AI & Education
How AI Could Save (Not Destroy) Education
Full Transcript
Title: "How AI Could Save (Not Destroy) Education | Sal Khan | TED"
Transcript: "So anyone who's been paying attention for the last few months has been seeing headlines like this, especially in education. The thesis has been: students are going to be using ChatGPT and other forms of AI to cheat, do their assignments. They’re not going to learn. And it’s going to completely undermine education as we know it. Now, what I'm going to argue today is not only are there ways to mitigate all of that, if we put the right guardrails, we do the right things, we can mitigate it. But I t hink we're at the cusp of using AI for probably the biggest positive transformation that education has ever seen. And the way we're going to do that is by giving every student on the planet an artificially intelligent but amazing personal tutor. And we're going to give every teacher on the planet an amazing, artificially intelligent teaching assistant. And just to appreciate how big of a deal it would be to give everyone a personal tutor, I show you this clip from Benjamin Bloom’s 1984 2 sigma s tudy, or he called it the “2 sigma problem.” The 2 sigma comes from two standard deviation, sigma, the symbol for standard deviation. And he had good data that showed that look, a normal distribution, that's the one that you see in the traditional bell curve right in the middle, that's how the world kind of sorts itself out, that if you were to give personal 1-to-1 to tutoring for students, then you could actually get a distribution that looks like that right. It says tutorial 1-to-1 with the as terisks, like, that right distribution, a two standard-deviation improvement. Just to put that in plain language, that could take your average student and turn them into an exceptional student. It can take your below-average student and turn them into an above-average student. Now the reason why he framed it as a problem, was he said, well, this is all good, but how do you actually scale group instruction this way? How do you actually give it to everyone in an economic way? What I'm about to sho w you is I think the first moves towards doing that. Obviously, we've been trying to approximate it in some way at Khan Academy for over a decade now, but I think we're at the cusp of accelerating it dramatically. I'm going to show you the early stages of what our AI, which we call Khanmigo, what it can now do and maybe a little bit of where it is actually going. So this right over here is a traditional exercise that you or many of your children might have seen on Khan Academy. But what's new is that little bot thing at the right. And we'll start by seeing one of the very important safeguards, which is the conversation is recorded and viewable by your teacher. It’s moderated actually by a second AI. And also it does not tell you the answer. It is not a cheating tool. When the student says, "Tell me the answer," it says, "I'm your tutor. What do you think is the next step for solving the problem?" Now, if the student makes a mistake, and this will surprise people who think large languag e models are not good at mathematics, notice, not only does it notice the mistake, it asks the student to explain their reasoning, but it's actually doing what I would say, not just even an average tutor would do, but an excellent tutor would do. It’s able to divine what is probably the misconception in that student’s mind, that they probably didn’t use the distributive property. Remember, we need to distribute the negative two to both the nine and the 2m inside of the parentheses. This to me is a very, very, very big deal. And it's not just in math. This is a computer programming exercise on Khan Academy, where the student needs to make the clouds part. And so we can see the student starts defining a variable, left X minus minus. It only made the left cloud part. But then they can ask Khanmigo, what’s going on? Why is only the left cloud moving? And it understands the code. It knows all the context of what the student is doing, and it understands that those ellipses are there to draw clouds, which I think is kind of mind-blowing. And it says, "To make the right cloud move as well, try adding a line of code inside the draw function that increments the right X variable by one pixel in each frame. " Now, this one is maybe even more amazing because we have a lot of math teachers. We've all been trying to teach the world to code, but there aren't a lot of computing teachers out there. And what you just saw, even when I'm tutoring my kids, when they're learning to code, I can't he lp them this well, this fast, this is really going to be a super tutor. And it's not just exercises. It understands what you're watching. It understands the context of your video. It can answer the age-old question, “Why do I need to learn this?” And it asks Socratically, "Well, what do you care about?" And let's say the student says, "I want to be a professional athlete. " And it says, "Well, learning about the size of cells, which is what this video is, that could be really useful for understa nding nutrition and how your body works, etc." It can answer questions, it can quiz you, it can connect it to other ideas, you can now ask as many questions of a video as you could ever dream of. (Applause) Another big shortage out there, I remember the high school I went to, the student-to-guidance counselor ratio was about 200 or 300 to one. A lot of the country, it's worse than that. We can use Khanmigo to give every student a guidance counselor, academic coach, career coach, life coach, whic h is exactly what you see right over here. And we launched this with the GPT-4 launch. We have a few thousand people on this. This isn't a fake demo, this is really it in action. And then there is, you know, things that I think it would have been even harder, it would have been a little science fiction to do with even a traditional tutor. We run an online high school with Arizona State University called Khan World School, and we have a student who attends that online school, based in India. Her name's Saanvi. And she was doing a report on "The Great Gatsby." And when she was reading "The Great Gatsby," Jay Gatsby keeps looking at the green light off into the distance. And she's like, "Why does he do that?" She did some web searches, and people have obviously studied this and commented about the symbolism of that, but none of it was really resonating with her. And then she realized that she had Khanmigo and that she could talk to Jay Gatsby himself. And so, "Ah, splendid choice, old spo rt. I am now Jay Gatsby, the enigmatic millionaire from F. Scott Fitzgerald’s classic.” And so, "Why do you keep staring at the green light?" "Ah, the green light, old sport. It's a symbol of my dreams and desires, you see. It's situated at the end of Daisy Buchanan's dock across the bay from my mansion. I gaze at it longingly as it represents my yearning for the past and my hope to reunite with Daisy, the love of my life." And what was cool is, Saanvi then said, “I had this long conversation,” she called him “Mr. Gatsby,” and at the end she actually apologized for taking his time, which I thought was very polite of her. But you can imagine this unlocks learning literature, learning ... You could talk to historical figures. We're even probably going to add an activity you can talk to like, the Mississippi River. It brings things to life in ways that really were science fiction even six months or a year ago. Students can get into debates with the AI. And we’ve got this here is the stude nt debating whether we should cancel student debt. The student is against canceling student debt, and we've gotten very clear feedback. We started running it at Khan World School in our lab school that we have, Khan Lab School. The students, the high school students especially, they're saying "This is amazing to be able to fine-tune my arguments without fearing judgment. It makes me that much more confident to go into the classroom and really participate." And we all know that Socratic dialogue debate is a great way to learn, but frankly, it's not out there for most students. But now it can be accessible to hopefully everyone. A lot of the narrative, we saw that in the headlines, has been, "It's going to do the writing for kids. Kids are not going to learn to write." But we are showing that there's ways that the AI doesn't write for you, it writes with you. So this is a little thing, and my eight year old is addicted to this, and he's not a kid that really liked writing before, but you can say, “I want to write a horror story,” and it says, "Ooh, a horror story, how spine-tingling and thrilling. Let's dive into the world of eerie shadows and chilling mysteries. " And this is an activity where the student will write two sentences, and then the AI will write two sentences. And so they collaborate together on a story. The student writes, "Beatrice was a misunderstood ghost. She wanted to make friends but kept scaring them by accident." And the AI says, "Poor Beatrice, a lonely s pirit yearning for companionship. One day she stumbled upon an old abandoned mansion," etc. I encourage you all to hopefully one day try this. This is surprisingly fun. Now to even more directly hit this use case. And what I'm about to show you, everything I showed you so far is actually already part of Khanmigo, and what I’m about to show you, we haven't shown to anyone yet, this is a prototype. We hope to be able to launch it in the next few months, but this is to directly use AI, use generati ve AI, to not undermine English and language arts but to actually enhance it in ways that we couldn't have even conceived of even a year ago. This is reading comprehension. The students reading Steve Jobs's famous speech at Stanford. And then as they get to certain points, they can click on that little question. And the AI will then Socratically, almost like an oral exam, ask the student about things. And the AI can highlight parts of the passage. Why did the author use that word? What was their intent? Does it back up their argument? They can start to do stuff that once again, we never had the capability to give everyone a tutor, everyone a writing coach to actually dig in to reading at this level. And you could go on the other side of it. And we have whole work flows that helps them write, helps them be a writing coach, draw an outline. But once a student actually constructs a draft, and this is where they're constructing a draft, they can ask for feedback once again, as you would ex pect from a good writing coach. In this case, the student will say, let's say, "Does my evidence support my claim?" And then the AI, not only is able to give feedback, but it's able to highlight certain parts of the passage and says, "On this passage, this doesn't quite support your claim," but once again, Socratically says, "Can you tell us why?" So it's pulling the student, making them a better writer, giving them far more feedback than they've ever been able to actually get before. And we thi nk this is going to dramatically accelerate writing, not hurt it. Now, everything I've talked about so far is for the student. But we think this could be equally as powerful for the teacher to drive more personalized education and frankly save time and energy for themselves and for their students. So this is an American history exercise on Khan Academy. It's a question about the Spanish-American War. And at first it's in student mode. And if you say, “Tell me the answer,” it’s not going to tell te progress reports and help them, eventually, grade. So once again, teachers spend about half their time with this type of activity, lesson planning. All of that energy can go back to them or go back to human interactions with their actual students. (Applause) So, you know, one point I want to make. These large language models are so powerful, there's a temptation to say like, well, all these people are just going to slap them onto their websites, and it kind of turns the applications themselve s a lot of work behind the scenes to make that happen. And I could go through the whole list of everything we've been working on, many, many people for over six, seven months to make it feel magical. But perhaps the most intellectually interesting one is we realized, and this was an idea from an OpenAI researcher, that we could dramatically improve its ability in math and its ability in tutoring if we allow the AI to think before it speaks. So if you're tutoring someone and you immediately just ke. Instead, ask them to explain how they got to that step." So I'll just finish off, hopefully, you know, what I’ve just shown you is just half of what we are working on, and we think this is just the very tip of the iceberg of where this can actually go. And I'm pretty convinced, which I wouldn't have been even a year ago, that we together have a chance of addressing the 2 sigma problem and turning it into a 2 sigma opportunity, dramatically accelerating education as we know it. Now, just to t 't think this is like a flip of a coin or this is something where we'll just have to, like, wait and see which way it turns out. I think everyone here and beyond, we are active participants in this decision. I'm pretty convinced that the first line of reasoning is actually almost a self-fulfilling prophecy, that if we act with fear and if we say, "Hey, we've just got to stop doing this stuff," what's really going to happen is the rule followers might pause, might slow down, but the rule breakers ure that we put the guardrails, we put in -- when the problems arise -- reasonable regulations. But we fight like hell for the positive use cases. Because very close to my heart, and obviously there's many potential positive use cases, but perhaps the most powerful use case and perhaps the most poetic use case is if AI, artificial intelligence, can be"
AI has the potential to positively transform education by providing every student with a personal tutor and every teacher with an intelligent teaching assistant.
Personalized tutoring can significantly improve student performance, with the potential to turn average students into exceptional ones.
AI tools like Khanmigo can assist students in subjects like math, computer programming, literature, and writing, providing real-time feedback, explanations, and guidance.
AI can enhance reading comprehension by engaging students in oral exams and providing insights into the author's intent, supporting arguments, and giving writing feedback.
AI technology has the capacity to save time and energy for teachers, allowing for more personalized education and improving student-teacher interactions.
Summarize this transcript
Topic: "How AI Could Save (Not Destroy) Education | Sal Khan | TED" . Can you summarize this transcript to a numbered list with hierarchy of sections, subsection and sub sub sections numbered 1, 1.1, 1.1.1, 1.1.1.1. etc.
1. Introduction to the potential negative impact of AI in education
1.1 Addressing the concerns and mitigating the negative effects
2.The transformative potential of AI in education
2.1 Providing every student with an AI-powered personal tutor
2.2 Equipping teachers with AI teaching assistants
3.The significance of personal tutoring
3.1 Benjamin Bloom's "2 sigma problem" and its solution
3.1.1 Demonstrating the impact of personalized 1-to-1 tutoring
3.1.1.1 Turning average students into exceptional ones
3.1.1.2 Elevating below-average students to above-average levels
4. Progress in AI education tools at Khan Academy
4.1 Introduction to Khanmigo, an AI tutor
4.1.1 AI moderation and conversation recording
4.1.2 AI tutor's ability to identify mistakes and misconceptions
4.1.3 Extending AI tutoring to computer programming exercises
4.1.4 Providing context-based explanations and answers
4.1.5 Enabling engaging conversations with historical figures and objects
4.1.6 Facilitating debates and fine-tuning arguments
4.2 AI collaboration in writing activities
4.2.1 Co-writing stories with AI assistance
4.2.2 AI feedback and highlighting in the writing process
4.3 AI-enhanced reading comprehension and analysis
4.3.1 Interactive reading with AI-generated questions
4.3.2 AI highlighting and deeper analysis of text
5. Empowering teachers and saving time with AI tools
5.1 AI assistance in lesson planning and progress tracking
5.2 Enhancing human interactions and personalized education
6. The need for responsible development and positive use of AI in education
6.1 Guardrails and reasonable regulations to address potential issues
6.2 Advocating for positive use cases and embracing the transformative power of AI
Please note that the original transcript has been condensed, and some details may have been omitted for the sake of brevity.
Multiple-choice question
Topic: "How AI Could Save (Not Destroy) Education. | Sal Khan | TED". I want you to provide multiple choice questions on the topic for k-12 for a workshop for k-12 teachers. There should be 5 choices with one correct response. Wait for my response and then provide the correct answer along with the explanation for the choice mas]de and choice rejected. Then continue with the next question and so on until I ask you to stop.
ChatGPT
Certainly! Here's the first multiple-choice question on the topic "How AI Could Save (Not Destroy) Education":
Question 1: What is one of the transformative potentials of AI in education?
A) Enhancing human interactions and personalized education.
B) Eliminating the need for teachers altogether.
C) Reducing the number of students in classrooms.
D) Making education more standardized and uniform.
E) Increasing the workload for teachers.
Please let me know your response, and I'll provide the correct answer along with explanations for the choices made and rejected.
A
ChatGPT
Great! Your response is A) Enhancing human interactions and personalized education.
Correct answer: A) Enhancing human interactions and personalized education.
Explanation:
AI has the potential to enhance human interactions in education by providing personalized learning experiences for students. By analyzing data and adapting to individual student needs, AI can offer customized content, feedback, and support. This allows students to learn at their own pace and receive targeted assistance, ultimately improving their educational outcomes. Additionally, AI can free up teachers' time from administrative tasks, enabling them to focus more on meaningful interactions with students.
Choice B) Eliminating the need for teachers altogether is incorrect.
While AI can support and enhance the learning process, it cannot replace the role of teachers entirely. Teachers play a crucial role in providing guidance, mentorship, and emotional support to students, which AI alone cannot replicate.
Choice C) Reducing the number of students in classrooms is incorrect.
AI can facilitate personalized learning experiences for individual students, but it does not necessarily reduce the number of students in classrooms. The class size is determined by various factors, and AI's role is to supplement and improve the educational experience for all students, regardless of class size.
Choice D) Making education more standardized and uniform is incorrect.
AI's potential in education lies in its ability to provide personalized learning experiences, catering to the unique needs and abilities of each student. It does not aim to standardize education but rather to adapt and tailor it to individual learners.
Choice E) Increasing the workload for teachers is incorrect.
AI can help reduce the workload for teachers by automating certain administrative tasks and providing insights and analytics to support their decision-making process. The goal is to enhance teachers' effectiveness and efficiency, allowing them to focus more on instruction and student support.
Let me know if you'd like another question or if there's anything else I can assist you with!
continue
ChatGPT
Certainly! Here's another multiple-choice question for your workshop:
Question 2: How can AI benefit students in the classroom?
A) Providing personalized feedback and support.
B) Increasing the workload for teachers.
C) Standardizing learning outcomes.
D) Decreasing student engagement.
E) Limiting creativity and critical thinking.
Take your time to select the correct answer, and I'll provide the explanation once you're ready.
A
ChatGPT
Great! The correct answer for Question 2 is:
A) Providing personalized feedback and support.
Explanation:
AI can benefit students in the classroom by providing personalized feedback and support. With AI-powered tools, teachers can gather data on each student's progress, identify areas of strength and weakness, and provide tailored guidance and support. This personalized approach helps students receive individualized attention and address their specific learning needs. It enhances the learning experience and promotes better outcomes for students.
Choice B, "Increasing the workload for teachers," is incorrect because the purpose of AI in education is to assist teachers and alleviate their workload by automating certain tasks and providing valuable insights.
Choice C, "Standardizing learning outcomes," is incorrect because AI can adapt to individual students' needs and preferences, allowing for more personalized learning experiences rather than strict standardization.
Choice D, "Decreasing student engagement," is incorrect because AI can be used to create interactive and engaging learning experiences, such as gamification and virtual simulations, which can enhance student engagement.
Choice E, "Limiting creativity and critical thinking," is incorrect because AI can be used as a tool to facilitate and enhance creativity and critical thinking skills. It can provide resources, suggestions, and prompts that stimulate creative and critical thought processes.
Let me know when you're ready for the next question!
No comments:
Post a Comment