Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Andrej Karpathy says you should learn AI depthwise, not breadthwise. Most education is breadthwise: watch lectures, memorize formulas, and trust you'll need it later. Karpathy flips this by learning "depthwise, on demand." What this means: Pick a project, start building, and learn exactly when you hit a wall. When... he created a tutorial on transformers (the architecture behind ChatGPT), he didn't start by explaining attention mechanisms or complex architectures. Instead, he started with the simplest possible thing: a lookup table that predicts the next word. You build that first. Then you try to make it handle more complex patterns. And it breaks. Only then, when you've felt the limitation, does he introduce the next concept. Each piece solves a problem you've actually encountered. As he puts it: "It's a dick move to present the solution before I give you a shot to try it yourself." When you attempt the problem first, the solution actually makes sense. Teaching forces you to learn. "If I don't really understand something, I can't explain it." When you try to explain and stumble, you've found the gaps in your understanding. ... Build a project that gives you a reward. Hit a wall. Learn just enough to solve it. Then explain it to someone else. Don't consume content. Build the code. That's how you actually learn.show more

Ruben Hassid

94,824 subscribers

403,827 views • 10 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Andrej Karpathy is a legendary researcher who helped start OpenAI and created Stanford's first deep learning class. Andrej Karpathy's advice on how to learn AI: (1) 10,000 hours of deliberate practice will make you an expert. You can iterate as you work. Only compare yourself to the past, not to others. (2) Don't worry about making mistakes. You build intuitions on what is useful vs. not useful- they are not dead work. (3) Teach to strengthen your understanding and find gaps in knowledge. Similar to "If you can't explain it to a six-year-old, then you don't understand it yourself" - Albert Einstein.

Andrej Karpathy is a legendary researcher who helped start OpenAI and created Stanford's first deep learning class. Andrej Karpathy's advice on how to learn AI: (1) 10,000 hours of deliberate practice will make you an expert. You can iterate as you work. Only compare yourself to the past, not to others. (2) Don't worry about making mistakes. You build intuitions on what is useful vs. not useful- they are not dead work. (3) Teach to strengthen your understanding and find gaps in knowledge. Similar to "If you can't explain it to a six-year-old, then you don't understand it yourself" - Albert Einstein.

Alex Ker 🔭

508,833 views • 2 years ago

Anthropic's Andrej Karpathy to Andrew Ng: "Most people uses AI by importing a library, don't - write the whole thing by hand that's what I've been thinking about a lot at OpenAI " how he actually learned it: → wrote his own neural net library by hand - just to understand backprop → never abstracted a single layer he didn't build → only then touched a framework the payoff: "if you don't build it, you can't debug it, and you can't improve it" Ng backed him up - people who can debug ML are 10-100x faster than the rest two AI legends in one room - watch it, then read the loop guide below ↓

Anthropic's Andrej Karpathy to Andrew Ng: "Most people uses AI by importing a library, don't - write the whole thing by hand that's what I've been thinking about a lot at OpenAI " how he actually learned it: → wrote his own neural net library by hand - just to understand backprop → never abstracted a single layer he didn't build → only then touched a framework the payoff: "if you don't build it, you can't debug it, and you can't improve it" Ng backed him up - people who can debug ML are 10-100x faster than the rest two AI legends in one room - watch it, then read the loop guide below ↓

codila

72,865 views • 2 months ago

Tony Robbins reveals the three skills he says will make anyone unstoppable in the AI era "The first thing is pattern recognition. If you start recognizing patterns fear disappears. Losers react, leaders anticipate. Anticipation is power" "The second skill is when you learn to use the patterns. The third level skill is pattern creation. That's what you've begun to do. That's what I've begun to do. It's like when you learn to play a piano, most people learn someone else's patterns. But if you do enough, now you get to come out and you start creating things"

Tony Robbins reveals the three skills he says will make anyone unstoppable in the AI era "The first thing is pattern recognition. If you start recognizing patterns fear disappears. Losers react, leaders anticipate. Anticipation is power" "The second skill is when you learn to use the patterns. The third level skill is pattern creation. That's what you've begun to do. That's what I've begun to do. It's like when you learn to play a piano, most people learn someone else's patterns. But if you do enough, now you get to come out and you start creating things"

Jaynit

321,767 views • 4 months ago

Pavel Durov on why he hasn't had depression in 20 years: "I normally never have depression. I don't remember having depression in the last 20 years, at least maybe when I was a teenager." Pavel's approach to difficult emotions is completely counterintuitive. As he puts it: "I'm a human being like everybody else. I do get to experience emotions and some of them are not very pleasant. But I believe that it's the responsibility of every one of us to cope with these emotions and to learn to work through them." On what creates depression: "Self-discipline is particularly important because without it, how can you overcome this seemingly endless loop of negativity or despair that ultimately leads to depression for some people?" His method: "One of the reasons I don't have depression is I start doing things. I identify the problem, I can see a solution, and I start executing the strategy. If you are stuck in this loop of being worried about something, nothing's ever going to change." The mistake people make: "People often make this mistake thinking 'Oh, I should just have some rest and then regain energy.' This is not how it works. You gain energy by doing something. So you start doing something, then it happens. You feel motivated, you feel inspired, and then ultimately you do something else a little bit more." He continues: "The whole point is to do first and then feel, not feel and then do. Going to the gym is a good example. There are many days when you don't want to start working out. But you have to overcome this initial reluctance and then you get to a point that you enjoy it and you think 'Oh my god, it was such a good idea to come to gym today.'" Action creates energy, not the other way around.

Pavel Durov on why he hasn't had depression in 20 years: "I normally never have depression. I don't remember having depression in the last 20 years, at least maybe when I was a teenager." Pavel's approach to difficult emotions is completely counterintuitive. As he puts it: "I'm a human being like everybody else. I do get to experience emotions and some of them are not very pleasant. But I believe that it's the responsibility of every one of us to cope with these emotions and to learn to work through them." On what creates depression: "Self-discipline is particularly important because without it, how can you overcome this seemingly endless loop of negativity or despair that ultimately leads to depression for some people?" His method: "One of the reasons I don't have depression is I start doing things. I identify the problem, I can see a solution, and I start executing the strategy. If you are stuck in this loop of being worried about something, nothing's ever going to change." The mistake people make: "People often make this mistake thinking 'Oh, I should just have some rest and then regain energy.' This is not how it works. You gain energy by doing something. So you start doing something, then it happens. You feel motivated, you feel inspired, and then ultimately you do something else a little bit more." He continues: "The whole point is to do first and then feel, not feel and then do. Going to the gym is a good example. There are many days when you don't want to start working out. But you have to overcome this initial reluctance and then you get to a point that you enjoy it and you think 'Oh my god, it was such a good idea to come to gym today.'" Action creates energy, not the other way around.

Jaynit

547,702 views • 8 months ago

I vibe coded an application with Gemini 3 that let's you pick up a pencil and actually start drawing on a piece of paper. The assets are 3D which adds another layer of immersion just purely for fun. Try it here You can't start drawing until you literally click on the pencil to pick it up. You can also switch to a marker or use the eraser on the pencil. If you don't like the drawing you can crumple the paper and throw it in the trash. It will then place a new piece of paper on the table and you have to pick up the pencil again to start drawing again. I added a learn section on the app that links to youtube channels where you can also learn how to draw. It's quite fun to use, it's basically like using a super simplified version of photoshop or paint. It works with a wacom tablet, just can't seem to figure out how to get pressure sensitivity enabled.

I vibe coded an application with Gemini 3 that let's you pick up a pencil and actually start drawing on a piece of paper. The assets are 3D which adds another layer of immersion just purely for fun. Try it here You can't start drawing until you literally click on the pencil to pick it up. You can also switch to a marker or use the eraser on the pencil. If you don't like the drawing you can crumple the paper and throw it in the trash. It will then place a new piece of paper on the table and you have to pick up the pencil again to start drawing again. I added a learn section on the app that links to youtube channels where you can also learn how to draw. It's quite fun to use, it's basically like using a super simplified version of photoshop or paint. It works with a wacom tablet, just can't seem to figure out how to get pressure sensitivity enabled.

Travis Davids

12,836 views • 9 months ago

Most educational content doesn't explain or visualize things the way I learn best So I use Claude Code to create personalized math lessons - Pick a topic and tell the agent what you want to learn - Ask it to break the topic into smaller parts - Then ask it to create a video tutorial for each one It will create really good professional tutorials You can literally create personalized lessons the way you understand them better

Most educational content doesn't explain or visualize things the way I learn best So I use Claude Code to create personalized math lessons - Pick a topic and tell the agent what you want to learn - Ask it to break the topic into smaller parts - Then ask it to create a video tutorial for each one It will create really good professional tutorials You can literally create personalized lessons the way you understand them better

Doruk

13,510 views • 20 days ago

Andrej Karpathy spent 2h showing how he actually uses AI day to day he's a co-founder of OpenAI and led AI at Tesla, so when he shows how he works, it’s worth watching and the whole session is just him telling the machine what he wants in simple terms, like he's briefing a coworker watch what's actually happening the entire time: > he describes the task in normal words > it goes off and does the work > he glances at the result and nudges it with one more sentence that's the whole skill, and you've had it since you learned to talk the only gap between that and a worker that runs on its own is handing that sentence a schedule and the tools to act check his work, then build the version that keeps working when you stop

Andrej Karpathy spent 2h showing how he actually uses AI day to day he's a co-founder of OpenAI and led AI at Tesla, so when he shows how he works, it’s worth watching and the whole session is just him telling the machine what he wants in simple terms, like he's briefing a coworker watch what's actually happening the entire time: > he describes the task in normal words > it goes off and does the work > he glances at the result and nudges it with one more sentence that's the whole skill, and you've had it since you learned to talk the only gap between that and a worker that runs on its own is handing that sentence a schedule and the tools to act check his work, then build the version that keeps working when you stop

Chrome

1,810,356 views • 3 months ago

Stephen A. Smith reveals the #1 business lesson Trump gave him that he has “never forgotten.” “He said, ‘Not just know your worth, but go for it. Go for it all. Always pursue the most.’” “And I said, ‘Explain. What do you mean?’” “And he said, ‘When you go to a bank, and you borrow $3 million, and you can’t pay it back, you’ve got a problem.’” “‘But when you go to a bank, and you borrow $300 million, and you can’t pay it back, WE’VE got a problem.’” “He said, ‘The moral of the story is the MORE you convince someone to invest in you, the MORE they must work diligently to ENSURE your success.’” “‘Don’t come cheap. Make sure you convince folks to make that requisite investment in you because they’ll be committed to you succeeding, because YOUR success means THEIR success, and they have a chance to recoup the investment they made in you.’” “That’s how you do that. That was the advice that he gave, and I never forgot it.” If you found that Trump story insightful, bookmark this post so you never forget it either. Because when the right opportunity shows up, this is exactly what you’ll wish you remembered.

Stephen A. Smith reveals the #1 business lesson Trump gave him that he has “never forgotten.” “He said, ‘Not just know your worth, but go for it. Go for it all. Always pursue the most.’” “And I said, ‘Explain. What do you mean?’” “And he said, ‘When you go to a bank, and you borrow $3 million, and you can’t pay it back, you’ve got a problem.’” “‘But when you go to a bank, and you borrow $300 million, and you can’t pay it back, WE’VE got a problem.’” “He said, ‘The moral of the story is the MORE you convince someone to invest in you, the MORE they must work diligently to ENSURE your success.’” “‘Don’t come cheap. Make sure you convince folks to make that requisite investment in you because they’ll be committed to you succeeding, because YOUR success means THEIR success, and they have a chance to recoup the investment they made in you.’” “That’s how you do that. That was the advice that he gave, and I never forgot it.” If you found that Trump story insightful, bookmark this post so you never forget it either. Because when the right opportunity shows up, this is exactly what you’ll wish you remembered.

The Vigilant Fox 🦊

1,223,848 views • 5 months ago

I just built a skill called 'Explain This'. It explains anything to you, tailored to how you learn. It's inspired by Geoffrey Litt's talk at AI Engineer: 'Understanding is the New Bottleneck'. AI can generate infinite code and content, and the scarce thing now is a human who actually understands. How often have you realized you read something but retained none of it? I built '/explain-this' to solve that. How it works: 🧠 It interviews you first. Ten minutes on what you know deeply, how explanations land for you, and what you're aiming to become. That generates your LEARNER.md profile. 📄 Then point your agent at any paper, PDF, or blog post and say "explain this." ✍️ It writes an explainer doc straight into your notes. Obsidian, OpenKnowledge, wherever you think, anchored to what you already know, skipping what you don't need to learn again. ✅ Every explanation ends with a quiz, and it grades your answers. Mastery learning means you don't move on until you prove to yourself you understood. 🔁 Your misses become spaced-repetition cards. Say "quiz me" next week and it re-teaches what didn't stick. Over time it learns your actual weak spots from evidence. Works in Claude Code or any agent that supports skills. Free and open source. Link to GitHub below. 👇

Dan McAteer

27,296 views • 2 months ago

Tyler, The Creator tells Jill Scott how he discovered he has a superpower in a conversation for Human To Human: “One girl told me: “Uh, damn. It seems you don't know how to fully express yourself unless it's an instrumental under it [...] I just see that you sit with the thing and you learn about yourself this and that through it and then you're able to express it through lyrics or words or an instrumental or this and that. And she said: “that's a superpower that you have.”

Tyler, The Creator tells Jill Scott how he discovered he has a superpower in a conversation for Human To Human: “One girl told me: “Uh, damn. It seems you don't know how to fully express yourself unless it's an instrumental under it [...] I just see that you sit with the thing and you learn about yourself this and that through it and then you're able to express it through lyrics or words or an instrumental or this and that. And she said: “that's a superpower that you have.”

Archive Tyler, The Creator

78,593 views • 5 months ago

Asmongold explains why you should never try to build your streaming brand on Twitch "Twitch is aggregated by viewer count. If you only have 100 viewers, you're probably going to stay there, but if you get a lot of viewers, you go up. So it's a snowball, when you win you keep winning, and when you're losing you lose even more. That's the bad thing about the website, and I don't know how Twitch can solve it, but it is a problem." "Streaming on there is also basically gambling. It's so random, you wake up wondering if today's going to be good, and especially for smaller creators with no other income, it's literally I hope somebody donates $50 today. It's a crazy reward structure and people get really attached to it." "So my best advice for anybody is do not try to build a brand on Twitch. Build it on TikTok, build it on YouTube, build it basically anywhere else but Twitch."

Kai

258,712 views • 3 months ago

MOTU breaks the lore that's IN THE THEME SONG yet people are praising it, don't get me started on everything else it gets wrong. IF you wanted Barbie the movie with He-Man, then you'll love it... if you wanted a He-Man that actually paid attention to the lore and respected it, then watch the 87 film, at least that gets "caveman" He-Man right...

MOTU breaks the lore that's IN THE THEME SONG yet people are praising it, don't get me started on everything else it gets wrong. IF you wanted Barbie the movie with He-Man, then you'll love it... if you wanted a He-Man that actually paid attention to the lore and respected it, then watch the 87 film, at least that gets "caveman" He-Man right...

MEAD The 4K💿 Master (Tom Connors)

24,658 views • 3 months ago

Rob Gronkowski says he left Body Armor right before Kobe's investment turned the company into an $8,000,000,000 sale Rob: "I was actually the first person to represent Body Armor, the first athlete to represent Body Armor and I didn't invest in the body armor. I got a, uh, you know, a little payday at first, couple shares" Rob: "It was about 2 years into it and then I won the Super Bowl and then like they kind of offered me something that was a little bit lower than what I had previously and I was like, that doesn't make sense" Rob: "I actually left and I went to Monster Energy. And um, and then they a year later, you saw the whole production with Kobe. He invested that much and you know body armor started to really catch on" Rob: "I see what they were doing at the beginning. I'm in the business world now like more and more cuz when you're a kid you don't know how anything works really. You got to learn as you grow"

Rob Gronkowski says he left Body Armor right before Kobe's investment turned the company into an $8,000,000,000 sale Rob: "I was actually the first person to represent Body Armor, the first athlete to represent Body Armor and I didn't invest in the body armor. I got a, uh, you know, a little payday at first, couple shares" Rob: "It was about 2 years into it and then I won the Super Bowl and then like they kind of offered me something that was a little bit lower than what I had previously and I was like, that doesn't make sense" Rob: "I actually left and I went to Monster Energy. And um, and then they a year later, you saw the whole production with Kobe. He invested that much and you know body armor started to really catch on" Rob: "I see what they were doing at the beginning. I'm in the business world now like more and more cuz when you're a kid you don't know how anything works really. You got to learn as you grow"

Arslan

1,141,705 views • 2 months ago

Tony Robbins reveals the 3 skills that will make anyone unstoppable in the AI era "The first thing is pattern recognition. If you start recognizing patterns fear disappears. Losers react, leaders anticipate. Anticipation is power" "The second skill is when you learn to use the patterns" "The third level skill is pattern creation. That's what you've begun to do. That's what I've begun to do. It's like when you learn to play a piano, most people learn someone else's patterns. But if you do enough, now you get to come out and you start creating things"

Tony Robbins reveals the 3 skills that will make anyone unstoppable in the AI era "The first thing is pattern recognition. If you start recognizing patterns fear disappears. Losers react, leaders anticipate. Anticipation is power" "The second skill is when you learn to use the patterns" "The third level skill is pattern creation. That's what you've begun to do. That's what I've begun to do. It's like when you learn to play a piano, most people learn someone else's patterns. But if you do enough, now you get to come out and you start creating things"

Jaynit

76,040 views • 1 month ago

"The worse thing you can do when you get on the range is to try and smack it as hard as you can. I just try to hit lots of small shots, hit the middle of the club face. Then build it up from there, that makes the difference. You can the build the reps up from there. Hit it a bit harder, find a bit of confidence. It seems really simple, that's actually what all the guys are doing. Nobody's coming out and trying to smack it as hard as they can. Nick Dougherty and Ewen Ferguson chat all things practice sessions on the driving range in Dubai. #HeroDubaiDesertClassic | #RolexSeries

"The worse thing you can do when you get on the range is to try and smack it as hard as you can. I just try to hit lots of small shots, hit the middle of the club face. Then build it up from there, that makes the difference. You can the build the reps up from there. Hit it a bit harder, find a bit of confidence. It seems really simple, that's actually what all the guys are doing. Nobody's coming out and trying to smack it as hard as they can. Nick Dougherty and Ewen Ferguson chat all things practice sessions on the driving range in Dubai. #HeroDubaiDesertClassic | #RolexSeries

DP World Tour

41,129 views • 7 months ago

"Elon Musk is a genius by all accounts. His commitment and his work, like I asked him one time about how does he learn. And the amount of research, the amount of study that he does is unheard of, but he'll always say the most important thing is imagination. You can learn anything that you want to learn. You can study all these things that you have in a book. If you don't have the imagination to take it to another level, it doesn't mean anything. I sat down and spoke with Elon for a couple hours. It was really, really a joy." — Kobe Bryant

"Elon Musk is a genius by all accounts. His commitment and his work, like I asked him one time about how does he learn. And the amount of research, the amount of study that he does is unheard of, but he'll always say the most important thing is imagination. You can learn anything that you want to learn. You can study all these things that you have in a book. If you don't have the imagination to take it to another level, it doesn't mean anything. I sat down and spoke with Elon for a couple hours. It was really, really a joy." — Kobe Bryant

DogeDesigner

242,479 views • 2 months ago

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

nader dabit

173,538 views • 10 months ago

Peter Thiel on the most important lesson he learned building PayPal The early employees of PayPal went on to build incredible companies like Tesla, SpaceX, LinkedIn, YouTube, Palantir, Yelp, Yammer, and more. When asked about the factors that explain these outlier successes, Thiel suggests that it was probably a combination of several different things: an entrepreneurial culture, lots of strong personalities, and the early 2000s was a great time to start a company. But Thiel also says that the overarching lesson you learned working at PayPal—which had a lot of challenges but ended up succeeding—was: “You can build a great company, but it’s hard.” He contrasts this to the lessons you learn at most startups: “If you’re at a startup that fails, you will learn the lesson that it’s impossible to build a great company and that you should try something less ambitious the next time around. If you’re at a startup where things work too easily [such as Microsoft or Google], you learn the lesson that it’s actually easy to build a great company.” He continues: “Hard is somehow better than easy or impossible. If it’s easy, you don’t need to work hard. If it’s impossible, there’s no point in working hard. So easy and impossible converge to not working hard. Hard tells you you have to work hard.” Video source: This Week in Startups @jason (2015)

Peter Thiel on the most important lesson he learned building PayPal The early employees of PayPal went on to build incredible companies like Tesla, SpaceX, LinkedIn, YouTube, Palantir, Yelp, Yammer, and more. When asked about the factors that explain these outlier successes, Thiel suggests that it was probably a combination of several different things: an entrepreneurial culture, lots of strong personalities, and the early 2000s was a great time to start a company. But Thiel also says that the overarching lesson you learned working at PayPal—which had a lot of challenges but ended up succeeding—was: “You can build a great company, but it’s hard.” He contrasts this to the lessons you learn at most startups: “If you’re at a startup that fails, you will learn the lesson that it’s impossible to build a great company and that you should try something less ambitious the next time around. If you’re at a startup where things work too easily [such as Microsoft or Google], you learn the lesson that it’s actually easy to build a great company.” He continues: “Hard is somehow better than easy or impossible. If it’s easy, you don’t need to work hard. If it’s impossible, there’s no point in working hard. So easy and impossible converge to not working hard. Hard tells you you have to work hard.” Video source: This Week in Startups @jason (2015)

Startup Archive

105,347 views • 11 months ago

🗣️ Mikel Arteta on the possibility of players leaving who have been here a long time: "It's a really, really tough moment, you need to face that reality. But you need to face it with real honesty and transparency because when you are on the other side, that's exactly what you need. "You might not like what you've been told, but if it's truthful, if it's the reality, if it's honest and it's going to help you to make better decisions and have more clarity for the next steps in your career, you have to do that. "These are always very difficult conversations, but they need to be done. It's like when a player doesn't feel that he belongs or he's important, he wants to have a different chapter, I think that communication has to exist and it has to be both ways. "We all know, everything has a start and has an end. When it comes to the end, I think our duty, our responsibility is to do it in the best possible way, maintaining the respect and admiration for the player and the relationship, but understanding that at the end, we need to make football decisions."

🗣️ Mikel Arteta on the possibility of players leaving who have been here a long time: "It's a really, really tough moment, you need to face that reality. But you need to face it with real honesty and transparency because when you are on the other side, that's exactly what you need. "You might not like what you've been told, but if it's truthful, if it's the reality, if it's honest and it's going to help you to make better decisions and have more clarity for the next steps in your career, you have to do that. "These are always very difficult conversations, but they need to be done. It's like when a player doesn't feel that he belongs or he's important, he wants to have a different chapter, I think that communication has to exist and it has to be both ways. "We all know, everything has a start and has an end. When it comes to the end, I think our duty, our responsibility is to do it in the best possible way, maintaining the respect and admiration for the player and the relationship, but understanding that at the end, we need to make football decisions."

Connor Humm

143,296 views • 29 days ago