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。

ELON: DATA COMPRESSION IS TESLA’S BIGGEST AI CHALLENGE "The single biggest technical challenge of Tesla self-driving AI is context compression of 1.5GB/s of video to ~2kB/s of control outputs using a puny inference computer without making any mistakes. Super hard to avoid overly lossy compression at any given step."

Mario Nawfal

3,609,010 subscribers

486,215 次观看 • 7 个月前 •via X (Twitter)

新闻政治科学技术

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

Ai is just massive data compression.

Ai is just massive data compression.

MERICA MEMED

168,935 次观看 • 11 个月前

AI has a "last-mile problem" similar to self-driving cars. With self-driving cars, early demos impressed, but real-world deployment took years. It's easy to hack up a prototype, but making it work reliably at scale is hard. If each step of an AI agent is only 95% accurate, none of the 30-step workflows will work reliably. Going from 95% to 99.9% accuracy is the real challenge.

AI has a "last-mile problem" similar to self-driving cars. With self-driving cars, early demos impressed, but real-world deployment took years. It's easy to hack up a prototype, but making it work reliably at scale is hard. If each step of an AI agent is only 95% accurate, none of the 30-step workflows will work reliably. Going from 95% to 99.9% accuracy is the real challenge.

Richard Socher

14,902 次观看 • 1 年前

A simple way to check the compression density of a machine. Good compression tear paper ⬇️

A simple way to check the compression density of a machine. Good compression tear paper ⬇️

MAr'S

827,538 次观看 • 4 个月前

Elon Musk explains why AI could be capable of discovering new physics. “You can think of intelligence like a compression problem. For any given field, it can be physics, or any field, you can distill things down to their most basic axiomatic elements, the things that are extremely likely to be true. And then, you can reason up from there to reach a cogent conclusion. I think if you apply that sort of first-principles compression to a field, and then you decompress it and contest the results against reality, then AI is capable of innovation and discovering new physics.” Town Hall in Philadelphia, October 18, 2024

Elon Musk explains why AI could be capable of discovering new physics. “You can think of intelligence like a compression problem. For any given field, it can be physics, or any field, you can distill things down to their most basic axiomatic elements, the things that are extremely likely to be true. And then, you can reason up from there to reach a cogent conclusion. I think if you apply that sort of first-principles compression to a field, and then you decompress it and contest the results against reality, then AI is capable of innovation and discovering new physics.” Town Hall in Philadelphia, October 18, 2024

ELON CLIPS

1,054,036 次观看 • 1 年前

ELON: AI COULD MAKE DISCOVERIES BY REASONING FROM FIRST PRINCIPLES “You can think of intelligence like a compression problem. For any given field, it can be physics, or any field, you can distill things down to their most basic axiomatic elements, the things that are extremely likely to be true. And then, you can reason up from there to reach a cogent conclusion. I think if you apply that sort of first-principles compression to a field, and then you decompress it and contest the results against reality, then AI is capable of innovation and discovering new physics.” Source: Town Hall in Philadelphia, October 2024

ELON: AI COULD MAKE DISCOVERIES BY REASONING FROM FIRST PRINCIPLES “You can think of intelligence like a compression problem. For any given field, it can be physics, or any field, you can distill things down to their most basic axiomatic elements, the things that are extremely likely to be true. And then, you can reason up from there to reach a cogent conclusion. I think if you apply that sort of first-principles compression to a field, and then you decompress it and contest the results against reality, then AI is capable of innovation and discovering new physics.” Source: Town Hall in Philadelphia, October 2024

Mario Nawfal

41,306 次观看 • 1 年前

Elon Musk says Tesla swallows 1.5 GB of video into 2 KB of control. "We really are photons in, controls out. That is the vast majority of your life: vision, photons in, and then motor controls out." Musk reduced the human nervous system to a single equation. That theory runs in every Tesla on the road. "Your Tesla is taking in one and a half gigabytes a second of video and outputting two kilobytes a second of control outputs with the video at 36 hertz and the control frequency at 18." A 750,000-to-1 compression ratio. The car decides which photons matter. "You don't care about the details of the leaves on the tree on the side of the road, but you care a lot about the road signs and the traffic lights, the pedestrians, and even whether someone in another car is looking at you or not looking at you." Then Musk extended the equation past Tesla. The same architecture runs Optimus. **Photons in. Controls out.** Different number of degrees of freedom. A car has steering and acceleration. A robot arm has dozens of joints. Same compression. More fingers on the other side. Musk, who built one Tesla AI engine across two products: "AI is mostly compression and correlation of two bitstreams." The implication: a human, a Tesla, and an Optimus all run the same loop. Musk, looking back at the human equation: "This is what happens with humans." If you're new here, GeniusThinking is a gallery for the greatest minds in economics, psychology, and history. Follow along for more similar content. P.S. I made a playbook breaking down 100+ mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Comment "MODELS" + Follow GeniusThinking and I'll send it to you. — Elon Musk ( Elon Musk ), CEO of Tesla and SpaceX, on Dwarkesh Patel's ( Dwarkesh Patel ) podcast

Elon Musk says Tesla swallows 1.5 GB of video into 2 KB of control. "We really are photons in, controls out. That is the vast majority of your life: vision, photons in, and then motor controls out." Musk reduced the human nervous system to a single equation. That theory runs in every Tesla on the road. "Your Tesla is taking in one and a half gigabytes a second of video and outputting two kilobytes a second of control outputs with the video at 36 hertz and the control frequency at 18." A 750,000-to-1 compression ratio. The car decides which photons matter. "You don't care about the details of the leaves on the tree on the side of the road, but you care a lot about the road signs and the traffic lights, the pedestrians, and even whether someone in another car is looking at you or not looking at you." Then Musk extended the equation past Tesla. The same architecture runs Optimus. Photons in. Controls out. Different number of degrees of freedom. A car has steering and acceleration. A robot arm has dozens of joints. Same compression. More fingers on the other side. Musk, who built one Tesla AI engine across two products: "AI is mostly compression and correlation of two bitstreams." The implication: a human, a Tesla, and an Optimus all run the same loop. Musk, looking back at the human equation: "This is what happens with humans." If you're new here, GeniusThinking is a gallery for the greatest minds in economics, psychology, and history. Follow along for more similar content. P.S. I made a playbook breaking down 100+ mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Comment "MODELS" + Follow GeniusThinking and I'll send it to you. — Elon Musk ( Elon Musk ), CEO of Tesla and SpaceX, on Dwarkesh Patel's ( Dwarkesh Patel ) podcast

GeniusThinking

160,972 次观看 • 29 天前

Jeff Dean says models hallucinate because their training data is “squishy.” But what’s in the context window is sharp, the exact text or video frame right in front of them. The goal is to bring more of the world into that context. Compression gives it intuition. Context gives it precision.

Jeff Dean says models hallucinate because their training data is “squishy.” But what’s in the context window is sharp, the exact text or video frame right in front of them. The goal is to bring more of the world into that context. Compression gives it intuition. Context gives it precision.

vitrupo

41,352 次观看 • 1 个月前

It is important to understand that human developed languages are actually lossy compression algorithms of the—human imagination. The artist comes closer to what is held in the imagination where words could never describe.

It is important to understand that human developed languages are actually lossy compression algorithms of the—human imagination. The artist comes closer to what is held in the imagination where words could never describe.

Brian Roemmele

36,110 次观看 • 1 年前

Matryoshka Representation Learning (MRL) is a super exciting approach to improving the quality and efficiency of embedding models and strategies ✨ MRL allows models to store more information in the earlier dimensions of their data vectors. This method not only boosts performance in tasks like classification and retrieval, but is also a super cool compression technique! Paper: For compression: It’s been so much fun learning and making this video with @DanielW966, thanks for all your help!

Matryoshka Representation Learning (MRL) is a super exciting approach to improving the quality and efficiency of embedding models and strategies ✨ MRL allows models to store more information in the earlier dimensions of their data vectors. This method not only boosts performance in tasks like classification and retrieval, but is also a super cool compression technique! Paper: For compression: It’s been so much fun learning and making this video with @DanielW966, thanks for all your help!

Victoria Slocum

120,436 次观看 • 1 年前

Elon: "Tesla AI is where the rubber hits the road. 'Make no mistakes' is not just a meme joke for self-driving AI. Tesla AI saves lives every day, at large scale. No other AI team can yet make that claim." Tesla

Elon: "Tesla AI is where the rubber hits the road. 'Make no mistakes' is not just a meme joke for self-driving AI. Tesla AI saves lives every day, at large scale. No other AI team can yet make that claim." Tesla

Mario Nawfal

198,218 次观看 • 1 个月前

Russian military personnel check the armor of a Ukrainian HMMWV vehicle - Ai upscaled 150% + dehalo + compression reverse + 30 to 60 FPS + Stabilization

Russian military personnel check the armor of a Ukrainian HMMWV vehicle - Ai upscaled 150% + dehalo + compression reverse + 30 to 60 FPS + Stabilization

Dariusz Zawadzki

34,371 次观看 • 2 年前

DOJO: ELON’S AI GAME-CHANGER Elon: “[Tesla’s Dojo] is the biggest computer overhaul since Cray”—and he’s not kidding. Cray ruled the ‘70s, but Dojo is here to crush AI tasks at scale, training Tesla’s Full Self-Driving system to make cars smarter, safer, and greener. And it’s not just about cars. Dojo’s insane power (shoutout to Tesla’s D1 chip) could spark breakthroughs in healthcare, finance, and chip design. From jobs to science, Dojo isn’t just a computer—it’s a revolution!

DOJO: ELON’S AI GAME-CHANGER Elon: “[Tesla’s Dojo] is the biggest computer overhaul since Cray”—and he’s not kidding. Cray ruled the ‘70s, but Dojo is here to crush AI tasks at scale, training Tesla’s Full Self-Driving system to make cars smarter, safer, and greener. And it’s not just about cars. Dojo’s insane power (shoutout to Tesla’s D1 chip) could spark breakthroughs in healthcare, finance, and chip design. From jobs to science, Dojo isn’t just a computer—it’s a revolution!

Mario Nawfal

115,934 次观看 • 1 年前

The power of compression shirt 🔥

The power of compression shirt 🔥

Brandon Chai

383,957 次观看 • 3 年前

Imitating translucent shadows using dithering is quite a neat technique! I decided to use Bayer dithering instead of Temporal, and video compression is helping a lot here :D #vfx #UnrealEngine

Imitating translucent shadows using dithering is quite a neat technique! I decided to use Bayer dithering instead of Temporal, and video compression is helping a lot here :D #vfx #UnrealEngine

Krystian Komisarek

32,828 次观看 • 1 年前

Minecraft effect for the Rings of Saturn using over 1,000,000 instanced moving blocks/cubes (RIP video compression) made this in May for RAT 🐀 's Reach for the Stars

Minecraft effect for the Rings of Saturn using over 1,000,000 instanced moving blocks/cubes (RIP video compression) made this in May for RAT 🐀 's Reach for the Stars

Ryan

38,532 次观看 • 1 年前

"Tesla is by far the best in the world at real world AI. Tesla is actually much better than anyone at real world AI. Tesla also has the highest intelligence density of any AI by far." 一 Elon Musk

"Tesla is by far the best in the world at real world AI. Tesla is actually much better than anyone at real world AI. Tesla also has the highest intelligence density of any AI by far." 一 Elon Musk

DogeDesigner

64,530 次观看 • 3 个月前

A banger just got released 💥 Here is a snapshot of L2D, the biggest self-driving dataset by far! - 90 TeraBytes of data - 5000 hours of driving - 6 surrounding HD cameras - OPENLY AVAILABLE - Train your car to drive like Tesla at home 🧵 More details in thread

A banger just got released 💥 Here is a snapshot of L2D, the biggest self-driving dataset by far! - 90 TeraBytes of data - 5000 hours of driving - 6 surrounding HD cameras - OPENLY AVAILABLE - Train your car to drive like Tesla at home 🧵 More details in thread

Remi Cadene

171,802 次观看 • 1 年前

I appreciate your diligence, Sergio, however image compression is a real thing and sometimes indiscernible from the signs of AI. This account will continue to avoid it as much as possible though so keep that skeptical eye, my friend.

I appreciate your diligence, Sergio, however image compression is a real thing and sometimes indiscernible from the signs of AI. This account will continue to avoid it as much as possible though so keep that skeptical eye, my friend.

Awful Taste But Great Execution

277,319 次观看 • 6 个月前