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.
Toute personne qui a fait attention ces derniers mois a pu voir des titres comme ceux-ci, notamment dans l’éducation. La thèse est la suivante : les étudiants vont utiliser ChatGPT et d’autres formes d’IA pour tricher, faire leurs devoirs. Ils ne vont pas apprendre. Et ça va complètement porter atteinte à l’éducation telle que nous la connaissons.
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.
Je vais répondre en disant que non seulement il existe des moyens de pallier à tout cela : en mettant en place les bons choix et barrières. Nous sommes à l’orée de l’utilisation de l’IA pour ce qui est probablement la plus grande transformation positive que l’éducation aie jamais connue. Et nous allons y parvenir en donnant à chaque étudiant sur la planète un tuteur personnel artificiel, intelligent et incroyable. Et nous allons donner à chaque professeur sur la planète un assistant personnel artificiel, intelligent et incroyable.
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.
Et pour bien se rendre compte de la portée de donner à tout le monde un tuteur personnel, je vais vous montrer ce schéma de 1984 de Benjamin Bloom : l’étude à deux sigmas, qu’il appelait le « problème à deux sigmas ». Les deux stigmas viennent de deux écart-types, sigma, le symbole pour l’écart-type. Et il avait de bonnes données pour montrer qu’une distribution normale, celle que vous voyez, à la courbe classique, en cloche, au milieu, c’est la façon dont le monde s’organise par lui-même, et si vous donniez un tuteur personnel à chaque étudiant, vous verriez une distribution similaire à celle à droite, « tutorial 1-to-1 », à droite, une amélioration de deux écarts-types.
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.
Pour parler plus simplement, vous transformeriez votre étudiant moyen en un étudiant exceptionnel. Vous transformeriez votre étudiant en dessous de la moyenne en un étudiant au dessus de la moyenne.
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?
La raison pour laquelle il a formulé ceci comme un problème, c’est qu’il a dit : « Tout cela est très bien, mais comment étendre cela à un groupe d’élèves ? Comment offrir ceci à tout le monde de manière économique ?
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.
Je vais vous montrer ce que je pense être une des premières étapes vers cela. Nous avons essayé de l’approcher d’une manière ou d’une autre à la Khan Academy depuis une dizaine d’années, et je pense que nous sommes à l’aube d’une amélioration drastique. Je vais vous montrer les premières choses que notre IA, que nous appelons Khanmigo, peut faire et peut-être un peu de ses futures possibilités.
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?"
Voici ici un exercice traditionnel que vous ou vos enfants ont peut-être vu sur la Khan Academy. Mais la nouveauté, c’est ce petit robot juste à droite. Nous allons commencer par découvrir une des premières barrières capitales : la conversation est enregistrée et visible par votre professeur. En fait, elle est modérée par une seconde IA. Elle ne donne pas la réponse, ce n’est pas un outil pour tricher. Si l’étudiant dit : « Dis-moi la réponse, » l’IA répond : « Je suis ton tuteur. Quelle serait l’étape suivante ? »
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.
Si l’étudiant fait une erreur - et cela va surprendre ceux qui pensent que les modèle de langue de grande taille ne sont pas bons en maths, non seulement elle repère l’erreur, elle demande à l’étudiant de lui expliquer son raisonnement, et fait en fait, je dirais qu’elle ne fait pas le travail d’un tuteur moyen, mais celui d’un excellent tuteur. Elle est capable de présager l’erreur probable que l’étudiant a en tête, qu’il n’a peut-être pas utilisé la bonne distributivité. Nous devons distribuer le 2 négatif à la fois au 9 et au 2m dans les parenthèses. C’est très, très important pour moi. Et ce n’est pas qu’en maths.
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."
Voici un exercice de programmation de la Khan Academy, où les étudiants travaillent à faire un nuage. Les étudiants commencent par définir une variable, « left X minus minus », qui ne crée que la partie gauche. Mais ils peuvent demander de l’aide à Khanmigo : pourquoi seule la partie gauche bouge ? Et elle comprend le code. Elle connait tout le contexte de ce que fait l’étudiant, et elle comprend que ces ellipses sont là pour dessiner les nuages, ce qui est révolutionnaire pour moi. Et elle dit : « Pour faire bouger la partie droite, ajoutes une ligne de code dans la fonction dessin qui incrémente la variable X droite d’un pixel par image. »
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.
C’est peut-être encore plus incroyable, nous avons beaucoup de profs de maths. Nous avons essayé d’apprendre au monde à coder, mais il n’existe pas beaucoup de professeurs d’informatique. Ce que vous venez de voir, même lorsque j’aide mes enfants à apprendre à coder, je ne peux pas les aider aussi bien ni aussi vite, et elle va vraiment être un bon tuteur.
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.
Et il ne s’agit pas que d’exercices. Elle comprend ce que vous regardez. Elle comprend le contexte de votre vidéo, répondre à l’éternelle question : « Pourquoi je dois savoir ça ? » Et à là Socrate, elle demande : « À quoi t’intéresses-tu ? » Disons que l’étudiant réponde : « Je veux devenir athlète professionnel ». Elle répond : « Et bien, comprendre la taille des cellules, le sujet de cette vidéo, peut être très utile pour comprendre la nutrition et comment ton corps fonctionne, etc. » Elle peut répondre aux questions, vous en poser, elle relie des idées, vous pouvez poser autant de questions que vous voulez au sujet d’une vidéo.
(Applause)
(Applaudissements)
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.
Autre grande pénurie - je me rappelle, quand j’allais au lycée, le ratio étudiant/conseiller d’orientation était de un pour 200 ou 300. Et dans beaucoup de régions, c’est même pire que ça. Khanmigo permet à chaque étudiant d’avoir un conseiller d’orientation, un coach scolaire, de carrière, de vie, ce qui est exactement ce que vous voyez ici. Nous avons lancé ceci avec le lancement de GPT-4 avec quelques centaines de personnes. Ce n’est pas une fausse démo, cela se passe en vrai.
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.
Et puis il y a des choses que je pensais être encore plus complexes, qui relèvent presque de la science-fiction, même avec un tuteur traditionnel. Nous gérons un lycée en ligne avec la Arizona State University, appelée Khan World School, et nous avons une étudiante qui fréquente ce lycée et qui habite en Inde. Elle s’appelle Saanvi. Elle devait faire une dissertation sur « Gatsby le Magnifique ». Et quand elle lisait « Gatsby le Magnifique », Jay Gatsby regardait continuellement vers cette lumière verte au loin. Et elle se demandait pourquoi. Elle a fait quelques recherches, et de nombreuses études existent déjà sur le symbolisme de cette action, mais rien ne lui parlait vraiment. Puis elle a réalisé qu’elle avait Khanmigo et qu’elle pouvait parler à Jay Gastby lui-même.
And so, "Ah, splendid choice, old sport. I am now Jay Gatsby, the enigmatic millionaire from F. Scott Fitzgerald’s classic.”
Et ainsi : « Ah excellent choix, vieux frère. Je suis maintenant Jay Gatsby, l’énigmatique millionaire du classique de F. Scott Fitzgerald. »
And so, "Why do you keep staring at the green light?"
« Pourquoi regardez-vous toujours la lumière verte ? »
"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."
« Ah, la lumière verte, vieux frère. Vous voyez, c’est le symbole de mes rêves et de mes désirs. Elle se trouve au bout du quai de Daisy Buchanan, de l’autre côté de la baie de mon manoir. Je la fixe avec envie car elle représente ma nostalgie du passé et mon espoir de retrouver Daisy, l’amour de ma vie. »
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.
Ce qui est cool, c’est que Saanvi a dit : « J’ai eu cette longue conversation, » - elle l’appelait « M. Gatsby », et à la fin, elle a présenté ses excuses d’avoir pris de son temps, ce qui je trouve était très poli de sa part.
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.
Vous pouvez imaginer que cela libère l’apprentissage de la littérature... Vous pourriez parler aux personnages historiques. Nous pensons ajouter une activité où vous pourriez parler à la rivière du Mississippi. Cela donne vie aux choses d’une façon qui était de la science fiction il y a encore six mois ou un an.
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.
Les étudiants peuvent débattre avec l’IA. Nous avons ici un étudiant qui débat sur l’annulation ou non de la dette étudiante. L’étudiant est contre, et nous avons un retour très clair. Nous avons commencé à l’utiliser dans notre laboratoire, le Khan Lab School. Les étudiants, et surtout ceux du lycée, nous disent : « C’est incroyable de pouvoir peaufiner mes arguments sans avoir peur d’être jugé. Cela me donne bien plus confiance en moi pour aller en cours et vraiment participer. Et nous savons tous que la maïeutique est un bon moyen d’apprendre, mais ce n’est pas disponible pour la plupart de nos étudiants. Mais maintenant, elle peut être accessible je l’espère pour tout le monde.
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.
Nous l’avons vu dans la presse, les principaux reproches sont : « Elle va écrire à la place de nos enfants, ils ne vont pas apprendre à écrire. » Mais nous montrons que l’IA n’écrit pas pour vous, mais qu’elle écrit avec vous.
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.
Voici un petit truc, mon enfant de huit ans y est accro, et pourtant il n’aimait pas trop écrire avant, mais vous pouvez dire : « Je veux écrire une histoire d’horreur, » « Ohh, une histoire d’horreur, que c’est palpitant et trépidant. Plongeons dans le monde des ombres inquiétantes et des mystères glaçants. » C’est une activité où l’étudiant va écrire deux phrases, puis l’IA va écrire deux phrases. Et ensemble, ils collaborent à créer l’histoire.
The student writes, "Beatrice was a misunderstood ghost. She wanted to make friends but kept scaring them by accident."
« Béatrice était un fantôme incompris. Elle voulait avoir des amis mais ne faisait que les effrayer sans le vouloir.
And the AI says, "Poor Beatrice, a lonely spirit yearning for companionship. One day she stumbled upon an old abandoned mansion," etc.
L’IA : « Pauvre Béatrice, esprit esseulé à la recherche de compagnons. » Un jour, elle tombe sur une vieille maison abandonnée. »
I encourage you all to hopefully one day try this. This is surprisingly fun.
Je vous encourage tous à essayer ceci un jour. C’est étonnamment amusant.
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.
Et pour étayer ceci, ce que je vais vous montrer, et tout ce que vous avez vu, est en fait déjà une partie de Khanmigo, mais cela, nous ne l’avons encore jamais montré, c’est un prototype que nous espérons pouvoir lancer bientôt, dans le but d’utiliser une IA créative, non pour nuire à la langue anglaise ou artistique, mais en réalité pour les valoriser d’une façon que nous n’aurions même pas pu imaginer il y a de cela un an. Voici une compréhension de lecture. Les étudiants lisent le célèbre discours de Steve Jobs à Stanford. Lorsqu’ils parviennent à certains moments, ils peuvent cliquer sur le bouton « Question ». Alors l’IA, de façon socratique, et presque comme un examen oral, pose des questions à l’étudiant. L’IA peut aussi surligner certains passages. Pourquoi l’auteur a-t-il utilisé ce mot ? Dans quelle intention ? Appuie-t-il son argument ? Ils peuvent faire des choses que, à nouveau - nous n’avons jamais pu donner un tuteur à chacun, de donner à tout le monde un coach qui creuse en détail la lecture.
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.
Et vous pouvez vous trouver de l’autre côté. Nous avons des processus pour les aider à écrire, les aider à être coach d’écriture, à donner les grandes lignes. Mais une fois qu’un étudiant élabore un brouillon, et c’est là qu’ils élaborent leurs brouillons, ils peuvent demander un retour, comme vous pourriez le faire avec un coach en écriture. Ici, l’étudiant pourrait dire : « Est-ce que cette preuve soutient ma thèse ? » L’IA, non seulement capable de proposer un retour, mais aussi de souligner certaines parties du passage et dira : « Ce passage ne soutient pas vraiment votre thèse, » mais aussi : « Peux-tu nous dire pourquoi ? » Cela force l’étudiant à devenir un meilleur rédacteur, lui proposant bien plus de retours qu’ils n’en ont jamais eu auparavant. Nous pensons que cela va radicalement accélérer la rédaction, non lui nuire.
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.
Tout ce dont j’ai parlé jusqu’à présent concerne les étudiants. Mais cela peut être tout aussi puissant pour les professeurs, pour les aider à offrir une éducation plus personnalisée, pour leur faire gagner du temps, de l’énergie, et pour leurs étudiants. Voici un exercice de la Khan Academy sur l’histoire américaine. Une question sur la guerre hispano-américaine. Je suis ici en mode étudiant. Si je dis : « Dis-moi la réponse », elle ne va pas me la donner. Elle va passer en mode tutorat. Mais les professeurs ont accès à ce petit bouton qui leur permet de stopper le mode étudiant et de passer un mode professeur. Et ce que cela fait ... C’est comme si vous aviez un professeur sous stéroïdes. Non seulement elle peut expliquer la réponse, mais aussi comment vous pourriez l’enseigner. Elle peut aider le professeur à préparer son matériel de cours, à créer des plans de leçons, comme vous pouvez le voir ici. Elle pourra les aider à créer des rapports de progression, et les aider à attribuer des notes. Les professeurs passent la moitié de leur temps à faire ça : préparer les leçons. Toute cette énergie pourrait leur revenir, être redirigée vers des interactions humaines avec leurs étudiants.
(Applause)
(Applaudissements)
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.
Il y a un point que je veux souligner. Ces grand modèle de langage sont si puissants, qu’il est tentant de dire que les gens vont juste les coller sur leurs sites Internet, transformant les applications en commodités. Et en réalité, je n’ai pas dormi pendant deux semaines à cause de ça, lorsque j’ai commencé à avoir accès à GPT-4, en août dernier. Mais nous avons vite compris que pour le rendre magique, je pense que vous l’avez aperçu avec Khanmigo, elle n’interagit pas avec vous de la même façon que ChatGPT le fait. Elle était un peu plus magique, un peu plus socratique, clairement meilleure en maths que ce que les gens voulaient bien admettre. Et la raison, c’est qu’il y a beaucoup de travail derrière pour que cela marche.
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."
Je pourrais lister toutes les choses sur lesquelles nous avons travaillé, beaucoup, beaucoup de gens pendant six, sept mois, pour rendre cela magique. Mais la chose la plus intéressante intellectuellement, c’est que nous avons réalisé, et c’était une idée d’un chercheur d’OpenAI, que nous pourrions considérablement améliorer son niveau en maths et sa capacité de tutorat si nous permettions à l’IA de réfléchir avant de parler. Si vous êtes le tuteur et que vous parliez immédiatement, avant d’avoir évalué le problème, vous vous tromperez peut-être. Mais si vous construisez vos propres pensées, et ce que vous voyez à droite est en fait l’IA qui réfléchit, quelque chose qu’elle génère pour elle, qu’elle ne partage pas avec l’étudiant. Sa précision s’est considérablement améliorée, ainsi que sa capacité à être un tuteur de niveau mondial. Vous pouvez la voir se parler à elle-même : « Il a une réponse différente de la mienne ; ne pas lui dire qu’il a fait une erreur. Je vais plutôt lui demander de m’expliquer comment il en est arrivé là.
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.
Pour finir, j’aimerais vous dire que ce que vous avez vu n’est que la moitié de ce sur quoi nous travaillons, et nous sommes convaincus que ce n’est que la partie émergée de l’iceberg de ce que nous pouvons réellement accomplir. Je suis certain maintenant, je ne l’étais pas il y a un an, qu’ensemble, nous avons une chance de résoudre le problème à deux sigmas et le transformer en opportunité à deux sigmas, accélérant considérablement l’éducation telle que nous la connaissons.
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.
Pour prendre un peu de recul au niveau méta, nous avons entendu beaucoup de choses aujourd’hui. Certaines personnes sont plus pessimistes quant à l’IA, la trouvent effrayante, il y a tous ces scénarios dystopiques, peut-être devrions-nous ralentir, faire une pause. De l’autre côté, il y a des personnes plus optimistiques : nous sommes déjà passé par des points d’inflection avant, nous avons vécu la révolution industrielle. C’était effrayant, mais tout a fini par fonctionner. Et l’argument que j’avancerai à présent, c’est que je ne pense pas que l’IA se joue à pile ou face, ou que ce soit quelque chose où nous devrons attendre de voir ce qui va se passer. Je pense que tout le monde ici et ailleurs, nous sommes des participants actifs de cette décision. Je suis convaincu que le premier niveau de raisonnement est en fait une prophétie auto-réalisée, que si nous agissons avec peur et que nous disons : « Hey, il faut juste arrêter de faire ça, » les adeptes des règles pourraient s’arrêter, pourraient ralentir, mais les transgresseurs, comme l’a dit Alexandr Wang, les gouvernements totalitaires, les organisations criminelles, vont prendre de l’ampleur. Et ça nous mènera, j’en suis presque sûr, à cet état dystopique, dans lequel les gentils ont de pires IA que les méchants.
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.
Mais je voudrais aussi m’adresser aux optimistes. Je ne pense pas que cela signifie : « On devrait juste se détendre et espérer le meilleur. » Ça ne ne se produira peut-être pas non plus. Je pense que tous ensemble, nous devons nous battre bec et ongles pour nous assurer que ces barrières que nous plaçons, lorsque les problèmes surviennent, soient des réglementations raisonnables. Mais nous nous battons sans relâche pour une utilisation positive. Car, et c’est très cher à mon cœur, et il y a potentiellement de nombreuses utilisations positives, mais le cas le plus puissant et peut-être le plus poétique, est que l’IA, l’intelligence artificielle, puisse être utilisée pour améliorer l’IH, l’intelligence humaine, le potentiel humain et la raison d’être humaine.
Thank you. (Applause)
Merci. (Applaudissements)