmic climate change, or nuclear war, or viruses that prove fatal to homo sapiens. Indeed, such systems could spread misinformation rapidly and thereby contribute to destructive climate change and the probability of nuclear war (recall “The Doomsday Machine” featured in the dystopic movie Dr. Strangelove). These destructive outcomes are certainly possible, although (admittedly) such calamities might happen even had there been no digital revolution.

And what about the effects of Large Language Instruments on our schools, our broader educational system?

Many fear that systems like ChatGPT will make it unnecessary for students to learn anything, since ChatGPT can tell them everything they might want or need to know—almost instantaneously and almost always accurately (or at least as accurately as an 20th century encyclopedia or today’s “edition” of Wikipedia!). I think that AI will have a huge impact on education, but not in that way.

Now that machines are rivalling or even surpassing us in so many ways, I have an ambitious and perhaps radical recommendation. What education of members of our species should do—increasingly and thoughtfully—is to focus on the human condition: what it means to be human, what our strengths and frailties are, what we have accomplished (for good or evil) over many centuries of biological and cultural evolution, what opportunities are afforded by our stature and our status, what we should avoid, what we should pursue, in what ways, and with what indices of success...or of concern.

But to forestall an immediate and appropriate reservation: I don’t intend to be homo sapiens centric. Rather, I want us to focus on our species as part of the wider world, indeed the wider universe. That universe includes the biological and geological worlds that are known to us.

Bruner in the Chanticleer 1936, Duke University (Source: Wikipedia)

Psychologist-turned-educator (and my teacher) Jerome Bruner inspired me. His curriculum for middle school children, developed nearly sixty years ago, centered on three questions:

  • What makes human beings human?

  • How did they get to be that way?

  • How can they be made more so?

To approach these framing topics intelligently, we need disciplinary knowledge, rigor, and tools. We may not need to completely scuttle earlier curricular frameworks (e.g., those posed in the United States in the 1890s by the “Committee of Ten” or the more recent “Common Core”); but we need to rethink how they can be taught, modelled, and activated to address such over-arching questions.

We need to understand our human nature—biologically, psychologically, culturally, historically, and pre-historically. That’s the way to preserve the planet, all of us on it. It’s also the optimal way to launch joint human-computational ventures—ranging from robots that construct or re-construct environments to programs dedicated (as examples) to economic planning, political positioning, military strategies and decisions.

To emphasize: this approach is not intended to glorify; homo sapiens has done much that is regrettable, and lamentable. Rather, it is to explain and to understand —so that, as a species, we can do better as we move forward in a human-computer era.


Against this background, how have I re-considered or re-conceptualized the three issues that, as a scholar, I’ve long pondered?

  1. Synthesizing is the most straightforward. Anything that can be laid out and formulated—by humans or machines—will be synthesized well by ChatGPT and its ilk. It’s hard to imagine that a human being—or even a large team of well-educated human beings—will do better synthesis than ChatGPT4, 5, or n.

    We could imagine a “Howard Gardner ChatGPT”—one that synthesizes the way that I do, only better—it would be like an ever-improving chess program in that way. Whether ChatGPT-HG is a dream or a nightmare I leave to your (human) judgment.

  2. Good work and good citizenship pose different challenges. Our aspirational conceptions of work and of membership in a community have emerged in the course of human history over the last several thousand years—within and across hundreds of cultures. Looking ahead, these aspirations indicate what we are likely to have to do if we want to survive as a planet and as a species.

    All cultures have views, conceptions, of these “goods,” but of course—and understandably, these views are not the same. What is good—and what is bad, or evil, or neutral—in 2023 is not the same as in 1723. What is valued today in China is not necessarily what is admired in Scandinavia or Brazil. And there are different versions of “the good” in the US—just think of the deep south compared to the East and West coasts.

    ChatGPT could synthesize different senses of “good,” in the realms of both “work” and “citizenship.” But there’s little reason to think that human beings will necessarily abide by such syntheses—the League of Nations, the United Nations, the Universal Declaration of Human Rights, the Geneva convention were certainly created with good will by human beings—but they have been honored as much in the breach as in the observance.

A Personal Perspective

We won’t survive as a planet unless we institute and subscribe to some kind of world belief system. It needs the prevalence of Christianity in the Occident a millennium ago, or of Confucianism or Buddhism over the centuries in Asia, and it should incorporate tactics like “peaceful disobedience” in the spirit of Mahatma Gandhi, Martin Luther King, or Nelson Mandela. This form of faith needs to be constructed so as to enable the survival and thriving of the planet, and the entities on it, including plants, non-human animals, and the range of chemical elements and compounds.

Personally, I do not have reservations about terming this a “world religion”—so long as it does not posit a specific view of an Almighty Figure—and require allegiance to that entity. But a better analogy might be a “world language”—one that could be like Esperanto or a string of bits 00010101111….

And if such a school of thought is akin to a religion, it can’t be one that favors one culture over others—it needs to be catholic, rather than Catholic, judicious rather than Jewish. Such a belief-and-action system needs to center on the recognition and the resolution of challenges—in the spirit of controlling climate change, or conquering illness, or combatting a comet directed at earth from outer space, or a variety of ChatGPT that threatens to “do us in” from within….Of the philosophical or epistemological choices known to me, I resonate most to humanism—as described well by Sarah Bakewell in her recent book Humanly Possible.

Multiple Intelligences (MI)

And, finally, I turn to MI. Without question, any work by any intelligence, or combination of intelligences, that can be specified with clarity will soon be mastered by Large Language Instruments—indeed, such performances by now constitute a trivial achievement with respect to linguistic, logical, musical, spatial intelligences—at least as we know them, via their human instantiations.

How—or even whether —such computational instruments can display bodily intelligences or the personal intelligences is a different matter. The answer depends on how broad a formulation one is willing to accept.

To be specific:

Taylor Swift at 2019 American Music Awards (Source: Wikipedia)

  • Does a robotic version of ChatGPT need to be able to perform ballet à la Rudolf Nureyev and Margot Fonteyn? And must it also show how these performers might dance in 2023 rather than in 1963?

  • Does it need to inspire people, the way Joan of Arc or Martin Luther King did?

  • Should it be able to conduct successful psychotherapy in the manner of Erik Erikson or Carl Rogers ?

  • Or are non-human attempts to instantiate these intelligences seen as category errors— the way that we would likely dismiss a chimpanzee that purported to create poetry on a keyboard?

The answers, in turn, are determined by what we mean by a human intelligence—is it certain behavioral outputs alone (the proverbial monkey that types out Shakespeare, or the songbird that can emulate Maria Callas or Luciano Pavarotti, Mick Jagger or Taylor Swift)? Or is it what a human or group of humans can express through that intelligence to other human beings—the meanings that can be created. conveyed, comprehended among members of the species.

I’m reminded of Thomas Nagel’s question: “What is it like to be a bat?” ChatGPT can certainly simulate human beings. But perhaps only human beings can realize—feel, experience, dream—what it’s like to be a human being. And perhaps only human beings can and will care—existentially—about that question. And this is what I believe education in our post-ChatGPT world should focus on.


For comments on earlier versions of this far-ranging blog, I am grateful to Shinri Furuzawa, Jay Gardner, Annie Stachura, and Ellen Winner.

References:

Bakewell, S. (2024). Humanly possible: Seven hundred years of humanist freethinking, inquiry, and hope. Vintage Canada.

Nagel, T. (1974). what is it like to be a bat? The Philosophical Review. https://doi.org/10.4159/harvard.9780674594623.c15

Wikimedia Foundation. (2023, August 21). Man: A course of study. Wikipedia. https://en.wikipedia.org/wiki/Man:_A_Course_of_Study

AI & MI: Artificial Intelligence and Multiple Intelligences

By Tom Hoerr

“What are multiple intelligences?” I asked ChatGPT, the new artificial intelligence (AI) technology.

Within a few seconds it said:

“Multiple intelligences are a theory of intelligence developed by Harvard psychologist Howard Gardner in 1983. It suggests that there are eight different types of intelligence: linguistic, logical-mathematical, spatial, bodily-kinesthetic, musical, interpersonal, intrapersonal, and naturalistic. Each type of intelligence is associated with a different way of processing information and solving problems.”

Wow, yes, within a few seconds.

And why is this relevant to MI?

MI is all about problem-solving. Howard Gardner defined intelligence as the ability to solve a problem or create a product that is valued in a culture, and each of the multiple eight intelligences encompasses a different set of skills and talents.

 ChatGPT, a technology that can follow instructions in a conversational prompt and provide a detailed response (as it did to my question), is also about solving problems. The concept of MI was revolutionary when Frames Of Mind was published in 1983. Today, the potential of AI captures our mind and activates our imagination. Typing ChatGPT in Google yields 855,000,000 links in .065 seconds.

How do MI and AI interact? Or do they?

First, let’s be clear, we already routinely deal with some AI-MI which we likely take for granted. Some salient MI-AI examples:

  • Linguistic: AI automated answering services. “Is that a real person?”

  • Logical-mathematical: AI chess or other game software. “I was check-mated again!”

  • Musical: AI playlists which emanate from our previous choices. “I don’t need to seek the songs I enjoy.”

  • Spatial: AI GPS directions. “Remember the AAA Triptik?!??

  • Bodily-kinesthetic: AI autopilot is coming. Check out “Robotic Limbs Moved By the Mind” in this 60 Minutes feature (click here for link).

Of course, just as performing a complex task requires using many intelligences, sophisticated AI acts require an amalgam of MI. For example, when buying something online (something I do far more than I should), the website features linguistic and spatial information about the products. Then, after I have purchased, I get a message that says, "Since you purchased X, you might be interested in Y and Z." The employees used their interpersonal and intrapersonal intelligences to conceptualize what a buyer of X might now want. Then they used their logical-mathematical intelligences to program the site.

But this is old news. As noted above, I did a small trial and asked ChatGPT “What are multiple intelligences?” The accurate response was based on readily accessible information and was generated within a few seconds. Then I posed a bit more complex question, “How can multiple intelligences be used?” Again, the lightning-fast response was accurate, although a bit superficial:

“1. Use visual aids such as diagrams, charts, and pictures to help students understand concepts. 2. Incorporate music and rhythm into lessons to help students remember information. 3. Use role-playing and simulations to help students understand abstract concepts. 4. Incorporate movement into lessons to help students stay engaged and learn.” And so on for each MI.

 I decided to be a bit contrarian and asked, “What about the opposition to MI?” ChatGPT said:

“The opposition to multiple intelligences theory is largely due to the fact that it challenges the traditional view of intelligence as a single, unitary construct. Critics argue that the theory is too vague and lacks empirical evidence to support its claims. Additionally, some argue that the theory is too broad and that it fails to account for individual differences in intelligence. Finally, some argue that the theory is too focused on the individual and fails to consider the social and cultural contexts in which intelligence is developed."

That response shows a bit more sophistication – particularly the last sentence – but simply regurgitates criticisms that have already been stated. The speed of the response, again within a few seconds, is very impressive.

To elicit a response that isn’t already lodged in libraries, I asked, “Can happiness be smelled?” The ChatGPT response:

“No, happiness is not something that can be smelled.” That’s true but I would expect a human with a bit of sophistication to continue, perhaps with, “No, happiness is not something that can be smelled but we surely associate some scents with happy feelings – freshly baked bread comes to mind as do popcorn and cookies.”

Of course, there’s an entire perfume industry.

The ChatGPT technology possesses some intrapersonal intelligence. When asked about its limitations, it responded:

“ChatGPT is not capable of solving problems that require complex reasoning or understanding of abstract concepts. It is also not capable of providing advice or making decisions for users. Additionally, ChatGPT cannot provide accurate answers to questions that require a deep understanding of a particular subject or domain.”

 Relatedly, very relatedly, I asked if ChatGPT could ascertain emotion. It replied that it cannot and said,

“ChatGPT is a natural language processing (NLP) system that is designed to generate responses to user input. It does not have the capability to detect or interpret emotion.”

Technology continues to advance at an astonishing rate (remember floppy computer disks?), so presumably the superficial response capacity of AI will increase so that answers will become more intricate. Imagine 100 Jeopardy champions crammed in a brain, spouting out facts. That’s impressive!

A Jeopardy game, however, is not the real world. The mastery of information and facts that it values ignores the nuances of life and complexity of human relationships. Nowhere are the categories of interpersonal or intrapersonal intelligences found on a Jeopardy board and ChatGPT shares that limitation.

Artificial intelligences using multiple intelligences (AI-MI) to solve problems will continue and, indeed, exacerbate. But I’m dubious about the ability of AI to read and understand people’s emotions; I’m doubtful that AI will be able to feel and generate empathy. I cannot imagine AI effectively serving as the personal intelligences.

At the New City School, we believed that each of the intelligences is important because they tapped into different human capacities. We infused MI throughout our curriculum and pedagogy to give students more pathways to learn. But we also said that we believed that the interpersonal and intrapersonal intelligences are the most important. Today I capture this by saying

“Who you are is more important than what you know.”

That is not to denigrate scholastics; kids need to learn to read, write, and calculate. It is to say that the personal intelligences – the ability to work with others and to know yourself – are the strongest contributors to success and happiness. I saw this in the progress of our students.

When we think about how our students must be prepared to succeed in the future – recognizing that we must prepare them for success in life, not to just do well in school –the importance of the personal intelligences, SEL in today’s nomenclature, is very clear. ChatGPT and its successors will dominate the routine. Our students still need to learn the 3 R’s, but we cannot stop there. We must teach them how to solve complex problems, including working with, learning from, and appreciating others.

What’s your take on AI-MI? Does the increasing pervasiveness of worry you? I would love to hear from you.

Tom (a real person)

Republished with permission from the newsletter: Intelligences Connections Volume 32, Number 5 (click here to subscribe).

Are Some Intelligences Superior to Others?

By Howard Gardner

I recently received an inquiry from an undergraduate student, Cuinn Lopes, who wanted to know whether some intelligences could be considered better than others.

He asked as follows:

“Based on what scientific evidence shows, should we believe that there are superior forms and inferior forms of intelligence; for example, should we believe that mathematical intelligence is superior to linguistic or kinesthetic intelligence? … Are there forms of intelligence that are more or less intelligent than other forms of intelligence?”

MY RESPONSE

This is a good question. My short answer is NO—there are no forms of intelligence that are crucially or essentially, more intelligent than others. Like beauty, intelligences are in the eye of the beholder.

Example: To gain admission to Harvard and other prestigious colleges in the 19th century, one had to demonstrate mastery of ancient languages—Latin, Greek, and sometimes Hebrew.

Nowadays, we smile at that because it is clear that mathematical-computation abilities are more valorized at the start of the 21st century.

But if in your lifetime, common algorithms such as ChatGPT (or its descendants) prove to be much better than we humans are at logical-mathematical operations, we may instead valorize bodily-kinesthetic intelligence or intrapersonal intelligence—no one cares about how computational systems would do on those dimensions.

Also, while we do not have validated tests for all of the intelligences, any teacher knows that excellence in one intelligence does not predict excellence (or disability) in another intelligence.

There may be some general capacities— like attention, or reflectiveness—that cut across the intelligences, but this possibility is essentially independent of the question that you raise.

I would also refer you to my previous blog post, “Are All Intelligences Equal: An Issue Raised by Cormac McCarthy’s Recent Novels” (link here). In this

What Happens to Human Intelligence If AI Surpasses Us?

Howard Gardner was recently interviewed by Athanasios Katsikidis of The New York Times and the Greek daily newspaper, Kathimerini, on the subject of multiple intelligences and AI. Read the interview in Greek (link here) or English (link here) to find out his views on the end of the Anthropocene era or dominance of human beings on the planet, and what will happen to human intelligence and creativity when AI surpasses us in many areas.

For the Greek version: click here.

English version: click here.