In the United States, a growing number of school districts are banning Open AI’s chatbot ChatGPT due to cheating concerns. Taiwan’s school boards have been quiet till now, but similar discussions are likely to emerge if Baidu releases its Mandarin AI chatbot Ernie in March or a Taiwanese-developed chatbot gains traction.
What impact will AI chatbots, or ChatGPT in particular, have on Taiwan’s education system? I had a chat with ChatGPT to find out.
What is ChatGPT?
ChatGPT: “ChatGPT is a large language model developed by OpenAI that can understand and generate human-like responses to text-based conversational inputs.”
How is ChatGPT different from other AI chatbots?
ChatGPT: “ChatGPT is different from other AI chatbots because of its advanced natural language processing capabilities and large knowledge base, allowing it to understand and respond to a wide range of topics and nuances in human language. ChatGPT is also capable of generating more human-like and engaging responses, making it feel more like a conversation with a real person than a machine.”
As ChatGPT suggests, its power lies in its ability to generate responses. That is why it’s called “generative AI.”
Technically, ChatGPT is the biggest “large language model (LLM)” to date using the transformer architecture to produce high-quality, human-like text responses. Apart from the huge training set, it was also trained with human experts and continues learning to enhance its ability to fine-tune responses.
ChatGPT uses billions of parameters to predict the next word in a sentence based on the preceding words. As a generative AI tool, it can generate original content by learning from vast amounts of existing text data, and by producing language that is virtually flawless, logically coherent, and natural.
OpenAI’s engineers have created something truly groundbreaking. And not even they fully understand how ChatGPT is able to work as well as it does. ChatGPT also knows this.
Do ChatGPT engineers really understand how ChatGPT works?
ChatGPT: “ChatGPT engineers have a general understanding of how the model works and the underlying principles of machine learning, but due to the complexity and scale of the model, it is difficult to fully comprehend all the intricacies of its behavior and decision-making processes. The model’s inner workings are influenced by a vast amount of data and mathematical computations, making it challenging to explain every detail of how ChatGPT generates its responses.”
ChatGPT marks a quantum leap forward in AI technology because of the billions of parameters of data and connections coupled with human supervised and reinforced learning. The chatbot is comparable to a brain with trillions of synaptic connections formed with human experiences.
This is not the emergence of AI consciousness that we see in science fiction movies like Terminator and Matrix, but it seems like a giant leap in that direction.
With access to hundreds of gigabytes of internet texts, ChatGPT can make a great teaching assistant.
Should ChatGPT be used in education in Taiwan?
ChatGPT: “As an AI language model, ChatGPT can be a valuable tool in certain educational contexts in Taiwan, but its use should be carefully evaluated and considered alongside the benefits of human interaction and personalized instruction.”
AI chatbots like ChatGPT can be a valuable tool in education. They know much more, answer faster, and explain things more clearly than most teachers.
I am not sure if teachers need to be worried about their jobs, but many should worry about their self-esteem. At least the less talented teachers who are afraid of technology.
Will generative AI tools like ChatGPT replace teachers?
ChatGPT: “It is unlikely that teachers will be completely replaced by generative AI tools like ChatGPT. While these tools can be useful for certain tasks such as providing personalized feedback or generating educational content, they lack the empathy, creativity, and interpersonal skills that are essential for effective teaching.”
This is a reassuring answer, and one that I completely agree with.
The potential uses of ChatGPT to generate information and text are unlimited, and constrained only by one’s imagination. I pushed ChaGPT a little more to give me formal, logical arguments for and against its use in education.
What is an argument against the use of ChatGPT in education?
ChatGPT:
- Premise 1: Education is a complex and multi-faceted process that involves more than just the transfer of information.
- Premise 2: AI chatbots lack the emotional intelligence, creativity, and critical thinking skills that are necessary for effective teaching and learning.
- Conclusion: Therefore, relying on AI chatbots as a primary source of education risks oversimplifying and devaluing the learning process, ultimately leading to suboptimal learning outcomes.
This a valid logical deductive argument against the idea relying on ChatGPT as “a primary source” of education. And I think we would all agree.
Yet I think it is interesting that ChatGPT did not mention the main worry that educators and critics have: students who ask AI chatbots to do their homework and assignments.
Why didn’t you mention students using ChatGPT to cheat?
ChatGPT: “I apologize if my previous response did not address the concern about cheating. One of the arguments against using ChatGPT in education is indeed that students could potentially use it to cheat on assignments or exams by copying or paraphrasing text generated by the model. It is important for educators to consider the potential for misuse and take steps to mitigate it, such as designing assessments that require critical thinking or using plagiarism detection software.”
These are important points. ChatGPT’s oversight about cheating was probably intentional due to its bias to discourage unethical or illegal behavior. ChatGPT makes clear in its user interface that it’s “trained to decline inappropriate requests,” which is perhaps why it would not overtly suggest that it could be used for “cheating.”
This should remind us that ChatGPT knowledge is constrained by at least three factors:
- It is based on the contents of internet texts it has access to as well as its training dataset,
- There are biases in programming and human training, and
- As a language model, fluency and coherent meaning simply trumps facticity.
Can we always trust the facticity of ChatGPT responses?
ChatGPT: “While ChatGPT strives to provide accurate and informative responses, its replies should always be verified and used in conjunction with other sources.”
Tech website CNET found itself in hot water about incorrect information in recent articles that it admitted were written by AI writing tools like ChatGPT. CNET didn’t verify the AI information.
I also asked for an argument in favor of its use in education.
What is an argument for using ChatGPT in education?
ChatGPT:
- Premise 1: AI chatbots have the ability to provide scalable and accessible support to students.
- Premise 2: The use of AI chatbots can free up time for human teachers to focus on more complex and personalized instruction.
- Conclusion: Therefore, incorporating AI chatbots into the educational process can enhance the overall learning experience and improve learning outcomes.
The arguments get to the primary purpose of good education technology: it can scale up and do more than any one teacher can. It can also relieve teachers from mundane aspects of information transmission and free up more of the teacher’s time to focus on more complex and personalized teaching.
In other words, the primary purpose of good education technology is to enable teachers to focus on their primary purpose: student learning.
Flipped classrooms are a good example of good education technology. In this model, good quality instructional videos and online practice, such as from platforms like the Khan Academy (or Junyi Academy in Taiwan), can be used to empower students to learn at home and at their own pace.
The education model is “flipped” because teachers outsource teaching to a good online learning platform and then use class time to monitor and help students with problems, or focus on higher level projects and activities that incorporate skills in more meaningful ways.
Unfortunately, even though flipped classrooms have been promoted for more than 10 years, most teachers have not responded to this more effective educational model.
Why do so few teachers use the flipped classroom model?
ChatGPT: “There are several reasons why this might be the case: 1. Lack of knowledge and training … , 2. Time constraints … , 3. Technology barriers … , 4. Resistance to change … , 5. Student readiness …”
Before asking ChatGPT, I came up with most of the same answers. It takes a lot of time and know-how to record videos necessary for the teaching model, and the teachers’ identity and sense of value can be threatened if they’re not the ones teaching in the videos. What’s worse, it’s also human nature to resist change. Teachers can get stuck in familiar teaching practices.
My hope is that more Taiwanese teachers and students will embrace AI chatbots as homework assistants and try to flip the classroom using AI. This would be certainly easier and less threatening than a flipped classroom based on online lectures.
So, can we trust AI chatbots in Taiwan’s education?
The issue of trust is mostly two-sided: student use of the technology and the quality and facticity of the information provided by the AI chatbot. But these two issues can be resolved with proper training. Both teachers and students need to be trained how to effectively, correctly, and safely use the AI large language models.
It is clear to me that AI tools will not replace human teachers. But I am convinced that human teachers with AI tools will replace human teachers without AI tools. Ultimately, human teachers and AI assistants will complement each other.
The sad truth is that many – perhaps most – students in public education in Taiwan cannot keep up with the fast pace of teaching and testing.
Imagine how amazing it would be for a struggling student to be able to ask ChatGPT not only to solve math problems again and again, but also to show him step by step how these problems are solved, and even to point out where mistakes were made? No human teacher can spend this much time with one student.
The real question is how AI should be used in Taiwan’s education, not whether it should be used. And here our first concern should be with what is best for the learner – not the teacher, not the school administrators, not the cram schools, and not the legislators worried about re-election.
The potential power of AI chatbots for the learner is so huge and so revolutionary that I thought it fitting to give ChatGPT the last word to celebrate this power.
Write a brief poem about how ChatGPT can revolutionize education in Taiwan
ChatGPT:
- In Taiwan’s schools, a new tool’s arrived,
- ChatGPT’s intelligence, it can’t be denied.
- With knowledge vast and insights sharp,
- It can aid in learning, a most valuable part.
- Personalized feedback, it can provide,
- For each student’s needs, it can help guide.
- Its wealth of content, a vast sea,
- Helps teachers enrich their pedagogy.
- Revolutionizing education, it may well do,
- Opening up new avenues, and paths anew.
- In Taiwan’s schools, it’s set to soar,
- ChatGPT, a tool that we can’t ignore.
READ NEXT: Will Chinese Advanced AI Chatbots Survive China’s Online Censorship?
TNL Editor: Bryan Chou (@thenewslensintl)
If you enjoyed this article and want to receive more story updates in your news feed, please be sure to follow our Facebook.
