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。

They literally made a Convolutional Neural Network in Minecraft before we got GPT-5.

ₕₐₘₚₜₒₙ

215,943 subscribers

2,910,413 次观看 • 2 年前 •via X (Twitter)

科学技术游戏

Anya Rossi• Live Now

Private livecam show

10 条评论

archeus 的头像

archeus2 年前

It was only a matter of time before some complicated shit like this would be made in Minecraft lmao

ₕₐₘₚₜₒₙ — e/acc 的头像

ₕₐₘₚₜₒₙ — e/acc2 年前

Minecraft above all.

Carlos Galarza 的头像

Carlos Galarza2 年前

Next @karpathy video: "Let's build GPT-4.5 from scratch, in Minecraft, spelled out."

ₕₐₘₚₜₒₙ — e/acc 的头像

ₕₐₘₚₜₒₙ — e/acc2 年前

@karpathy The fact that he liked this video is awesome👏

Sváťa Barek 🇺🇦 的头像

Sváťa Barek 🇺🇦2 年前

I am pretty sure We will reach AGI in Minecraft faster than in the real world. Weird way to open-source, but ok 🤪

ₕₐₘₚₜₒₙ — e/acc 的头像

ₕₐₘₚₜₒₙ — e/acc2 年前

Haha!

Fennecous 的头像

Fennecous2 年前

I see 5 so it means this is GPT-5

Mike Kim 的头像

Mike Kim2 年前

The tricky part was doing it without Python libraries

SKY 🦀 的头像

SKY 🦀2 年前

Using command blocks basically allows you to program in Java, not very impressive. Though I have seem computers made entirely on redstone no command blocks.

Mikameel ᯅ 的头像

Mikameel ᯅ2 年前

Hey, I don't think this is done in minecraft but a self made game forked from a Minecraft copy. its quite easy to set this up with Unity Sentis. AFAIK you cant draw like this in Minecraft. Check this tutorial

相关视频

Visualization of Convolutional Neural Network

Visualization of Convolutional Neural Network

Chubby♨️

3,784,329 次观看 • 1 年前

CNN (Convolutional Neural Network) Visualization

CNN (Convolutional Neural Network) Visualization

Interesting As Fuck

390,097 次观看 • 1 年前

In 1993, the world's first handwritten digit recognition convolutional neural network achieved a major Al milestone

In 1993, the world's first handwritten digit recognition convolutional neural network achieved a major Al milestone

Historic Vids

475,572 次观看 • 2 年前

Convolutional Neural Networks in action

Convolutional Neural Networks in action

ₕₐₘₚₜₒₙ

918,115 次观看 • 2 年前

𝗛𝗼𝘄 𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗮𝗹 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀 𝗪𝗼𝗿𝗸 A Convolutional Neural Network (CNN) works by using layers to process images: • Convolutional layers scan the input image using filters to detect features like edges, textures, and patterns.👇

𝗛𝗼𝘄 𝗖𝗼𝗻𝘃𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝗮𝗹 𝗡𝗲𝘂𝗿𝗮𝗹 𝗡𝗲𝘁𝘄𝗼𝗿𝗸𝘀 𝗪𝗼𝗿𝗸 A Convolutional Neural Network (CNN) works by using layers to process images: • Convolutional layers scan the input image using filters to detect features like edges, textures, and patterns.👇

𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰

41,750 次观看 • 1 年前

"Make a Minecraft clone in one single HTML file. Think hard." GPT-5 Pro

"Make a Minecraft clone in one single HTML file. Think hard." GPT-5 Pro

BLCNYY

21,784 次观看 • 10 个月前

GPT - 5 attempt on minecraft ZENITH TO BE EXACT This is impressive this is magic . roon Aidan McLaughlin Jimmy Apples 🍎/acc OPEN AI has literally made something insane 🙏

GPT - 5 attempt on minecraft ZENITH TO BE EXACT This is impressive this is magic . roon Aidan McLaughlin Jimmy Apples 🍎/acc OPEN AI has literally made something insane 🙏

Chetaslua

139,349 次观看 • 10 个月前

we got minecraft bhop before gta 6

we got minecraft bhop before gta 6

quaki

134,383 次观看 • 1 年前

we really got Gordon Ramsay in Minecraft before gta 6 💀💀

we really got Gordon Ramsay in Minecraft before gta 6 💀💀

i like food

2,331,085 次观看 • 2 年前

we got minecraft boothill horses before playable sunday

we got minecraft boothill horses before playable sunday

madi/hyacinth ♡ ashveil & zegect!!

847,660 次观看 • 2 年前

We got Minecraft x Hyper Potions before GTA 6

We got Minecraft x Hyper Potions before GTA 6

Hyper Potions

33,044 次观看 • 1 年前

We got ScreaM playing CS: Minecraft before GTA 6

We got ScreaM playing CS: Minecraft before GTA 6

Tradeit

310,407 次观看 • 1 年前

I’m thrilled to present the KAN Convolutional Layer, a promising neural architecture for image processing. Last week KANs came out, as an alternative to the MLP. We extended this idea to Convolutional Layers, creating the KAN Convolution. Join me in this thread to more about it🧵

I’m thrilled to present the KAN Convolutional Layer, a promising neural architecture for image processing. Last week KANs came out, as an alternative to the MLP. We extended this idea to Convolutional Layers, creating the KAN Convolution. Join me in this thread to more about it🧵

Alex Bodner

200,027 次观看 • 2 年前

we really got ai minecraft before gta 6 this gameplay screws up my mind in a way i can't explain

we really got ai minecraft before gta 6 this gameplay screws up my mind in a way i can't explain

Nucleus☕️

132,876 次观看 • 1 年前

Sam Altman on GPT 5: “ GPT-5 is the smartest thing. GPT-5 is smarter than us in almost every way. You know, and yet here we are. ” This might be the last podcast before the big release!

Sam Altman on GPT 5: “ GPT-5 is the smartest thing. GPT-5 is smarter than us in almost every way. You know, and yet here we are. ” This might be the last podcast before the big release!

Chris

134,450 次观看 • 10 个月前

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Bones

165,655 次观看 • 1 年前

Visualization of a neural network

Visualization of a neural network

Interesting As Fuck

48,219 次观看 • 10 个月前

Just for fun, I've implemented a Convolutional Neural Network (CNN) that predicts handwritten digits... Fully using #glsl and fragment shaders! The model exactly has 2023 parameters and its inner activations are displayed as you draw Try it out live!

Just for fun, I've implemented a Convolutional Neural Network (CNN) that predicts handwritten digits... Fully using #glsl and fragment shaders! The model exactly has 2023 parameters and its inner activations are displayed as you draw Try it out live!

kishimisu

118,358 次观看 • 3 年前

Fukushima's video (1986) shows a CNN that recognises handwritten digits [3], three years before LeCun's video (1989). CNN timeline taken from [5]: ★ 1969: Kunihiko Fukushima published rectified linear units or ReLUs [1] which are now extensively used in CNNs. ★ 1979: Fukushima published the basic CNN architecture with convolution layers and downsampling layers [2]. He called it neocognitron. It was trained by unsupervised learning rules. Compute was 100 times more expensive than in 1989, and a billion times more expensive than today. ★ 1986: Fukushima's video on recognising hand-written digits [3]. ★ 1988: Wei Zhang et al had the first "modern" 2-dimensional CNN trained by backpropagation, and also applied it to character recognition [4]. Compute was about 10 million times more expensive than today. ★ 1989-: later work by others [5]. REFERENCES (more in [5]) [1] K. Fukushima (1969). Visual feature extraction by a multilayered network of analog threshold elements. IEEE Transactions on Systems Science and Cybernetics. 5 (4): 322-333. This work introduced rectified linear units or ReLUs, now widely used in CNNs and other neural nets. [2] K. Fukushima (1979). Neural network model for a mechanism of pattern recognition unaffected by shift in position—Neocognitron. Trans. IECE, vol. J62-A, no. 10, pp. 658-665, 1979. The first deep convolutional neural network architecture, with alternating convolutional layers and downsampling layers. In Japanese. English version: 1980. [3] Movie produced by K. Fukushima, S. Miyake and T. Ito (NHK Science and Technical Research Laboratories), in 1986. YouTube: [4] W. Zhang, J. Tanida, K. Itoh, Y. Ichioka. Shift-invariant pattern recognition neural network and its optical architecture. Proc. Annual Conference of the Japan Society of Applied Physics, 1988. First "modern" backpropagation-trained 2-dimensional CNN, applied to character recognition. [5] J. Schmidhuber (AI Blog, 2025). Who invented convolutional neural networks?

Fukushima's video (1986) shows a CNN that recognises handwritten digits [3], three years before LeCun's video (1989). CNN timeline taken from [5]: ★ 1969: Kunihiko Fukushima published rectified linear units or ReLUs [1] which are now extensively used in CNNs. ★ 1979: Fukushima published the basic CNN architecture with convolution layers and downsampling layers [2]. He called it neocognitron. It was trained by unsupervised learning rules. Compute was 100 times more expensive than in 1989, and a billion times more expensive than today. ★ 1986: Fukushima's video on recognising hand-written digits [3]. ★ 1988: Wei Zhang et al had the first "modern" 2-dimensional CNN trained by backpropagation, and also applied it to character recognition [4]. Compute was about 10 million times more expensive than today. ★ 1989-: later work by others [5]. REFERENCES (more in [5]) [1] K. Fukushima (1969). Visual feature extraction by a multilayered network of analog threshold elements. IEEE Transactions on Systems Science and Cybernetics. 5 (4): 322-333. This work introduced rectified linear units or ReLUs, now widely used in CNNs and other neural nets. [2] K. Fukushima (1979). Neural network model for a mechanism of pattern recognition unaffected by shift in position—Neocognitron. Trans. IECE, vol. J62-A, no. 10, pp. 658-665, 1979. The first deep convolutional neural network architecture, with alternating convolutional layers and downsampling layers. In Japanese. English version: 1980. [3] Movie produced by K. Fukushima, S. Miyake and T. Ito (NHK Science and Technical Research Laboratories), in 1986. YouTube: [4] W. Zhang, J. Tanida, K. Itoh, Y. Ichioka. Shift-invariant pattern recognition neural network and its optical architecture. Proc. Annual Conference of the Japan Society of Applied Physics, 1988. First "modern" backpropagation-trained 2-dimensional CNN, applied to character recognition. [5] J. Schmidhuber (AI Blog, 2025). Who invented convolutional neural networks?

Jürgen Schmidhuber

703,493 次观看 • 6 个月前