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).