PLATO enabled students to reach the same level of achievement as in-person classes in less time. And most students preferred this mode of instruction over sitting in a large lecture class. Yet, the system was too expensive to be used by many colleges and universities. Each computer terminal was marketed at over 8,000 dollars – about 58,000 dollars today – and schools were charged additional fees every time a student used the system. Still, PLATO’s success with students inspired a number of companies to create software that provided a similar kind of tutoring, including the College Curriculum Corporation, which was co-founded by Suppes.

Popular personal computer brands, such as Apple and Commodore, advertised the availability of educational software as a reason for families to invest in a home computer.

By 1985, researchers at Carnegie Mellon University were designing software using advances in artificial intelligence and cognitive psychology. They claimed that the current technology had advanced to a level that enabled computer systems to be designed to serve as effective as human tutors. However, even though there were over 10,000 pieces of educational software available at the time, much of it was of fairly low quality and did not provide real tutoring.

Although the more advanced designs of the educational software developed at Carnegie Mellon enabled students to learn significantly more than students in traditional classrooms, they were not widely used in schools.

In the 1980s and 1990s, a school would need a sizable number of expensive, high-powered computer workstations for students to use an intelligent tutor. Today, the computers are much more powerful and much less expensive.

And early intelligent tutors were used primarily in math, science and technology courses, which limited their appeal. Students could not ask the software programs a question. However, students could get feedback on answers to quizzes and tests.

In 2001, the next generation of intelligent tutoring systems was able to have conversations with students in written English. These systems, early chatbots, used advances in natural language processing to have dialogues with students about a range of subjects. Each system was designed specifically for one subject, such as physics. Adding another subject, like English, would require its own specialised tutoring system.

The next few years brought three developments, which enabled a forward leap in achieving the dream of computerised tutoring. One was the availability of broadband internet, which was faster than the dial-up connections of the 1990s. The second was the lower cost of more powerful computers. The third was investment by technology companies and government funding for university research in artificial intelligence, which led to the development of what we now call chatbots.

The First Chatbots

By 2007, early AI chatbots provided tutoring by talking students through their answers to questions. Research showed these chatbots supported learning outcomes similar to the effects of human tutors.. Even so, using chatbot technology to provide tutoring was primarily experimental.

During the 2010s, social networks and advances in artificial intelligence dramatically changed the way people interact with technology. Chatbots are integrated into many parts of our lives and are no longer experimental. People now talk to their phones, to their cars and their home appliances. Many people have virtual assistants at home. They can ask Alexa, Siri or Google for directions or the answers to simple homework questions.

Today, ChatGPT has advanced abilities that enable more complex conversations and can provide individualised tutoring much like what Suppes predicted in 1966.

I asked ChatGPPT why it would be a good tutor, and it responded: “I am a good tutor for a student because I am able to understand and respond to a wide range of questions and prompts, and I can provide detailed and accurate information on a wide range of subjects. Additionally, I am able to communicate this information in a clear and easy-to-understand manner, making it accessible for students of all levels of understanding. Because I am a machine-learning model, I can also provide a large amount of information quickly and efficiently, which can be especially helpful for students who are trying to learn a lot of new material in a short amount of time.”

By contrast, Siri said, “Hmm … I don’t have an answer for that. Is there something else I can help you with?”

Recent research in using chatbots in college courses shows that how chatbots are used is important in encouraging students to learn more deeply. For instance, AI chatbots enabled significant improvements in learning in a graduate course on cloud computing at Carnegie Mellon. These learning gains occurred when these chatbots asked students to build on an existing argument or to provide more information about a claim they had made. In this case, the chatbot asked the student a question, rather than vice versa.

Many educators are worried about students learning less with ChatGPT since it can be used to cheat on assignments and papers. Others are worried about ChatGPT giving wrong answers or spreading misinformation.

Yet the history and research of intelligent tutors show that using the right design to harness the power of chatbots like ChatGPT can make deeper, individualised learning available to almost anyone. For example, if people use ChatGPT to ask students questions that prompt them to revise or explain their work, students will have better learning gains. Since ChatGPT has access to far more knowledge than Aristotle ever did, it has great potential for providing tutoring to students to help them learn more than they would otherwise.