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。

Found a nice resource for learning ML/AI concepts interactively: VizLearn. You can play with gradient descent, SVMs, PCA, Bayes, BPE tokenization, Q/K/V, KV cache, quantization and a lot more, and watch the actual computation change as you modify the inputs. Free, no account needed.

Tech with Mak

47,849 subscribers

14,479 次观看 • 25 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

2 条评论

Sijie · AI × PCB 的头像

Sijie · AI × PCB25 天前

Interactive beats passive. The hardware versions: clearance, coupling, silkscreen keep-out. I turned 131 tutorial episodes into 30 rules (24 runnable) because reading about rules never catches a header 1.14mm outside the board. Running them does.

Shefali 的头像

Shefali25 天前

Thanks for sharing, Mayank

相关视频

Holy shit… someone just made machine learning click. Not static diagrams. Not math-heavy PDFs. Not black-box training. Real algorithms — training step-by-step — visually. It’s called Machine Learning Visualized and it lets you watch models learn in real time. Here’s why this is different: Instead of dumping theory first, it shows optimization happening live: • gradients moving • weights updating • decision boundaries shifting • loss decreasing • models converging You literally see learning happen. Everything is built from first principles: • Gradient Descent • Logistic Regression • Perceptron • PCA • K-Means • Neural Networks • Backpropagation No magic. Just math → code → visualization. Each chapter is a Jupyter notebook that derives the math then implements it then animates training. So you can watch: • neural nets shape decision surfaces • PCA rotate feature space • K-means clusters form live • gradient descent find minima • sigmoid reshape boundaries • backprop update weights step-by-step This solves a huge problem: Most ML resources teach: math → code → ??? → trained model This shows: math → code → learning process → result Which means you finally understand: • why gradients matter • how weights evolve • what loss landscapes look like • how convergence actually happens • why deep nets learn non-linear functions Even better: You can open any notebook modify parameters and watch behavior change instantly. Learning ML becomes interactive. Not passive. Not abstract. Not confusing. Just… visible. Perfect for: • beginners learning ML • devs moving into AI • interview prep • teaching concepts • understanding backprop • visual learners • building intuition This is the kind of resource that makes neural networks finally “click”. Link: We’re moving from: reading about ML → watching ML learn That’s a big shift. Because once you can see training, you stop memorizing… and start understanding. AI education just got visual.

Holy shit… someone just made machine learning click. Not static diagrams. Not math-heavy PDFs. Not black-box training. Real algorithms — training step-by-step — visually. It’s called Machine Learning Visualized and it lets you watch models learn in real time. Here’s why this is different: Instead of dumping theory first, it shows optimization happening live: • gradients moving • weights updating • decision boundaries shifting • loss decreasing • models converging You literally see learning happen. Everything is built from first principles: • Gradient Descent • Logistic Regression • Perceptron • PCA • K-Means • Neural Networks • Backpropagation No magic. Just math → code → visualization. Each chapter is a Jupyter notebook that derives the math then implements it then animates training. So you can watch: • neural nets shape decision surfaces • PCA rotate feature space • K-means clusters form live • gradient descent find minima • sigmoid reshape boundaries • backprop update weights step-by-step This solves a huge problem: Most ML resources teach: math → code → ??? → trained model This shows: math → code → learning process → result Which means you finally understand: • why gradients matter • how weights evolve • what loss landscapes look like • how convergence actually happens • why deep nets learn non-linear functions Even better: You can open any notebook modify parameters and watch behavior change instantly. Learning ML becomes interactive. Not passive. Not abstract. Not confusing. Just… visible. Perfect for: • beginners learning ML • devs moving into AI • interview prep • teaching concepts • understanding backprop • visual learners • building intuition This is the kind of resource that makes neural networks finally “click”. Link: We’re moving from: reading about ML → watching ML learn That’s a big shift. Because once you can see training, you stop memorizing… and start understanding. AI education just got visual.

Suryansh Tiwari

132,906 次观看 • 6 个月前

I added KV caching and INT8 KV quantization to our transformer inference, improving throughput by 35x. All of this was done from scratch in Rust + CUDA, on top of a homemade ML framework. On a 4-token prompt with 252 generated tokens: - Original: 0.76 tok/s - KV cache fp32: 27.21 tok/s - KV cache int8 (quantized): 27.29 tok/s Try it out yourself here: In practice: - KV caching gave us about a 35x end-to-end speedup - INT8 KV cache kept roughly the same speed as fp32 but cut KV cache memory by 3.78x FP32 cache used 4.5 MB in this run while the INT8 cache used only 1.19 MB This simple change to inference created a huge impact on performance. To learn more about the KV cache and other optimizations like this, check out the blog at

I added KV caching and INT8 KV quantization to our transformer inference, improving throughput by 35x. All of this was done from scratch in Rust + CUDA, on top of a homemade ML framework. On a 4-token prompt with 252 generated tokens: - Original: 0.76 tok/s - KV cache fp32: 27.21 tok/s - KV cache int8 (quantized): 27.29 tok/s Try it out yourself here: In practice: - KV caching gave us about a 35x end-to-end speedup - INT8 KV cache kept roughly the same speed as fp32 but cut KV cache memory by 3.78x FP32 cache used 4.5 MB in this run while the INT8 cache used only 1.19 MB This simple change to inference created a huge impact on performance. To learn more about the KV cache and other optimizations like this, check out the blog at

Reese Chong

53,026 次观看 • 6 个月前

The easiest way to misunderstand KV cache is to assume every token goes through an LLM in the same way. It doesn’t. Take a decoder-only Transformer and a four-token prompt: x1, x2, x3, x4. During the prefill phase, the prompt is processed and each self-attention layer computes the keys and values for its prompt positions. Those K/V states are stored in that layer’s KV cache. The representation at the final prompt position produces the logits used to select the first generated token, y1. Here is the part that is easy to miss => Selecting y1 does not mean y1 is already in the KV cache. On the next forward step, y1 enters the model as position 5. At each self-attention layer, its Q, K and V are computed. Its query attends to the cached K/V from positions 1-4 plus its own current K/V at position 5. Its K/V then become part of that layer’s cache. The resulting final-layer representation produces logits for y2. Then y2 is processed as position 6, its K/V extend the cache, and the process continues. So for standard single-token, KV-cached autoregressive decoding: > prompt → prefill phase > new token → process one new position > past K/V → reuse them instead of recomputing them > KV cache → grows as new positions are processed One subtle distinction matters a lot and I want to highlight it => a token can be generated before it has been processed into the KV cache.

The easiest way to misunderstand KV cache is to assume every token goes through an LLM in the same way. It doesn’t. Take a decoder-only Transformer and a four-token prompt: x1, x2, x3, x4. During the prefill phase, the prompt is processed and each self-attention layer computes the keys and values for its prompt positions. Those K/V states are stored in that layer’s KV cache. The representation at the final prompt position produces the logits used to select the first generated token, y1. Here is the part that is easy to miss => Selecting y1 does not mean y1 is already in the KV cache. On the next forward step, y1 enters the model as position 5. At each self-attention layer, its Q, K and V are computed. Its query attends to the cached K/V from positions 1-4 plus its own current K/V at position 5. Its K/V then become part of that layer’s cache. The resulting final-layer representation produces logits for y2. Then y2 is processed as position 6, its K/V extend the cache, and the process continues. So for standard single-token, KV-cached autoregressive decoding: > prompt → prefill phase > new token → process one new position > past K/V → reuse them instead of recomputing them > KV cache → grows as new positions are processed One subtle distinction matters a lot and I want to highlight it => a token can be generated before it has been processed into the KV cache.

Tech with Mak

12,211 次观看 • 1 个月前

Huge DX update! We shipped a big improvement to wrangler, which means you can view and modify the state of your local KV, D!, R2 bindings through a nice local dashboard No code change required. Local explorer is available in wrangler 4.81.2 and up

Huge DX update! We shipped a big improvement to wrangler, which means you can view and modify the state of your local KV, D!, R2 bindings through a nice local dashboard No code change required. Local explorer is available in wrangler 4.81.2 and up

Confidence

11,699 次观看 • 6 个月前

You can literally type a sentence and watch a Transformer process it. This interactive explainer runs a GPT-style model in the browser and lets you follow the whole path: tokenization → embeddings → Q/K/V → attention → MLP → logits → next-token probabilities You can inspect attention maps, intermediate values, and change temperature, top-k and top-p to see how generation changes. If Transformers still feel like boxes connected by arrows, this is worth opening.

You can literally type a sentence and watch a Transformer process it. This interactive explainer runs a GPT-style model in the browser and lets you follow the whole path: tokenization → embeddings → Q/K/V → attention → MLP → logits → next-token probabilities You can inspect attention maps, intermediate values, and change temperature, top-k and top-p to see how generation changes. If Transformers still feel like boxes connected by arrows, this is worth opening.

Tech with Mak

134,790 次观看 • 18 天前

Found this free site that lets you play with ML algorithms in real time Adjust a parameter.... the model updates instantly.... no code, no setup Link - neural networks, decision trees, SVM, k-means.... all interactive

Found this free site that lets you play with ML algorithms in real time Adjust a parameter.... the model updates instantly.... no code, no setup Link - neural networks, decision trees, SVM, k-means.... all interactive

Vaishnavi

25,380 次观看 • 7 个月前

✨️V.2 customizable vtuber model is finally out! ✨️ You can modify the facial structure, hairstyles, change the colors, and many more features! ❗️ Link below #Live2D #VTubeStudio

✨️V.2 customizable vtuber model is finally out! ✨️ You can modify the facial structure, hairstyles, change the colors, and many more features! ❗️ Link below #Live2D #VTubeStudio

May 🐻🍿Live2D artist ✨️

91,106 次观看 • 2 年前

wrote a piece on how we do tiling and gradient descent on TinyTPU included some animations of the weight and bias gradient descent

wrote a piece on how we do tiling and gradient descent on TinyTPU included some animations of the weight and bias gradient descent

Xander Chin

33,195 次观看 • 1 年前

Interesting approach to long context/continual learning here from Baseten at Cursor Compact long trajectories by compressing a prefix of the KV cache using an MLP/autoencoder. You can train this "compactor" MLP by learning to reconstruct activations that the original KV cache would produce on subsequent tokens. This maximally reconstructs information from long context that's useful for subsequent outputs. If you run an agent over extremely long context and run this compaction recursively, the activations of this compressed KV cache become like trained weights. Similar to task-specific LoRA or "cartridges". Would not be surprised if OpenAI is running a similar algorithm for their blackbox compaction. Clear benefits here if you can avoid busting the cache, as e.g. compacting via writing to a text file would. Seeing many emerging approaches to fixed size latent states for LLMs that seem promising. If building a task-specific KV cache compression ends up being more sample efficient than running backprop, getting this to "work" feels like one of the 2-3 remaining breakthroughs on the path to true AGI

Interesting approach to long context/continual learning here from Baseten at Cursor Compact long trajectories by compressing a prefix of the KV cache using an MLP/autoencoder. You can train this "compactor" MLP by learning to reconstruct activations that the original KV cache would produce on subsequent tokens. This maximally reconstructs information from long context that's useful for subsequent outputs. If you run an agent over extremely long context and run this compaction recursively, the activations of this compressed KV cache become like trained weights. Similar to task-specific LoRA or "cartridges". Would not be surprised if OpenAI is running a similar algorithm for their blackbox compaction. Clear benefits here if you can avoid busting the cache, as e.g. compacting via writing to a text file would. Seeing many emerging approaches to fixed size latent states for LLMs that seem promising. If building a task-specific KV cache compression ends up being more sample efficient than running backprop, getting this to "work" feels like one of the 2-3 remaining breakthroughs on the path to true AGI

Jay Hack

30,031 次观看 • 3 个月前

One of the amazing things about Ai is the possibility of just exploring a world you imagine for no other reason than your own play and joy. Made with Luma Ray3 Modify. Luma | Dream Lab

One of the amazing things about Ai is the possibility of just exploring a world you imagine for no other reason than your own play and joy. Made with Luma Ray3 Modify. Luma | Dream Lab

Jon Finger

336,294 次观看 • 9 个月前

I always enjoy talking with my friend Sean White, as his background and inputs are multidisciplinary: machine learning, neuroscience, creativity, decoding animal languages—you name it. We cover a lot—and touch on Inflection AI, where he’s CEO. Full ep:

I always enjoy talking with my friend Sean White, as his background and inputs are multidisciplinary: machine learning, neuroscience, creativity, decoding animal languages—you name it. We cover a lot—and touch on Inflection AI, where he’s CEO. Full ep:

Reid Hoffman

18,211 次观看 • 2 年前

What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt? Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based platform for interactive artificial life research. The setup: several small CNNs share a 2D grid, each seeing only a 3x3 neighborhood. No global plan. They compete for territory by attacking neighbours and defending against incoming attacks, learning via gradient descent online while the simulation runs. What we didn't expect was the role of the learning itself. Gradient descent isn't just optimising each species' strategy. Instead, it acts to stabilize the whole system during simulation. Species that overextend get pushed back by the loss. Species that stagnate get nudged to grow. This means you can push parameters toward edge-of-chaos regimes: a zone characterised by emergent complexity. Letting the neural networks learn acts to hold the complex system together while you explore and interact. The platform lets you steer all of this interactively. You can draw walls to create niches, erase parts of the system online, and tune 40+ system parameters to explore the most interesting configurations. We find it mesmerizing to watch species carve out territories and reorganise when you perturb them. Everything runs client-side in your browser, no install needed. Blog: Code:

What happens when you put competing neural networks in a Petri Dish and start changing the rules while they adapt? Last year we released Petri Dish NCA, where neural nets are the organisms that learn during simulation. Today we're releasing Digital Ecosystems: a browser-based platform for interactive artificial life research. The setup: several small CNNs share a 2D grid, each seeing only a 3x3 neighborhood. No global plan. They compete for territory by attacking neighbours and defending against incoming attacks, learning via gradient descent online while the simulation runs. What we didn't expect was the role of the learning itself. Gradient descent isn't just optimising each species' strategy. Instead, it acts to stabilize the whole system during simulation. Species that overextend get pushed back by the loss. Species that stagnate get nudged to grow. This means you can push parameters toward edge-of-chaos regimes: a zone characterised by emergent complexity. Letting the neural networks learn acts to hold the complex system together while you explore and interact. The platform lets you steer all of this interactively. You can draw walls to create niches, erase parts of the system online, and tune 40+ system parameters to explore the most interesting configurations. We find it mesmerizing to watch species carve out territories and reorganise when you perturb them. Everything runs client-side in your browser, no install needed. Blog: Code:

Sakana AI

258,700 次观看 • 6 个月前

Microsoft has launched a powerful new data analysis tool! Introducing Data Formulator, a 100% open-source LLM-powered, no-code tool that transforms data in a snap and creates stunning visualizations. Key features include: 🤖 AI-powered data transformation 🖱️ Interactive drag-and-drop UI for visualizations 💬 Seamless blend of UI & natural language inputs But that’s not all: You can even create charts beyond your initial dataset. Data Formulator automatically identifies extra computation needs, generates fields for you, and outputs the final visualization. Find the GitHub repo in the next tweet! _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on AI and Machine Learning.

Microsoft has launched a powerful new data analysis tool! Introducing Data Formulator, a 100% open-source LLM-powered, no-code tool that transforms data in a snap and creates stunning visualizations. Key features include: 🤖 AI-powered data transformation 🖱️ Interactive drag-and-drop UI for visualizations 💬 Seamless blend of UI & natural language inputs But that’s not all: You can even create charts beyond your initial dataset. Data Formulator automatically identifies extra computation needs, generates fields for you, and outputs the final visualization. Find the GitHub repo in the next tweet! _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on AI and Machine Learning.

Akshay 🚀

280,679 次观看 • 1 年前

Tokenization is the tool for free markets. Better credit terms, programmable yield, and no gatekeeper deciding what you can access.

Tokenization is the tool for free markets. Better credit terms, programmable yield, and no gatekeeper deciding what you can access.

Securitize

14,292 次观看 • 5 个月前

I think I found my favourite one. It’s a pottery studio. But instead of just showing you a finished vase, you can actually shape it yourself. Change the height. Adjust the body width. Change the opening. And watch the proportions change in real time. It feels more like a digital workbench than a website. That’s what I find interesting about GPT-6 Astra. It’s not just generating a visual. It’s helping turn an idea into something you can actually play with. Have a look at what you can build: Enter Pro by Converge.AI #GPT6Astra #EnterPro #convergeai #AI #VibeCoding

I think I found my favourite one. It’s a pottery studio. But instead of just showing you a finished vase, you can actually shape it yourself. Change the height. Adjust the body width. Change the opening. And watch the proportions change in real time. It feels more like a digital workbench than a website. That’s what I find interesting about GPT-6 Astra. It’s not just generating a visual. It’s helping turn an idea into something you can actually play with. Have a look at what you can build: Enter Pro by Converge.AI #GPT6Astra #EnterPro #convergeai #AI #VibeCoding

Elizabeth

82,663 次观看 • 1 个月前

Small prototype with AI + generative sketching workflow. Sketches are written as usual in code, and prompts can be used to augment/modify the artwork's inputs and parameters. 🤖 This is using OpenAI API with GPT 3.5, already showing a surprisingly good grasp of color for an LLM.

Small prototype with AI + generative sketching workflow. Sketches are written as usual in code, and prompts can be used to augment/modify the artwork's inputs and parameters. 🤖 This is using OpenAI API with GPT 3.5, already showing a surprisingly good grasp of color for an LLM.

Matt DesLauriers

22,328 次观看 • 3 年前