正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

"Tesla’s new AI5 chip is about 3 times more power efficient than NVIDIA Blackwell at under 10% of the cost. I am super hardcore on chips right now. I have chips on the brain. I dream about chips. A single AI5 has ~5 times the useful compute of a... show more

DogeDesigner

1,897,787 subscribers

168,376 次观看 • 4 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

ELON MUSK: We believe the AI5 chip will be roughly comparable performance to an NVIDIA Blackwell, and at much less than 10% of the cost Transcription: I'm super hardcore on chips right now as you may be able to tell. I have chips on the brain. I dream about chips, Literally! Because in order to have a functional robot, you have to have a great AI chip. And it needs to be an inexpensive chip and it needs to be very power efficient So we think we believe the AI5 chip will be probably about a third of the power of say something like a Blackwell, an NVIDIA Blackwell, which is a great chip, for roughly comparable performance. And much less than 10% of the cost. This is a chip that is very much optimized for the Tesla AI software stack. So it's not meant to be a general purpose chip, it's meant to be an amazing chip for the Tesla AI software And I mean a couple of things that I think make... like how is Tesla able to achieve such an improvement? I think it is because we are specialized. We're not trying to... you know, NVIDIA has to serve the superset of all past and future customers. So all of their requirements, all of the software that they've written has to work, which is a very difficult problem. Whereas we just need to make it work for our software. And so we're able to simplify the chip dramatically And then we also, I think we're unique in this, but like we have an integer-based system. And integer operations are fundamentally more efficient than floating point operations. So we can do floating point, but the vast majority of our inference is done in integer. Which is, if you're familiar with sort of logic gates, the simplicity of integer... it's integer is much more power efficient, much more silicon efficient, but you have to, you actually have to train for integer inference, which everyone else is training for floating point. That's kind of like a niche technical detail, but it's actually very important. So, yeah, this is going to be a great chip So this chip will be made in basically in four places: TSMC Taiwan, Samsung Korea, TSMC Arizona, and TSMC Texas. And we already know what improvements to make for AI6. So I'm hopeful that we can within less than a year of AI5 starting production, we can actually transition in the same fab to AI6 and double all of the performance metrics

ELON MUSK: We believe the AI5 chip will be roughly comparable performance to an NVIDIA Blackwell, and at much less than 10% of the cost Transcription: I'm super hardcore on chips right now as you may be able to tell. I have chips on the brain. I dream about chips, Literally! Because in order to have a functional robot, you have to have a great AI chip. And it needs to be an inexpensive chip and it needs to be very power efficient So we think we believe the AI5 chip will be probably about a third of the power of say something like a Blackwell, an NVIDIA Blackwell, which is a great chip, for roughly comparable performance. And much less than 10% of the cost. This is a chip that is very much optimized for the Tesla AI software stack. So it's not meant to be a general purpose chip, it's meant to be an amazing chip for the Tesla AI software And I mean a couple of things that I think make... like how is Tesla able to achieve such an improvement? I think it is because we are specialized. We're not trying to... you know, NVIDIA has to serve the superset of all past and future customers. So all of their requirements, all of the software that they've written has to work, which is a very difficult problem. Whereas we just need to make it work for our software. And so we're able to simplify the chip dramatically And then we also, I think we're unique in this, but like we have an integer-based system. And integer operations are fundamentally more efficient than floating point operations. So we can do floating point, but the vast majority of our inference is done in integer. Which is, if you're familiar with sort of logic gates, the simplicity of integer... it's integer is much more power efficient, much more silicon efficient, but you have to, you actually have to train for integer inference, which everyone else is training for floating point. That's kind of like a niche technical detail, but it's actually very important. So, yeah, this is going to be a great chip So this chip will be made in basically in four places: TSMC Taiwan, Samsung Korea, TSMC Arizona, and TSMC Texas. And we already know what improvements to make for AI6. So I'm hopeful that we can within less than a year of AI5 starting production, we can actually transition in the same fab to AI6 and double all of the performance metrics

X Freeze

305,109 次观看 • 9 个月前

Elon Musk on Tesla’s AI5 chip: At Tesla, there are two chip programs: • Dojo → training • AI4 / AI5 → inference in vehicles AI4 is what’s shipping in cars today AI5 is being finalized and it’s a massive leap By some metrics, AI5 is ~40× better than AI4 (Not 40%. 40 times.) Why the jump is so big: "This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip" • Tesla fixes actual bottlenecks, not just adds compute • Example: SoftMax – AI4: ~40 emulation steps – AI5: a few steps natively in silicon Raw improvements: • ~8× compute • ~9× memory • ~5× memory bandwidth • Native mixed-precision handling But the real gain comes from eliminating core AI4 limitations at the silicon level, turning those raw gains into a ~40× real-world improvement This isn’t just a faster chip, it’s a fundamentally smarter one

Elon Musk on Tesla’s AI5 chip: At Tesla, there are two chip programs: • Dojo → training • AI4 / AI5 → inference in vehicles AI4 is what’s shipping in cars today AI5 is being finalized and it’s a massive leap By some metrics, AI5 is ~40× better than AI4 (Not 40%. 40 times.) Why the jump is so big: "This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip" • Tesla fixes actual bottlenecks, not just adds compute • Example: SoftMax – AI4: ~40 emulation steps – AI5: a few steps natively in silicon Raw improvements: • ~8× compute • ~9× memory • ~5× memory bandwidth • Native mixed-precision handling But the real gain comes from eliminating core AI4 limitations at the silicon level, turning those raw gains into a ~40× real-world improvement This isn’t just a faster chip, it’s a fundamentally smarter one

X Freeze

73,645 次观看 • 7 个月前

Elon Musk: At Tesla, we basically had two different chip programs: one Dojo and one. Dojo on the training side, and then what we call AI4, it's just our inference chip The AI4 is what's currently shipping in all vehicles, and we're finalizing the design of AI5, which will be an immense jump from AI4. By some metrics, the improvement in AI5 will be 40 times better than AI4. So not 40%, 40 times This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip Compared to the worst limitation on AI4, which is running the SoftMax operation, we currently have to run SoftMax in around 40 steps in emulation mode, whereas that'll just be done in a few steps natively in AI5 AI5 will also be able to easily handle mixed precision models, so you don't have it, it'll dynamically handle mixed precision. There's a bunch of sort of technical stuff that AI5 will do a lot better In terms of nominal raw compute, it's eight times more compute, about nine times more memory, and roughly five times more memory bandwidth But because we're addressing some core limitations in AI4, you multiply that 8x compute improvement by another 5x improvement because of optimization at a very fine-grained silicon level of things that are currently suboptimal in AI4, that's where you get the 40x improvement

Elon Musk: At Tesla, we basically had two different chip programs: one Dojo and one. Dojo on the training side, and then what we call AI4, it's just our inference chip The AI4 is what's currently shipping in all vehicles, and we're finalizing the design of AI5, which will be an immense jump from AI4. By some metrics, the improvement in AI5 will be 40 times better than AI4. So not 40%, 40 times This is because we work so closely at a very fine-grained level on the AI software and the AI hardware. So we know exactly where the limiting factors are. And so effectively the AI hardware and software teams are co-designing the chip Compared to the worst limitation on AI4, which is running the SoftMax operation, we currently have to run SoftMax in around 40 steps in emulation mode, whereas that'll just be done in a few steps natively in AI5 AI5 will also be able to easily handle mixed precision models, so you don't have it, it'll dynamically handle mixed precision. There's a bunch of sort of technical stuff that AI5 will do a lot better In terms of nominal raw compute, it's eight times more compute, about nine times more memory, and roughly five times more memory bandwidth But because we're addressing some core limitations in AI4, you multiply that 8x compute improvement by another 5x improvement because of optimization at a very fine-grained silicon level of things that are currently suboptimal in AI4, that's where you get the 40x improvement

X Freeze

21,223,192 次观看 • 9 个月前

ELON: TESLA FUTURE'S HINGES ON THE AI5 CHIP PROJECT "The AI5 chip, which is going to be a great chip, all of Tesla hinges on that chip. That's the chip that is going into our next generation of self-driving cars, and it's also essential for the Optimus robot. So that chip program was in bad shape. It wasn't closing because it's quite an ambitious chip design, and it really wasn't on a path to success. And then we also had the Dojo program, which was doing okay but not on a path to be competitive with NVIDIA. So I collapsed the two programs into just one program, which is to get everyone focused on the AI5 chip, which is essential. Continue to use NVIDIA for training, but we need the AI5 inference chip, which is a very powerful chip, but it's also a very low-power chip. So it doesn't use a lot of power. Its performance per watt is extremely good. I think it's probably going to be at least 2 to 4 times better than NVIDIA performance per watt at the inference level in the car and the robot. And I don't know, 10% of the cost of an NVIDIA chip, something like that. So these are very important numbers to achieve." Source: Elon Musk, Baron Capital, Ron Baron, Tesla

ELON: TESLA FUTURE'S HINGES ON THE AI5 CHIP PROJECT "The AI5 chip, which is going to be a great chip, all of Tesla hinges on that chip. That's the chip that is going into our next generation of self-driving cars, and it's also essential for the Optimus robot. So that chip program was in bad shape. It wasn't closing because it's quite an ambitious chip design, and it really wasn't on a path to success. And then we also had the Dojo program, which was doing okay but not on a path to be competitive with NVIDIA. So I collapsed the two programs into just one program, which is to get everyone focused on the AI5 chip, which is essential. Continue to use NVIDIA for training, but we need the AI5 inference chip, which is a very powerful chip, but it's also a very low-power chip. So it doesn't use a lot of power. Its performance per watt is extremely good. I think it's probably going to be at least 2 to 4 times better than NVIDIA performance per watt at the inference level in the car and the robot. And I don't know, 10% of the cost of an NVIDIA chip, something like that. So these are very important numbers to achieve." Source: Elon Musk, Baron Capital, Ron Baron, Tesla

Mario Nawfal

225,142 次观看 • 9 个月前

ELON: "WE'LL HAVE MORE AI CHIPS THAN POWER TO RUN THEM" "The limiting factor for AI deployment is fundamentally electrical power. It's energy. We're seeing the rate of AI chip production increase exponentially, but the rate of electricity being brought online is 5% a year, max. It's clear that we're very soon, maybe even later this year, we'll be producing more chips than we can turn on." Source: Elon Musk

ELON: "WE'LL HAVE MORE AI CHIPS THAN POWER TO RUN THEM" "The limiting factor for AI deployment is fundamentally electrical power. It's energy. We're seeing the rate of AI chip production increase exponentially, but the rate of electricity being brought online is 5% a year, max. It's clear that we're very soon, maybe even later this year, we'll be producing more chips than we can turn on." Source: Elon Musk

Mario Nawfal

40,874 次观看 • 6 个月前

ELON: TESLA'S AI5 CHIP IS THE SILICON VERSION OF “LESS IS MORE” "The AI5 chip will be 40 times better than the AI4 chip – not 40%, 40 times. We have a detailed understanding of the entire software and hardware stack. We are designing the hardware to address all of the pain points in software. We know what the chip needs to do, and we know, just as importantly, what the chip doesn’t need to do. A long list of deletions that are very important. As a result of these deletions, we can actually fit AI5 in a half reticle with a good margin for the traces from the memory to the Tesla chip accelerators, the ARM CPU cores, and the PCI blocks. This is a beautiful chip." Source: Elon Musk, Tesla Podcast, October 22, 2025

ELON: TESLA'S AI5 CHIP IS THE SILICON VERSION OF “LESS IS MORE” "The AI5 chip will be 40 times better than the AI4 chip – not 40%, 40 times. We have a detailed understanding of the entire software and hardware stack. We are designing the hardware to address all of the pain points in software. We know what the chip needs to do, and we know, just as importantly, what the chip doesn’t need to do. A long list of deletions that are very important. As a result of these deletions, we can actually fit AI5 in a half reticle with a good margin for the traces from the memory to the Tesla chip accelerators, the ARM CPU cores, and the PCI blocks. This is a beautiful chip." Source: Elon Musk, Tesla Podcast, October 22, 2025

Mario Nawfal

363,507 次观看 • 9 个月前

ELON MUSK: "The AI 5 chip which is going to be a great chip. All of Tesla hinges on that chip. That's the chip that going to our next gen self driving cars and it's also essential for Optimus. So that chip program was in bad shape. It wasn't on the path to success and we also had the DOJO program which was also doing okay but not on a path to be competitive with NVIDIA. So I collapsed the two programs into just one program to get everyone focused on the AI5 chip. It's performance per watt is extremely good. It is probably going to be at least 2-3 times better than NVIDIA performance per watt and 10% cost of the NVIDIA chip something like that."

ELON MUSK: "The AI 5 chip which is going to be a great chip. All of Tesla hinges on that chip. That's the chip that going to our next gen self driving cars and it's also essential for Optimus. So that chip program was in bad shape. It wasn't on the path to success and we also had the DOJO program which was also doing okay but not on a path to be competitive with NVIDIA. So I collapsed the two programs into just one program to get everyone focused on the AI5 chip. It's performance per watt is extremely good. It is probably going to be at least 2-3 times better than NVIDIA performance per watt and 10% cost of the NVIDIA chip something like that."

DogeDesigner

265,257 次观看 • 9 个月前

"I am super excited about the robots Elon Musk is working on" - Nvidia CEO Jensen Huang

"I am super excited about the robots Elon Musk is working on" - Nvidia CEO Jensen Huang

Tesla Owners Silicon Valley

557,462 次观看 • 8 个月前

NEWS: Nvidia has released a new video of its next-generation Rubin chips, which are 5X more powerful than their predecessor, Blackwell. The new Rubin chips are already in production. CEO Jensen Huang: "This is a Rubin pod. 1,152 GPUs and 16 racks. Each rack has 72 Rubins."

NEWS: Nvidia has released a new video of its next-generation Rubin chips, which are 5X more powerful than their predecessor, Blackwell. The new Rubin chips are already in production. CEO Jensen Huang: "This is a Rubin pod. 1,152 GPUs and 16 racks. Each rack has 72 Rubins."

Sawyer Merritt

798,317 次观看 • 7 个月前

#Bittensor creating super Intelligence faster than Elon Musk, at 1/1000th the cost ⚪️ "The power of decentralization gets you 20,000 times more powerful than a hundred billion dollar value company for trivially less" ⚪️ "I'm underselling it. Tens of thousands of times. More efficient outputs, yes, but also at a thousand times less cost" ⚪️ "I think we could actually use #Bittensor to create super intelligence faster than Elon Musk can create super intelligence" I highly recommend listening to the full discussion of The $TAO Pod with JJ and James Altucher here 👉 $TAO

#Bittensor creating super Intelligence faster than Elon Musk, at 1/1000th the cost ⚪️ "The power of decentralization gets you 20,000 times more powerful than a hundred billion dollar value company for trivially less" ⚪️ "I'm underselling it. Tens of thousands of times. More efficient outputs, yes, but also at a thousand times less cost" ⚪️ "I think we could actually use #Bittensor to create super intelligence faster than Elon Musk can create super intelligence" I highly recommend listening to the full discussion of The $TAO Pod with JJ and James Altucher here 👉 $TAO

ＤＲＥＡＤＢＯＮＧＯ

17,576 次观看 • 1 年前

Elon Musk says the AI boom hits a WALL this year when we run out of power to run the chips. He says the whole industry is about to learn a hard lesson in hardware. Chip output is exploding, but electricity is nearly flat everywhere outside China. So the two lines cross this year. He says by the end of the year, we will be making more AI chips than we can actually turn on. Millions of them pile up with nowhere to plug in. In his words, the bottleneck for the next year is not chips, it is raw power. Whoever can turn on the most chips fastest wins the race. In the end, the AI race comes down to one thing: Raw electricity. — Elon Musk (.Elon Musk) on Dwarkesh Patel's (.Dwarkesh Patel) podcast

Elon Musk says the AI boom hits a WALL this year when we run out of power to run the chips. He says the whole industry is about to learn a hard lesson in hardware. Chip output is exploding, but electricity is nearly flat everywhere outside China. So the two lines cross this year. He says by the end of the year, we will be making more AI chips than we can actually turn on. Millions of them pile up with nowhere to plug in. In his words, the bottleneck for the next year is not chips, it is raw power. Whoever can turn on the most chips fastest wins the race. In the end, the AI race comes down to one thing: Raw electricity. — Elon Musk (.Elon Musk) on Dwarkesh Patel's (.Dwarkesh Patel) podcast

Genius Thinking

705,865 次观看 • 1 天前

Elon Musk on the A5 chip: “This powers Tesla’s self-driving cars and Optimus robot. Collapsed two programs into one. It’s low-power, 2–3x better than Nvidia at inference, and just 10% of the cost." $TSLA

Elon Musk on the A5 chip: “This powers Tesla’s self-driving cars and Optimus robot. Collapsed two programs into one. It’s low-power, 2–3x better than Nvidia at inference, and just 10% of the cost." $TSLA

Herbert Ong

39,546 次观看 • 9 个月前

ELON: TESLA'S PEDAL TO THE METAL ON AI5 & AI6 "Tesla's pedal to the metal max production is to get Tesla AI5 chip design into production and then reaching scale, that'll probably happen around the second quarter of next year. AI6 would hopefully follow less than a year later. We've secured all the chip fab production that we can using TSMC Taiwan, Samsung Korea, TSMC Arizona, Samsung Texas. The limiting factor once you can get to space is chips, but the limiting factor before you can get to space will be power." Source: Cheeky Pint Podcast, Elon Musk

ELON: TESLA'S PEDAL TO THE METAL ON AI5 & AI6 "Tesla's pedal to the metal max production is to get Tesla AI5 chip design into production and then reaching scale, that'll probably happen around the second quarter of next year. AI6 would hopefully follow less than a year later. We've secured all the chip fab production that we can using TSMC Taiwan, Samsung Korea, TSMC Arizona, Samsung Texas. The limiting factor once you can get to space is chips, but the limiting factor before you can get to space will be power." Source: Cheeky Pint Podcast, Elon Musk

Mario Nawfal

72,185 次观看 • 6 个月前

Alex Jones 5 years ago talking about Elon Musk with David Icke: “His eyes are all whacked out, his pupils are giant…I know a lot of military have gotten brain chips… From the Intel I’ve gotten, a lot of these guys already have chips and are also on a lot of drugs. And that goes into the whole culture of Silicon Valley and convincing people to give up their humanity.”

Alex Jones 5 years ago talking about Elon Musk with David Icke: “His eyes are all whacked out, his pupils are giant…I know a lot of military have gotten brain chips… From the Intel I’ve gotten, a lot of these guys already have chips and are also on a lot of drugs. And that goes into the whole culture of Silicon Valley and convincing people to give up their humanity.”

Miss Qniverse✨

65,409 次观看 • 1 年前

🚨🇺🇸 CHAMATH: ELON’S AI5 CHIP IS 40X BETTER THAN AI4 — A BEAUTIFUL DESIGN “He had these multiple efforts with Dojo and other stuff that he merged into one unit. The quote is incredible: ‘We’re going to focus TSMC and Samsung on AI5.’ By some metrics, it’ll be 40x better than AI4. With AI5, they deleted the legacy GPU — it basically is a GPU. They also deleted the image signal processor. Elon said, ‘This is a beautiful chip. I poured so much life energy into this personally. It’ll be a real winner.’” Source: Chamath Palihapitiya The All-In Podcast

🚨🇺🇸 CHAMATH: ELON’S AI5 CHIP IS 40X BETTER THAN AI4 — A BEAUTIFUL DESIGN “He had these multiple efforts with Dojo and other stuff that he merged into one unit. The quote is incredible: ‘We’re going to focus TSMC and Samsung on AI5.’ By some metrics, it’ll be 40x better than AI4. With AI5, they deleted the legacy GPU — it basically is a GPU. They also deleted the image signal processor. Elon said, ‘This is a beautiful chip. I poured so much life energy into this personally. It’ll be a real winner.’” Source: Chamath Palihapitiya The All-In Podcast

Mario Nawfal

1,016,192 次观看 • 10 个月前

Elon about Terafab: “We’re not going to do just conventional compute, I think there’s some very interesting new physics” Very interesting! NVIDIA style chips are just one way of doing AI compute. Is Elon talking about analog AI? Neuromorphic chips? I hope it’s something very ambitious. I think we’re stuck in a local minima in AI hardware and I’m excited to see a big ambitious R&D effort to try and break out. Here’s the meat of the Terafab announcement where he describes what makes it different from all other AI hardware efforts.

Elon about Terafab: “We’re not going to do just conventional compute, I think there’s some very interesting new physics” Very interesting! NVIDIA style chips are just one way of doing AI compute. Is Elon talking about analog AI? Neuromorphic chips? I hope it’s something very ambitious. I think we’re stuck in a local minima in AI hardware and I’m excited to see a big ambitious R&D effort to try and break out. Here’s the meat of the Terafab announcement where he describes what makes it different from all other AI hardware efforts.

Phil Trubey

26,251 次观看 • 5 个月前

ELON MUSK: "The AI 5 chip which is going to be a great chip. All of Tesla hinges on that chip. That's the chip that going to our next gen self driving cars and it's also essential for Optimus. It's performance per watt is extremely good. It is probably going to be at least 2-3 times better than NVIDIA performance per watt and 10% cost of the NVIDIA chip something like that."

ELON MUSK: "The AI 5 chip which is going to be a great chip. All of Tesla hinges on that chip. That's the chip that going to our next gen self driving cars and it's also essential for Optimus. It's performance per watt is extremely good. It is probably going to be at least 2-3 times better than NVIDIA performance per watt and 10% cost of the NVIDIA chip something like that."

DogeDesigner

162,829 次观看 • 8 个月前

NEWS: SpaceX just made its AI space computer 67% more powerful, Elon Musk says The satellite is called AI1. It is basically a data center that floats in space and runs on sunlight instead of the power grid. Musk says its peak power is going up to ~250 kW, from 150 kW. Its average power is going up to 160 kW, from 120 kW. Why the boost. A single Nvidia Rubin NVL72 rack, 72 of Nvidia's newest AI chips, needs that much power to run. The bigger number means one AI1 can now handle a full rack. Musk's reasoning is simple. A GPU running all day uses about two-thirds of its peak power, even when it is very efficient. So the satellite has to be built for the peak. AI1 works with chips from any maker, not just Nvidia. SpaceX has filed to launch up to 1 million of these satellites. (Source: Elon Musk on X, July 16)

NEWS: SpaceX just made its AI space computer 67% more powerful, Elon Musk says The satellite is called AI1. It is basically a data center that floats in space and runs on sunlight instead of the power grid. Musk says its peak power is going up to ~250 kW, from 150 kW. Its average power is going up to 160 kW, from 120 kW. Why the boost. A single Nvidia Rubin NVL72 rack, 72 of Nvidia's newest AI chips, needs that much power to run. The bigger number means one AI1 can now handle a full rack. Musk's reasoning is simple. A GPU running all day uses about two-thirds of its peak power, even when it is very efficient. So the satellite has to be built for the peak. AI1 works with chips from any maker, not just Nvidia. SpaceX has filed to launch up to 1 million of these satellites. (Source: Elon Musk on X, July 16)

Muskonomy

56,507 次观看 • 1 个月前