أي شخص كان منتبهًا خلال الأشهر القليلة الماضية كان يرى عناوين مثل هذه، خاصة في التعليم. كان الطرح: سيستخدم الطلاب ChatGPT وأشكال أخرى من الذكاء الاصطناعي للغش، وللقيام بمهامهم. لن يتعلموا. وسوف يقوض ذلك التعليم كما نعرفه.
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.
الآن، ما سأناقشه اليوم ليس فقط أن هناك طرق للتخفيف من كل ذلك، إذا وضعنا الضوابط المناسبة، وفعلنا الأشياء الصحيحة، فيمكن تخفيف خطورته. لكنني أعتقد أننا على وشك استخدام الذكاء الاصطناعي في ما ربما سيكون التحول الإيجابي الأكبر الذي شهده التعليم من أي وقت مضى. والطريقة التي سنفعل بها ذلك هي من خلال إعطاء كل طالب على هذا الكوكب معلماً شخصياً بذكاء اصطناعي مذهل. وسنقدم لكل معلم على هذا الكوكب، مساعد تدريس بذكاء الاصطناعي.
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 think 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.
وفقط لتقدير حجم الصفقة التي ستكون من توفير معلمًا شخصيًا للجميع، أريد أن أعرض عليكم هذا المقطع من دراسة بنجامين بلوم لعام 1984 لمسألة 2 سيجما، أو أطلق عليها اسم "مشكلة 2 سيجما". تأتي 2 سيجما من درجتي الانحراف المعياري، سيجما، رمز الانحراف المعياري. كانت لديه بيانات جيدة ظهرت بهذا الشكل، توزيع طبيعي، هذا الذي تراه هو منحنى الجرس التقليدي في المنتصف، هكذا العالم نوعًا ما يفرز نفسه، إذا كنت ستعطي لكل طالب مدرس خاص، فستحصل على توزيع يبدو كهذا. نقول لكل طالب مدرس خاص مع ملاحظة، لمثل هذا التوزيع الأيمن، تحسن درجتين من الانحراف المعياري.
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 study, 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 asterisks, like, that right distribution, a two standard-deviation improvement.
فقط لوضع ذلك بلغة واضحة، يمكن أن نأخذ الطالب ذو المستوي المتوسط وتحويله إلى طالب استثنائي. يمكن أن تأخذ طالب ذو مستوي أقل من المتوسط وتحويله إلى طالب ذي مستوي فوق المتوسط.
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.
الآن السبب الذي جعله يصورها كمشكلة، هو أنه قال، حسنًا، كل هذا جيد، لكن كيف يمكنك بالفعل توسيع نطاق تعليمات المجموعة بهذه الطريقة؟ كيف توفرها للجميع بطريقة اقتصادية؟
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?
أنا على وشك أن أريكم الخطوات الأولى للقيام بذلك من الواضح أننا كنا نحاول الاقتراب منه بطريقة ما في أكاديمية خان لأكثر من عقد حتى الآن، لكن أعتقد أننا على أعتاب تسريعها بشكل كبير. سأريكم المراحل الأولى لما لدينا من الذكاء الاصطناعي، التي نسميها Khanmigo، ما يمكن أن يفعله الآن وإلى أين نتجه بالفعل.
What I'm about to show 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.
هذا تمرين تقليدي أنتم أو العديد من أطفالكم ربما رأيتوه في أكاديمية خان. لكن الجديد هو هذا ال bot على اليمين. وسنبدأ برؤية أحد الضمانات المهمة للغاية، وهي المحادثة المسجلة والتي يمكن لمعلمك مشاهدتها. يتم الإشراف عليها بواسطة ذكاء اصطناعي ثانٍ. إنه لا يخبرك بالإجابة. إنها ليست أداة غش. عندما يقول الطالب، “أخبرني الإجابة،” يقول، “أنا مدرسك. ما هي الخطوة التالية لحل المشكلة؟”
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?"
الآن، إذا أخطأ الطالب، وهذا سيفاجئ الناس الذين يظنون أن “النماذج اللغوية الكبيرة” ليست جيدة في الرياضيات، لم يلاحظ الخطأ فقط، بل يطلب من الطالب أن يشرح تفكيره، في الواقع ما يقوم به، لا يقارن بالمعلم العادي، بل بالمعلم الممتاز. إنه قادر على التكهن بما هو على الأرجح الاعتقاد الخاطئ في عقل ذلك الطالب، أنه ربما لم يستخدم خاصية التوزيع. تذكر أننا بحاجة إلى توزيع سالب اثنين إلى كل من 9 و 2م في داخل الأقواس. هذا بالنسبة لي هو شأنٌ كبيرٌ جداً جداً. وهذا ليس فقط في الرياضيات.
Now, if the student makes a mistake, and this will surprise people who think large language 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.
هذا تمرين برمجة كمبيوتر في أكاديمية خان، حيث يحتاج الطالب لجعل الغيوم تتفرق. وهكذا يمكننا أن نرى الطالب يبدأ تحديد متغير، يسار X ناقص ناقص. جعل الجزء الأيسر من السحاب يتحرك. ولكن يمكنهم أن يسألوا Khanmigo، ماذا يحدث هنا؟ لماذا تتحرك السحابة اليسرى فقط؟ وهو يفهم الكود. يعرف كل السياق الذي يفعله الطالب، ويدرك أن تلك الأشكال البيضوية هنا لرسم الغيوم، وهو ما أعتقد أنه أمر مذهل نوعًا ما. ويقول:“لتحرك السحابة اليمين، حاول إضافة سطر من التعليمات البرمجية داخل وظيفة السحب التي تزيد من المتغير X بمقدار بكسل واحد في كل إطار“.
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."
الآن، ربما يكون هذا أكثر روعة لأنه لدينا الكثير من معلمي الرياضيات. لقد حاولنا جميعًا تدريس البرمجة، لكن ليس هناك الكثير من معلمي البرمجة. وما رأيتم للتو، حتى أنا عندما أقوم بتدريس أطفالي، عندما يتعلمون البرمجة، لا أستطيع مساعدتهم جيدًا بهذه السرعة، سيكون هذا حقًا مدرسًا رائعًا.
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 help them this well, this fast, this is really going to be a super tutor.
وهي ليست مجرد تمارين. إنه يفهم ما تشاهده. يفهم سياق الفيديو الخاص بك. يمكن أن يجيب على السؤال القديم، "لماذا أحتاج إلى تعلم هذا؟" ويسأل بطريقة سقراطية، “حسنًا، ما الذي تهتم به؟” ولنفترض أن الطالب يقول، “أريد أن أصبح رياضياً محترفاً.” فيقول، “حسنًا، تعلم حجم الخلايا، الذي هو محتوى هذا الفيديو، يمكن أن يكون مفيدًا حقًا لفهم التغذية وكيف يعمل جسمك، وما إلى ذلك " يمكن أن يجيب على الأسئلة، ويمكن أن يختبرك، يمكنه ربط أفكار بأخرى، يمكنك أن تسأل الآن العديد من الأسئلة في الفيديو كما كنت تحلم به.
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 understanding 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.
(تصفيق)
(Applause)
نقص كبير آخر هناك، أتذكر المدرسة الثانوية التي درست بها، نسبة المرشد الطلابي إلى التوجيه كان حوالي 200 أو 300 إلى واحد. في الكثير من البلاد إنه أسوأ من ذلك. يمكننا استخدام Khanmigo لإعطاء كل طالب مستشاراً توجيهاً، مدرباً أكاديمياً، مدرباً مهنياً، مدرب حياة، وهو بالضبط ما ترونه هنا. وقد أطلقنا هذا مع إطلاق GPT-4. لدينا بضعة آلاف شخص يعملون في هذا الشأن. هذا ليس عرضًا توضيحيًا مزيفًا، هذا هو المنتج الحقيقي.
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, which 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.
ثم هناك، كما تعلم، الأشياء التي أعتقد أنها ستكون الأصعب، التي كان من الخيال العلمي القيام بها حتى مع مدرس تقليدي. نحن ندير مدرسة ثانوية على الإنترنت مع جامعة ولاية أريزونا تسمى مدرسة خان العالمية، ولدينا طالبة تدرس في تلك المدرسة عبر الإنترنت وهي تقيم في الهند. اسمها سانفي. وكانت تقوم بعمل تقرير عن “غاتسبي العظيم“. وعندما كانت تقرأ “غاتسبي العظيم،” كان جاي كاتسبي يواصل البحث عن الضوء الأخضر بعيدًا في الأفق. وهي تقول، "لماذا يفعل ذلك؟" أجرت بعض عمليات البحث على الويب، ومن الواضح أن الناس قد درسوا هذا وعلقوا على رمزية ذلك، لكن لم يكن لأي منها صدى معها. ثم أدركت أن لديها Khanmigo وأنها يمكن أن تتحدث لجاي جاتسبي نفسه.
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.
وهكذا، رد “آه، خيار رائع، يا صاح. أنا الآن جاي غاتسبي، المليونير الغامض من كلاسيكيات إف سكوت فيتزجيرالد“.
And so, "Ah, splendid choice, old sport. I am now Jay Gatsby, the enigmatic millionaire from F. Scott Fitzgerald’s classic.”
“لماذا تستمر في التحديق على الضوء الأخضر؟ ”
And so, "Why do you keep staring at the green light?"
“آه، الضوء الأخضر، يا صاح. إنه رمز لأحلامي ورغباتي، كما ترين. إنه يقع في نهاية رصيف ديزي بوكانان عبر الخليج من قصري. أنا أحدق في ذلك بشوق لأنه يمثل شوقي للماضي وآمل أن ألتقي مع ديزي، حب حياتي.”
"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."
وألم يكن هذا رائعًا، قالت “سانفي” بعد ذلك، “لقد أجريت هذه المحادثة الطويلة،” اتصلت ب “السيد/ غاتسبي ” وفي النهاية اعتذرت بالفعل لأخذ وقته، الذي اعتقدت أنه كان فعلاً مهذبًا جدًا منها.
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.
لكن يمكنكم تخيل كم عدد الفرص التي يتيحها لتعلم الأدب، الخ... يمكنك التحدث إلى الشخصيات التاريخية. نحن على الأرجح سنضيف نشاط يمكنك التحدث فيه إلى نهر المسيسيبي. إنه يجلب الأشياء إلى الحياة بطرق كانت من الخيال العلمي حتى قبل ستة أشهر أو عام.
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.
يمكن للطلاب الدخول في مناقشات مع الذكاء الاصطناعي. ولدينا هنا مناظرة الطلاب في ما إذا كان علينا إلغاء ديون الطلاب. الطلاب ضد إلغاء ديون الطلاب، وحصلنا على تعليقات واضحة جدًا. بدأنا تشغيله في مدرسة خان العالمية في المختبر لدينا، معمل مدرسة خان. طلاب المدرسة الثانوية على وجه الخصوص، يقولون “إنه لأمر مدهش أن أكون قادرًا على ضبط حججي دون خوف من الحكم. يجعلني أكثر ثقة للذهاب إلى الفصل والمشاركة“. وكلنا نعرف ذلك الحوار السقراطي والنقاش هو وسيلة رائعة للتعلم، لكن بصراحة، ليس متاح لمعظم الطلاب. ولكن الآن يمكن الحصول عليه للجميع.
Students can get into debates with the AI. And we’ve got this here is the student 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.
الكثير من السرد، الذي رأيناه في العناوين الرئيسية، "ستقوم بالكتابة للأطفال. لن يتعلم الأطفال الكتابة“. لكننا نظهر أن هناك طرقًا في جعل الذكاء الاصطناعي لا يكتب لك، بل يكتب معك.
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.
لذلك هذا شيء صغير، وطفلي ذو الثماني سنوات مدمن على هذا، وهو ليس الطفل الذي كان يحب الكتابة من قبل، لكن يمكنك قول "أريد أن أكتب قصة رعب،" ويقول، “آه، قصة رعب، الكثير من الإثارة. دعنا نغوص في عوالم الظلال المخيفة وألغاز تقشعر لها الأبدان“. وهذا نشاط سيكتب الطالب جملتين، ومن ثم سيكتب الذكاء الاصطناعي جملتين. ولذا فهم يتعاونون معًا في قصة.
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.
يكتب الطالب، “كانت بياتريس شبحًا أسيء فهمه. أرادت تكوين صداقات لكنها استمرت في إخافتهم بالصدفة“.
The student writes, "Beatrice was a misunderstood ghost. She wanted to make friends but kept scaring them by accident."
ويقول الذكاء الاصطناعي، “بياتريس المسكينة، وحيدة ومشتاقة للرفقة. ذات يوم عثرت على قصر قديم مهجور“، إلخ.
And the AI says, "Poor Beatrice, a lonely spirit yearning for companionship. One day she stumbled upon an old abandoned mansion," etc.
أشجعكم جميعا أن تجربوا هذا يومًا ما. هذا ممتع بشكل مدهش.
I encourage you all to hopefully one day try this. This is surprisingly fun.
لشرح مباشر أكثر لحالة الاستخدام هذه. ما أنا على وشك أن أريكم إياه، وكل ما عرضته عليك حتى الآن هو بالفعل جزء من Khanmigo، وما أنا على وشك أن أريكم إياه، لم نعرضه لأي شخص حتى الآن، هذا نموذج أولي. نأمل أن نتمكن من إطلاقه في الأشهر القليلة المقبلة، باستخدام الذكاء الاصطناعي مباشرةً، باستخدام تقنية الذكاء الاصطناعي التوليفي، لعدم تقويض اللغة الإنجليزية ومهارات اللغة ولكن في الواقع لتحسينها بطرق لم نتمكن من الحصول عليها بل حتى تصورها قبل عام. تمارين فهم القراءة. الطلاب يقرؤون خطاب ستيف جوبز المشهور في ستانفورد. وبعد ذلك عندما يصلون إلى نقاط معينة، يمكنهم النقر فوق هذا السؤال الصغير. وسوف يقوم الذكاء الاصطناعي بطريقة سقراطية، تقريبا مثل الامتحان الشفوي، بسؤال الطلاب عن أشياء. ويمكن للذكاء الاصطناعي أن يبرز أجزاء من المقطع. لماذا استخدم المؤلف تلك الكلمة؟ ماذا كانت نواياه؟ هل يدعم حجته؟ يمكنهم البدء في فعل أشياء، لم تكن لدينا القدرة لها، كإعطاء معلم للجميع، كل شخص مدرب كتابة للبحث في الواقع عن القراءة على هذا المستوى.
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 generative 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.
ويمكنك البحث عن الجانب الآخر منه. ولدينا تدفقات عمل كاملة تساعدهم على الكتابة، تساعدهم على أن يكونوا مدربين للكتابة، يحددون مخطط الكتابة. ولكن عندما يبني الطالب المسودة، وهذا هو المكان الذي ينشئون فيه مسودة، يمكنهم طلب التعليقات، كما تتوقع من مدرب كتابة جيد. في هذه الحالة الطالب سيقول، "هل يدعم دليلي ادعائي؟" ثم الذكاء الاصطناعي، ليس فقط قادر على إبداء الرأي، بل قادر على إبراز أجزاء معينة من المقطع ويقول، “في هذا المقطع، هذا لا يدعم ادعائك تمامًا،” لكن مرة أخرى، يقول سقراطي، “هل يمكنك أن تخبرنا لماذا؟” لذا فهي تجذب الطالب، لما سيجعله كاتبًا أفضل، مما يمنحه المزيد من التعليقات أكثر من أي وقت مضى. ونعتقد أن هذا سوف يحدث تحسن في الكتابة بشكل كبير، ولا يضر بها.
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 expect 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 think this is going to dramatically accelerate writing, not hurt it.
كل ما تحدثت عنه حتى الآن هو للطالب. لكننا نعتقد أن هذا يمكن أن يكون بنفس الأثر للمعلم لقيادة تعليم أكثر تخصيصًا وتوفير الوقت والطاقة لأنفسهم ولطلابهم. تمرين في التاريخ الأمريكي من أكاديمية خان. انه سؤال حول الحرب الإسبانية الأمريكية. وفي البداية تكون في وضع الطالب. وإذا قلت، “قل لي الإجابة،” فلن يخبرك بالإجابة. سوف ننتقل إلى وضع التدريس. لكن مع هذا التبديل الصغير الذي يمكن للمدرسين فعله، يمكنهم إيقاف وضع الطالب والانتقال إلى وضع المعلم. وما يفعله هذا هو أنه يتحول إلى -- يمكنك أن تنظر إليه على أنه دليل للمعلم حول المنشطات. لا يمكنه فقط شرح الإجابة، بل يمكن أن يشرح كيف يمكن أن تعلمها. يمكن أن يساعد في اعداد المعلم لتلك المادة. يمكن أن يساعدهم في وضع خطط الدروس، كما ترون تفعل هناك. سوف يساعدهم في النهاية في إنشاء تقارير التقدم ومساعدتهم في وضع الدرجات. لذا مرة أخرى، ينفق المعلمون حوالي نصف وقتهم مع هذا النوع من النشاط، لتخطيط الدرس. كل هذه الطاقة يمكن أن تعود إليهم أو العودة إلى التفاعلات البشرية مع طلابهم الفعليين.
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 the answer. It's going to go into tutoring mode. But that little toggle which teachers have access to, they can turn student mode off and then it goes into teacher mode. And what this does is it turns into -- You could view it as a teacher's guide on steroids. Not only can it explain the answer, it can explain how you might want to teach it. It can help prepare the teacher for that material. It can help them create lesson plans, as you could see doing right there. It'll eventually help them create 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.
(تصفيق)
(Applause)
لذا، كما تعلمون، أود أن أوضح نقطة واحدة. هذه النماذج اللغوية الكبيرة قوية جدا، هناك إغراء للقول، حسنًا، أن كل هؤلاء الناس سيذهبون إليها في الويب، وهو ما يحول التطبيقات إلى سلع. وما علي أن أخبرك به هو أحد أسباب لماذا لم أنم لمدة أسبوعين عندما تمكنت من الوصول لأول مرة إلى GPT-4 في أغسطس. أدركنا بسرعة أن هذا سيجعله ساحرًا بالفعل، أعتقد ما رأيتم مع Khanmigo، لم يتفاعل معكم بالطريقة التي تفاعل ChatGPT. كان الأمر أكثر سحرية، كان أكثر سقراطية، واضح أنه أفضل بكثير في الرياضيات مما ظن معظم الناس. والسبب هو كان هناك الكثير من العمل وراء الكواليس لتحقيق ذلك.
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 themselves into commodities. And what I've got to tell you is that’s one of the reasons why I didn’t sleep for two weeks when I first had access to GPT-4 back in August. But we quickly realized that to actually make it magical, I think what you saw with Khanmigo a little bit, it didn't interact with you the way that you see ChatGPT interacting. It was a little bit more magical, it was more Socratic, it was clearly much better at math than what most people are used to thinking. And the reason is, there was a lot of work behind the scenes to make that happen.
ويمكنني استعراض القائمة بأكملها من كل شيء كنا نعمل عليه، كثير، كثير من الناس لأكثر من ستة- سبعة أشهر لجعله يبدو سحري. ولكن ربما الأكثر اثارة للاهتمام فكريا هو أننا أدركنا، وكانت هذه الفكرة من بحث OpenAI، يمكننا تحسين بشكل كبير قدرته في الرياضيات وقدرته في التدريس إذا سمحنا للذكاء الاصطناعي بالتفكير قبل أن يتكلم. إذا كنت تقوم بتدريس شخص ما وبدأت بالحديث فورًا قبل أن تقيم رياضياتهم، فقد لا تفهم بشكل صحيح. ولكن إذا قمت ببناء أفكار لنفسك، وما تراه على اليمين هناك مفكرة فعلية للذكاء الاصطناعي، شيء يولده لنفسه لكنه لا يشاركه مع الطالب. رفعت دقته بشكل كبير، وقدرته على أن يكون مدرسًا على مستوى عالمي ارتفعت بشكل كبير. ويمكنك أن ترى أنه يتحدث لنفسه هنا. يقول، “حصل الطالب على إجابة مختلفة عني، لكن لا تخبرهم أنه أخطأ. بدلاً من ذلك، اطلب منهم التوضيح كيف وصلوا إلى تلك الخطوة ".
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 start talking before you assess their math, you might not get it right. But if you construct thoughts for yourself, and what you see on the right there is an actual AI thought, something that it generates for itself but it does not share with the student. then its accuracy went up dramatically, and its ability to be a world-class tutor went up dramatically. And you can see it's talking to itself here. It says, "The student got a different answer than I did, but do not tell them they made a mistake. Instead, ask them to explain how they got to that step."
لذلك سوف أنهي للتو، وآمل، ما رأيتموه للتو هو نصف ما نعمل عليه فقط، ونعتقد أن هذا غيض من فيض إلى أين يمكن أن نذهب مع هذا في الواقع. وأنا مقتنع تمامًا، بما لم أكن مقتنع به قبل عام، أن لدينا فرصة لمعالجة مشكلة 2 سيجما وتحويلها إلى فرصة 2 سيجما، يتسارع التعليم بشكل كبير عن ما نعرفه.
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.
الآن، فقط لأخذ خطوة إلى الوراء على مستوى واسع، واضح أننا سمعنا الكثير اليوم، نقاشات من كلا الجانبين. هناك أشخاص يتخذون نظرة أكثر تشاؤماً للذكاء الاصطناعي، يقولون هذا مخيف، كل هذه السيناريوهات البائسة، ربما نريد أن نبطئ، ونريد أن نتوقف. على الجانب الآخر، هناك أناس أكثر تفاؤلاً يقولون لقد مررنا بنقاط الانعطاف هذه من قبل، لقد مررنا بالثورة الصناعية. كان الأمر مخيفًا، لكن نجحنا. وما سأجادل به الآن لا أعتقد أن هذا مثل رمي لعملة أو شيء يتعين علينا فيه فقط، الانتظار والنظر إلى الطريقة التي ستظهر. أعتقد أن الجميع هنا وبالخارج، مشاركين نشطين في هذا القرار. أنا مقتنع جدا أن السطر الأول من المنطق في الواقع نبوءة تتحقق من تلقاء نفسها، أنه إذا تصرفنا بخوف وإذا قلنا، “علينا التوقف عن القيام بهذه الأشياء،” ما سيحدث حقًا هو القاعدة التي قد يتوقف أتباعها مؤقتًا، قد تتباطأ، لكن منتهك القواعد، كما ذكر الكسندر [وانغ]، الحكومات المستبدة، المنظمات الإجرامية، سوف تتسارع فقط. وهذا يقودني إلى ما أنا مقتنع به في هذه الحالة البائسة، هو أن الجيدين لديهم أنظمة من الذكاء الصنعي أسوأ من الجهات الفاعلة السيئة.
Now, just to take a step back at a meta level, obviously we heard a lot today, the debates on either side. There's folks who take a more pessimistic view of AI, they say this is scary, there's all these dystopian scenarios, we maybe want to slow down, we want to pause. On the other side, there are the more optimistic folks that say, well, we've gone through inflection points before, we've gone through the Industrial Revolution. It was scary, but it all kind of worked out. And what I'd argue right now is I don'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, as Alexandr [Wang] mentioned, the totalitarian governments, the criminal organizations, they're only going to accelerate. And that leads to what I am pretty convinced is the dystopian state, which is the good actors have worse AIs than the bad actors.
لكنني أيضًا، تحدثت إلى المتفائلين قليلاً. لا أعتقد أن هذا يعني، أن علينا الاسترخاء وأن نأمل فقط في الأفضل. فهذا قد لا يحدث ايضا أعتقد أننا جميعا معا يجب أن نقاتل للتأكد من أننا نضع حواجز الحماية، نضعها - عندما تظهر المشاكل - لوائح حل معقولة. لكننا نحارب لحالات الاستخدام الإيجابي. لانها قريبة جدا من قلبي واضح أن هناك الكثير من حالات الاستخدام الإيجابية المحتملة، ولكن ربما تكون أقوى حالة استخدام وربما أكثر حالات الاستخدام شعرية هو إذا كان الذكاء الاصطناعي، يمكن استخدامه لتحسين الذكاء بشري، الإمكانات البشرية والغرض البشري.
But I'll also, you know, talk to the optimists a little bit. I don't think that means that, oh, yeah, then we should just relax and just hope for the best. That might not happen either. I think all of us together have to fight like hell to make sure 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 used to enhance HI, human intelligence, human potential and human purpose.
شكرًا لكم. (تصفيق)
Thank you. (Applause)