正在加载视频...

视频加载失败

返回首页

GOOGLE DEEPMIND JUST TURNED A RANDOM OFFICE WALKTHROUGH INTO A SEARCHABLE 4D WORLD YOU CAN QUERY IN PLAIN ENGLISH. You feed it raw video. Nothing tagged, nothing labeled, no manual annotation. GenCeption tears that footage apart into four layers at once: a depth map, surface normals, a camera raymap,...

himarre's profile picture

Marre

28,476 subscribers

22,861 次观看 • 7 天前 •via X (Twitter)

科学技术教育
LIVE

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

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this
0:21

A DOCTOR BUILT AN AI-QUERYABLE DATABASE OF EVERY DISEASE HE KNOWS IN OBSIDIAN. THE SAME STACK CAN RUN AN ENTIRE COMPANY ON ONE PERSON'S BRAIN Zoomed out, his vault looks like a constellation. Every disease linked to its symptoms, every symptom to the conditions it shows up in, every treatment to what it treats. Adding a new case is one note that wires itself into the rest. It's a personal database, and the structure has nothing to do with medicine. It's just nodes and links. Once you see that, the same setup runs anything: > a startup that needs to remember every customer, decision, and meeting; > a school whose curriculum links to every lecture and student question; > a business where SOPs, clients, and vendors all sit in one queryable graph. Drop Claude on top, and the vault stops being a map. It becomes something you can ask, in plain English, across everything you've ever written down. Full Claude + Obsidian build in the article below. Bookmark this

Yarchi

32,476 次观看 • 1 个月前

Is the Universe Actually a Hologram? “Is everything we see in 3D space, 4D spacetime, actually projected from a 2D surface like a hologram? I would say, in some sense, yeah, by definition. But how physical is it? If you can describe things the same way, you might as well use whatever definition is useful. I don’t always take it too literally in the sense of, like, we are in the celestial sphere. It’s more like, can I convert everything to variables on that celestial sphere, and does that help me organize scattering computations?”
13:38

Is the Universe Actually a Hologram? “Is everything we see in 3D space, 4D spacetime, actually projected from a 2D surface like a hologram? I would say, in some sense, yeah, by definition. But how physical is it? If you can describe things the same way, you might as well use whatever definition is useful. I don’t always take it too literally in the sense of, like, we are in the celestial sphere. It’s more like, can I convert everything to variables on that celestial sphere, and does that help me organize scattering computations?”

Shawn Ryan

66,352 次观看 • 1 个月前

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!
0:51

✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!

@levelsio

119,210 次观看 • 1 年前

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.
2:42

This is a pretty wild model! You can use it to turn an image into a 3D object with texture. The quality is out of this world! I'm not even a designer, and I've been using this nonstop for the last 2 hours. The model is Hunyuan 3D 2.1. It's open source. You'll find model weights, training/inference code, data pipelines, and architecture on their repository. You can even fine-tune it if you want! GitHub Repository: By the way, the model runs on consumer-grade GPUs. You don't need a datacenter for this! I've been using the model from the HuggingFace demo page: To use it, go to the link and upload an image. That's it! Check out the video I recorded for a couple of examples.

Santiago

44,783 次观看 • 1 年前

THE BARRIER BETWEEN A PHOTO AND A VIDEO NO LONGER EXISTS AND HEYGEN JUST PROVED IT. I uploaded a photo to HeyGen, and it came back as a video. I genuinely did not expect that to work. But it did. And now every photo in my camera roll is potential video content.
0:21

THE BARRIER BETWEEN A PHOTO AND A VIDEO NO LONGER EXISTS AND HEYGEN JUST PROVED IT. I uploaded a photo to HeyGen, and it came back as a video. I genuinely did not expect that to work. But it did. And now every photo in my camera roll is potential video content.

Brooks Whale X 🐋

34,537 次观看 • 1 个月前

I'm putting a lot of attention into getting a high quality transfer for the Face Proxy Mesh we're adding to the Fondant Custom Normals Blender addon. Even if the proxy has great Normals, it will not matter if the transfer is distorted. A basic world space Nearest Surface (aka Nearest Face Interpolated) transfer can get screwed up if there are gaps between the meshes. And if they are different shapes and poly counts, there will be! So the first big piece of the puzzle is getting a clean transfer. Before transferring Normals, a transfer space is made and a UV map is transferred from the proxy. Then any other data needed can be transferred in that UV space. As long as it is right, any other data will be clean! (Normals or anything else you might want.) And a UV map is easy to debug because you can put a grid texture on it. If the grid is evenly spaced, then distortion is minimal. This clip shows the differences in distortion between a basic World Space transfer and a better transfer space made by blending Sphere projection and a simple projection of the face forward onto the proxy (used down the center line.) Different faces will need slightly different configuration. Most of this is automatic, but the addon will have some simple controls to adjust it to different face shapes.
1:09

I'm putting a lot of attention into getting a high quality transfer for the Face Proxy Mesh we're adding to the Fondant Custom Normals Blender addon. Even if the proxy has great Normals, it will not matter if the transfer is distorted. A basic world space Nearest Surface (aka Nearest Face Interpolated) transfer can get screwed up if there are gaps between the meshes. And if they are different shapes and poly counts, there will be! So the first big piece of the puzzle is getting a clean transfer. Before transferring Normals, a transfer space is made and a UV map is transferred from the proxy. Then any other data needed can be transferred in that UV space. As long as it is right, any other data will be clean! (Normals or anything else you might want.) And a UV map is easy to debug because you can put a grid texture on it. If the grid is evenly spaced, then distortion is minimal. This clip shows the differences in distortion between a basic World Space transfer and a better transfer space made by blending Sphere projection and a simple projection of the face forward onto the proxy (used down the center line.) Different faces will need slightly different configuration. Most of this is automatic, but the addon will have some simple controls to adjust it to different face shapes.

aVersionOfReality

14,935 次观看 • 1 年前

A DEVELOPER MADE A REAL COMMIT WITHOUT EVER TYPING GIT ADD OR GIT COMMIT -- JUST TO PROVE THE COMMANDS YOU LIVE BY ARE A THIN SHELL OVER A DATABASE YOU'VE NEVER ONCE OPENED 55 minutes from Tim Berglund, a longtime Git teacher and GitHub evangelist, taking the tool apart down to the raw objects almost nobody who uses it every day has ever touched. -> The moment it clicks, Git stops being a pile of memorized commands and becomes what it actually is underneath: a tiny content-addressed database of blobs, trees and commits. git add and git commit are just polite wrappers around writing objects into it by hand. Every commit you've ever made was Git hashing a snapshot and filing it by fingerprint. Branches are just labels pointing at one of those objects. The work you thought you destroyed with a bad reset is still sitting in the reflog. Once you can see that graph, the commands that used to terrify you stop being scary at all. Memorizing commands was never the skill -> reading the object graph in your head is. And with an AI agent now committing and rebasing on your machine faster than you can follow, the one person who can untangle the mess it leaves is the one who knows what's really stored down there. There's a person on every team everyone runs to when Git breaks. This is the talk that quietly turns you into them. You'll reach for it the next time a rebase goes sideways. Bookmark & Watch it today ↓
55:19

A DEVELOPER MADE A REAL COMMIT WITHOUT EVER TYPING GIT ADD OR GIT COMMIT -- JUST TO PROVE THE COMMANDS YOU LIVE BY ARE A THIN SHELL OVER A DATABASE YOU'VE NEVER ONCE OPENED 55 minutes from Tim Berglund, a longtime Git teacher and GitHub evangelist, taking the tool apart down to the raw objects almost nobody who uses it every day has ever touched. -> The moment it clicks, Git stops being a pile of memorized commands and becomes what it actually is underneath: a tiny content-addressed database of blobs, trees and commits. git add and git commit are just polite wrappers around writing objects into it by hand. Every commit you've ever made was Git hashing a snapshot and filing it by fingerprint. Branches are just labels pointing at one of those objects. The work you thought you destroyed with a bad reset is still sitting in the reflog. Once you can see that graph, the commands that used to terrify you stop being scary at all. Memorizing commands was never the skill -> reading the object graph in your head is. And with an AI agent now committing and rebasing on your machine faster than you can follow, the one person who can untangle the mess it leaves is the one who knows what's really stored down there. There's a person on every team everyone runs to when Git breaks. This is the talk that quietly turns you into them. You'll reach for it the next time a rebase goes sideways. Bookmark & Watch it today ↓

slash1s

237,718 次观看 • 1 个月前

Steve Jobs on why everything around you was made by people no smarter than you: "When you grow up, you tend to get told that the world is the way it is and your life is just to live your life inside the world. Try not to bash into the walls too much, have a nice family life, have fun, save a little money. But that's a very limited life." Steve believed most people live with a fundamental misconception. As he puts it: "Life can be much broader once you discover one simple fact. And that is—everything around you that you call life was made up by people that were no smarter than you." He continues: "And you can change it. You can influence it. You can build your own things that other people can use. And the minute that you understand that you can poke life and actually something will pop out the other side—that you can change it, you can mold it." On what matters most: "Maybe the most important thing is to shake off this erroneous notion that life is there and you're just going to live in it versus embrace it, change it, improve it, make your mark upon it. I think that's very important." His perspective on why you should change things: "However you learn that, once you learn it, you'll want to change life and make it better because it's kind of messed up in a lot of ways." The shift: "Once you learn that, you'll never be the same again."
1:28

Steve Jobs on why everything around you was made by people no smarter than you: "When you grow up, you tend to get told that the world is the way it is and your life is just to live your life inside the world. Try not to bash into the walls too much, have a nice family life, have fun, save a little money. But that's a very limited life." Steve believed most people live with a fundamental misconception. As he puts it: "Life can be much broader once you discover one simple fact. And that is—everything around you that you call life was made up by people that were no smarter than you." He continues: "And you can change it. You can influence it. You can build your own things that other people can use. And the minute that you understand that you can poke life and actually something will pop out the other side—that you can change it, you can mold it." On what matters most: "Maybe the most important thing is to shake off this erroneous notion that life is there and you're just going to live in it versus embrace it, change it, improve it, make your mark upon it. I think that's very important." His perspective on why you should change things: "However you learn that, once you learn it, you'll want to change life and make it better because it's kind of messed up in a lot of ways." The shift: "Once you learn that, you'll never be the same again."

Jaynit

48,518 次观看 • 6 个月前

🚨ELON MUSK: "As we dug into USAID it became apparent that what we have here is not an apple with a worm in it, but we have actually just a ball of worms. If you have an apple with a worm in it, you can take the worm out. If you have a whole ball of worms, it's hopeless. USAID is a ball of worms. There is no apple. And when there is no apple you just need to get rid of the whole thing. That's why it's got to go. It's beyond repair."
0:39

🚨ELON MUSK: "As we dug into USAID it became apparent that what we have here is not an apple with a worm in it, but we have actually just a ball of worms. If you have an apple with a worm in it, you can take the worm out. If you have a whole ball of worms, it's hopeless. USAID is a ball of worms. There is no apple. And when there is no apple you just need to get rid of the whole thing. That's why it's got to go. It's beyond repair."

Autism Capital 🧩

1,539,400 次观看 • 1 年前

i built a tool that lets you clone ANY video with AI saw a movie scene you want to recreate? a commercial? a music video? just upload it to this tool and get the exact structured prompt to generate it in sora 2 you no longer need to guess how to describe what you want to generate. show the tool the reference and it engineers the prompt for you. the tool analyzes: - camera movements and angles - lighting and color grading - scene composition and timing then converts everything into sora-optimized prompt structure this is how you recreate any visual style without prompt engineering experience RT + reply 'TOOL' and i'll send you access (must follow so i can dm)
0:21

i built a tool that lets you clone ANY video with AI saw a movie scene you want to recreate? a commercial? a music video? just upload it to this tool and get the exact structured prompt to generate it in sora 2 you no longer need to guess how to describe what you want to generate. show the tool the reference and it engineers the prompt for you. the tool analyzes: - camera movements and angles - lighting and color grading - scene composition and timing then converts everything into sora-optimized prompt structure this is how you recreate any visual style without prompt engineering experience RT + reply 'TOOL' and i'll send you access (must follow so i can dm)

Miko

42,946 次观看 • 9 个月前

You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join it with other tables. It's awesome! This is all thanks to mindshub. Here is their GitHub repository: They are sponsoring this post. Watch the video.
6:49

You can now access AI directly from your database! Here is a step-by-step demo that uses GPT-4 to classify customer reviews from a MySQL dataset. And I'm only writing SQL instructions! You have to see it! The model acts as another table in the database. I can query it and join it with other tables. It's awesome! This is all thanks to mindshub. Here is their GitHub repository: They are sponsoring this post. Watch the video.

Santiago

209,454 次观看 • 2 年前

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.
5:58:26

AI BASKETBALL ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, OPENCV, AND PYTHON. Take any NBA broadcast. Any camera angle. Any resolution. Feed it into the system. YOLO finds every player and the ball. Frame by frame. No manual annotation. No pre-labeled data.The model just sees the court and understands it. Zero-shot classification looks at jersey pixels and decides who plays for whom. Two teams separated in milliseconds. Without ever being told the team names. But here's where it gets wild. Court keypoint detection identifies the geometry of the playing surface. Homography transforms the broadcast camera into a top-down tactical map. Real meters. Real coordinates. From a flat 2D video. Now every player has a position on a real court. Every movement becomes a data point. Every pass becomes a vector. Speed. Distance. Possession time. Pass networks. All extracted from nothing but pixels. No GPS. No chips in the ball. No million-dollar Second Spectrum setup. A Python script and a GPU. The full pipeline is open source. The tutorial walks through every line of code. From detection to transformation to analytics output. Teams used to pay six figures for this data. Now you build it in an afternoon. Computer vision didn't just enter basketball. It democratized it.

zostaff

230,194 次观看 • 3 个月前

Bridgit Mendler on how Northwood is fixing the space economy's ground infrastructure problem: "The problem that we're solving is for every satellite, it requires a connection point back to Earth so that they can control the spacecraft." "That point of contact on Earth is called the ground infrastructure." "If you don't have it, you don't have a space mission." "It literally is just like a rock in space you're doing nothing with." "There was this whole boom around spacecraft manufacturing." "And interestingly what started becoming the longest pole in the tent was just getting the point of contact on the ground to connect with." "You could build a satellite and launch it faster than you could actually connect with it from the ground." "Which just seemed absurd." Bridgit Mendler with Erik Torenberg
1:42

Bridgit Mendler on how Northwood is fixing the space economy's ground infrastructure problem: "The problem that we're solving is for every satellite, it requires a connection point back to Earth so that they can control the spacecraft." "That point of contact on Earth is called the ground infrastructure." "If you don't have it, you don't have a space mission." "It literally is just like a rock in space you're doing nothing with." "There was this whole boom around spacecraft manufacturing." "And interestingly what started becoming the longest pole in the tent was just getting the point of contact on the ground to connect with." "You could build a satellite and launch it faster than you could actually connect with it from the ground." "Which just seemed absurd." Bridgit Mendler with Erik Torenberg

a16z

13,324 次观看 • 4 个月前

ELON MUSK: The only way to reach 1,000 terawatts of AI power is a mass driver on the Moon. "In order to get to 1,000x from a terawatt per year. The only way that we can really achieve that is on the moon with a mass driver, essentially where you do local production of photovoltaics and radiators on the moon, maybe you bring the chips from Earth, or you could conceivably make the chips on the moon, and but you need most of the mass to be made on the moon, so you don't have to transport it to the moon from Earth, and then because the moon has no atmosphere and only 1/6 Earth's gravity, you can accelerate the AI satellites into deep space without a rocket, so you can basically shoot them into space using an electromagnetic gun, like a, like a rail gun type. I mean, just, it's basically a linear electric motor, as a way to think about it."
1:06

ELON MUSK: The only way to reach 1,000 terawatts of AI power is a mass driver on the Moon. "In order to get to 1,000x from a terawatt per year. The only way that we can really achieve that is on the moon with a mass driver, essentially where you do local production of photovoltaics and radiators on the moon, maybe you bring the chips from Earth, or you could conceivably make the chips on the moon, and but you need most of the mass to be made on the moon, so you don't have to transport it to the moon from Earth, and then because the moon has no atmosphere and only 1/6 Earth's gravity, you can accelerate the AI satellites into deep space without a rocket, so you can basically shoot them into space using an electromagnetic gun, like a, like a rail gun type. I mean, just, it's basically a linear electric motor, as a way to think about it."

DogeDesigner

122,205 次观看 • 1 个月前

I paid $150/mo for a mobile developer. That was around 5 years ago. Today, you can describe the app you want to create in plain English and have AI build it for you. Check out the video I recorded using OnSpace AI. It took me 10 minutes to build a mobile application that scans receipts and uses OCR to read all of the information. A few of the highlights: • You can create what you want by just describing it. • You can plug in cutting-edge AI models instantly. No API keys, no setup. • You can stitch together reasoning, workflows, data, and UI without writing a single line of code. • Whatever you build runs right away, so you can iterate in seconds. A couple of years ago, it would have taken the best developers days to get to this point. Pretty incredible progress! You can find a link to this project in the comment below.
4:14

I paid $150/mo for a mobile developer. That was around 5 years ago. Today, you can describe the app you want to create in plain English and have AI build it for you. Check out the video I recorded using OnSpace AI. It took me 10 minutes to build a mobile application that scans receipts and uses OCR to read all of the information. A few of the highlights: • You can create what you want by just describing it. • You can plug in cutting-edge AI models instantly. No API keys, no setup. • You can stitch together reasoning, workflows, data, and UI without writing a single line of code. • Whatever you build runs right away, so you can iterate in seconds. A couple of years ago, it would have taken the best developers days to get to this point. Pretty incredible progress! You can find a link to this project in the comment below.

Santiago

44,774 次观看 • 7 个月前

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!
2:41

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 次观看 • 3 个月前

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.
21:00

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

68,221 次观看 • 29 天前

MolmoAct2 kinda just works out of the box in an unseen environment and with unseen objects. I find it really crazy that I can just download a model from the internet and plug it into my robot and it can do some tasks at a limited capacity right away. this video is at 2x speed
1:48

MolmoAct2 kinda just works out of the box in an unseen environment and with unseen objects. I find it really crazy that I can just download a model from the internet and plug it into my robot and it can do some tasks at a limited capacity right away. this video is at 2x speed

atharva ☆

32,150 次观看 • 2 个月前

I asked Luke Kornet about his memories from stretches where he was a DNP for many games in a row, and what his message is to the young guys who find themselves in that position now: “It's just a lot of peace to come to life of accepting the position that you're in and then just doing the best with that, versus trying to fight it and want to be in a different one.” “You can spend a lot of time worrying about things that you can't really control. But when you just take the opportunity that you have and do the best with that, you can have days like today where a lot of guys came in and were able to contribute. You can have peace about knowing that you did your job well, just as you did the day before, the day after. It might just look a different way every time. I feel like that's what I've been taught through my life. That's the only thing attitude that you can have that you can actually do something with – versus trying to control things that are outside of what you can control.”
2:15

I asked Luke Kornet about his memories from stretches where he was a DNP for many games in a row, and what his message is to the young guys who find themselves in that position now: “It's just a lot of peace to come to life of accepting the position that you're in and then just doing the best with that, versus trying to fight it and want to be in a different one.” “You can spend a lot of time worrying about things that you can't really control. But when you just take the opportunity that you have and do the best with that, you can have days like today where a lot of guys came in and were able to contribute. You can have peace about knowing that you did your job well, just as you did the day before, the day after. It might just look a different way every time. I feel like that's what I've been taught through my life. That's the only thing attitude that you can have that you can actually do something with – versus trying to control things that are outside of what you can control.”

Noa Dalzell 🏀

48,992 次观看 • 1 年前