From Wharton professor and author of the popular One Useful Thing Substack newsletter Ethan Mollick comes the definitive playbook for working, learning, and living in the new age of AI.
In Co-Intelligence, Mollick urges us to engage with AI as co-worker, co-teacher, and coach. He assesses its profound impact on business and education, using dozens of real-time examples of AI in action. Co-Intelligence shows what it means to think and work together with smart machines, and why it’s imperative that we master that skill.
INTRODUCTION: Three Sleepless Nights
I believe the cost of getting to know AI—really getting to know AI—is at least three sleepless nights.
After a few hours of using generative AI systems, there will come a moment when you realize that Large Language Models (LLMs), the new form of AI that powers services like ChatGPT, don’t act like you expect a computer to act. Instead, they act more like a person. It dawns on you that you are interacting with something new, something alien, and that things are about to change. You stay up, equal parts excited and nervous, wondering: What will my job be like? What job will my kids be able to do? Is this thing thinking? You go back to your computer in the middle of the night and make seemingly impossible requests, only to see the AI fulfill them. You realize the world has changed in fundamental ways and that nobody can really tell you what the future will look like.
Though I am not a computer scientist, I am an academic studying innovation who has long been involved in work on the applications of AI, especially for learning. Over the years, AI has promised much more than it has delivered. For decades, AI research has always seemed to be on the edge of a massive breakthrough, but most practical uses, from self-driving cars to personalized tutoring, always advanced grindingly slowly. During this time, I kept experimenting with AI tools, including OpenAI’s GPT models, figuring out ways to incorporate them into my work, and assigning my students to use AI in class. So my sleepless nights came early, just after the release of ChatGPT in November 2022.
After only a couple of hours, it was clear that something huge had shifted between previous iterations of GPT and this new one. Four days after the AI was launched, I decided to demonstrate this new tool to my undergraduate entrepreneurship class. Barely anyone had heard of it. In front of my students, I put on a show, demonstrating how AI can help generate ideas, write business plans, turn those business plans into poems (not that there is a lot of demand for that), and generally fill the role of company cofounder. By the end of the class, one of my students, Kirill Naumov, had created a working demo for his entrepreneurship project—a Harry Potter–inspired moving picture frame that reacted to people walking near it—using a code library he had never used before, in less than half the time it would otherwise have taken. He had venture capital scouts reaching out to him by the end of the next day.
Within two days of introducing students to AI, several told me they used ChatGPT to explain confusing concepts to them “like they were ten years old.” They stopped raising their hands as much—why expose themselves in class when they could just ask the AI later? And every essay was suddenly written with perfect grammar (though references were often wrong and the final paragraph tended to start with “In conclusion”—a telltale sign of early ChatGPT writing, since fixed). But the students weren’t just excited, they were nervous. They wanted to know the future.
Some of them asked me what it means for their preferred careers (“Should I become a radiologist if AI can do a lot of the work?” “Will writing marketing copy still be a good job five years from now?”). Others asked when this technological development would stop, or if it would stop. Someone even asked if Artificial General Intelligence (AGI), the hypothetical machine that would be smarter than a human, might arrive before graduation.
I didn’t have any answers then (though I have a few more now), yet I recognized that I wasn’t immune to these changes. So I decided to get hands-on and put the AI through its paces. Much of my work over the past five years has been building simulations that teach business skills. It has taken tremendous investment from my university, and the efforts of a dozen talented people, to build these elaborate digital experiences. After thousands of hours, the games were great: using thousands of lines of code, we could do elaborate learning simulations that helped teach skills like negotiation.
But I decided to type something into ChatGPT: You will be my negotiation teacher. You will simulate a detailed scenario in which I have to engage in a negotiation. You will fill the role of one party, I will fill the role of the other. You will ask for my response in each step of the scenario and wait until you receive it. After getting my response, you will give me details of what the other party does and says. You will grade my response and give me detailed feedback about what to do better using the science of negotiation. You will give me a harder scenario if I do well, and an easier one if I fail.
ChatGPT wrote back: Sure, I’d be happy to help you practice negotiations through a simulation exercise! Let’s start with a simple scenario. You are a salesperson trying to sell 100 pens to a customer. The pens are usually $1, but the customer is trying to negotiate the price down. The customer starts by offering to buy the pens for $0.50 each. How do you respond?
And it proceeded to take me through an entire simulation that, while not perfect, did 80 percent of what took our team months to do. Based on just a paragraph-long prompt from me!
My sleepless nights began.
And to be honest, they haven’t ended. Every week, it seems like AI serves up a new miracle—or a new concerning development. I soon found myself arguing with a chatbot that accused me of being unethical when I asked it to help me write computer code. I discovered that I could create beautiful images by giving the right words to a machine. I could code in Python, a language I never learned. I discovered that a machine could do large amounts of my job . . . and maybe lots of other people’s jobs. I discovered something remarkably close to an alien cointelligence, one that can interact well with humans, without being human or, indeed, sentient. I think we will all have our three sleepless nights soon.
And sleep-deprived as I now am, I keep going back to my students’ questions: What does this technology mean for the future of work and education? Things are happening so quickly that it is hard to be sure, but we can begin to see its outlines. AI is what those of us who study technology call a General Purpose Technology (ironically, also abbreviated GPT). These advances are once-in-a-generation technologies, like steam power or the internet, that touch every industry and every aspect of life. And, in some ways, generative AI might even be bigger . . . Where previous technological revolutions often targeted more mechanical and repetitive work, AI works, in many ways, as a co- intelligence. It augments, or potentially replaces, human thinking to dramatic results. . . . And all of this ignores the larger issue, the alien in the room. We have created something that has convinced many smart people that it is, in some way, the spark of a new form of intelligence. An AI that has blown through both the Turing Test (Can a computer fool a human into thinking it is human?) and the Lovelace Test (Can a computer fool a human on creative tasks?) within a month of its invention, an AI that aces our hardest exams, from the bar exam to the neurosurgery qualifying test. An AI that maxes out our best measures for human creativity and our best tests for sentience. Even weirder, it is not entirely clear why the AI can do all these things, even though we built the system and understand how it technically works.
No one really knows where this is all heading, including me. Yet, despite not having definitive answers, I think I can be a useful guide. I have found myself to be an influential voice on the implications of AI, particularly through my newsletter, One Useful Thing, even though I am not a computer scientist myself. Indeed, I think that one of my advantages in understanding AI is that, as a professor at Wharton, I have long studied and written about how technologies are used. As a result, my coauthors and I have published some of the first research on AI in education and in business, and we have been experimenting with practical uses of AI in ways that major AI companies have cited as examples. I regularly speak with organizations, companies, and government agencies, as well as with many AI experts, to understand the world we are making. I also attempt to keep up with the flood of research in the field, much of it in the form of scientific working papers that have not yet gone through the long process of peer review but still offer valuable data about this new phenomenon (I will be citing a lot of this early work in the book to help fill in the picture of where we are headed, but it is important to realize that the field is evolving rapidly). Based on all these conversations and papers, I can assure you that there is nobody who has the complete picture of what AI means, and even the people making and using these systems do not understand their full implications.
So I want to try to take you on a tour of AI as a new thing in the world, a co-intelligence, with all the ambiguity that the term implies. We have invented technologies, from axes to helicopters, that boost our physical capabilities; and others, like spreadsheets, that automate complex tasks; but we have never built a generally applicable technology that can boost our intelligence. Now humans have access to a tool that can emulate how we think and write, acting as a co-intelligence to improve (or replace) our work. But many of the companies developing AI are going further, hoping to create a sentient machine, a truly new form of co-intelligence that would coexist with us on Earth. To get a handle on what this means, we need to start from the beginning, with a very basic question: What is AI?
So we are going to start there, discussing the technology of Large Language Models. That will give us a basis for thinking about how we, as humans, can best work with these systems. After that, we can dive into how AI can change our lives by acting as a coworker, a teacher, an expert, and even a companion. Finally, we can turn to what this might mean for us, and what it means to think together with an alien mind.
Copyright © 2024 by Ethan Mollick. All rights reserved. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher.
Ethan Mollick is a professor of management at Wharton, specializing in entrepreneurship and innovation. His research has been featured in various publications, including Forbes, The New York Times, and The Wall Street Journal. He is the creator of numerous educational games on a variety of topics. He lives and teaches in Philadelphia, Pennsylvania.
