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。

Opus 5 enables this crazy new live AI tutor concept I'm prototyping for @AlphaSchool. It powers chat + direction under the hood, while a custom trained tiny world model(ish) acts as a real-time renderer and interactivity layer. Still rough, but it's already kind of insane.

Matt Shumer

385,602 subscribers

155,181 次观看 • 1 个月前 •via X (Twitter)

艺术科学技术教育

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

I've been experimenting with block-based mega menus powered by a single custom block and the Interactivity API. Still a bit rough under the hood, but a successful proof-of-concept.

I've been experimenting with block-based mega menus powered by a single custom block and the Interactivity API. Still a bit rough under the hood, but a successful proof-of-concept.

Nick Diego

10,467 次观看 • 2 年前

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

World Labs CEO Dr. Fei-Fei Li explains says "world model" has become an overloaded term & explains what each kind of world model does: "Right now there are three ways of calling world models when it comes to spatial intelligence." "One is what I call a renderer, when the model puts beautiful pixels on the screen." "Another kind of world model is what we call a planner. That is more for machines, more for robots." "The third kind, which I think is the linchpin of the three, is a simulator." "A simulator could become a renderer. The simulator could become a planner. But this layer is a huge critical path to unlock spatial intelligence. And that's what World Labs is working on." Fei-Fei Li at Bloomberg Tech live with Emily Chang

a16z

112,217 次观看 • 2 个月前

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

The new SpaceX-Cursor model is going to be insane. It is being trained from scratch, unlike previous Composer models, which were built off Kimi. This new model is Elon’s attempt to get back in the AI race, and he might rejoin as the frontrunner. Composer 2.5 is already a world-class model, only losing to models like GPT-5.5, Opus 4.8, and Fable 5. Grok Composer 3, with SpaceX’s massive compute and xAI’s team, could become the best AI model on the planet. Elon is back.

Ali Romman

119,837 次观看 • 2 个月前

I'm deeply impressed. You can now have your own AI tutor who can see your screen and chat in real time with Gemini 2.0. It's a real revolution in the way you learn new things. Available for free using Google AI Studio (link below)

I'm deeply impressed. You can now have your own AI tutor who can see your screen and chat in real time with Gemini 2.0. It's a real revolution in the way you learn new things. Available for free using Google AI Studio (link below)

Paul Couvert

266,658 次观看 • 1 年前

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,164,245 次观看 • 5 个月前

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

1/ Tencent releases HY World 1.5 (WorldPlay), an open-source real-time world model with 24fps A streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency In direct comparison to Genie 3, it's technically inferior, and there's no information on how long the consistency will last. However, Tencent has released a significant world model as open source for the first time, making it available to everyone. A few more examples, a thread 🧵

Chubby♨️

37,776 次观看 • 8 个月前

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Wes Roth

82,506 次观看 • 5 个月前

I got something crazy for today - custom GI from a plugin in #UE5!! This is super rough and unoptimized sketch, but it's already faster than Lumen, though of course it's muuuch less accurate. Here I'm just imitating Large Scale AO using Global SDFs, no sun light bounces yet.

I got something crazy for today - custom GI from a plugin in #UE5!! This is super rough and unoptimized sketch, but it's already faster than Lumen, though of course it's muuuch less accurate. Here I'm just imitating Large Scale AO using Global SDFs, no sun light bounces yet.

Dmitry Karpukhin

25,639 次观看 • 1 年前

AI Mode in Search introduces new reasoning and tools under the hood with a custom version of Gemini models. For any question, it makes a plan, breaks it down into related subtopics, and runs multiple Google searches to find the most helpful and reliable info. With this query fan-out, AI Mode finds real-time info from both the web and from Google, like facts from our Knowledge Graph, info about the real-world, and shopping details on billions of products. This approach helps you get a greater breadth and depth of information than a traditional search on Google.

AI Mode in Search introduces new reasoning and tools under the hood with a custom version of Gemini models. For any question, it makes a plan, breaks it down into related subtopics, and runs multiple Google searches to find the most helpful and reliable info. With this query fan-out, AI Mode finds real-time info from both the web and from Google, like facts from our Knowledge Graph, info about the real-world, and shopping details on billions of products. This approach helps you get a greater breadth and depth of information than a traditional search on Google.

Robby Stein

38,619 次观看 • 1 年前

🌐 BEATOZ — the future of Web3, connected 📌 Web3: Web3 is growing fast, but businesses still struggle to use it in real operations. Assets are on-chain, but compliance and processes remain off-chain. 📌 Hybrid Layer-1 mainnet: BEATOZ solves this with a Hybrid Layer-1 mainnet, connecting Web3 technology with real-world business systems. 📌 Operations: With private and public networks working together, it enables secure, scalable, and compliant operations. From payments to digital assets, BEATOZ powers real-world blockchain use. 🛡🚀 #BEATOZ #Web3 #Blockchain

🌐 BEATOZ — the future of Web3, connected 📌 Web3: Web3 is growing fast, but businesses still struggle to use it in real operations. Assets are on-chain, but compliance and processes remain off-chain. 📌 Hybrid Layer-1 mainnet: BEATOZ solves this with a Hybrid Layer-1 mainnet, connecting Web3 technology with real-world business systems. 📌 Operations: With private and public networks working together, it enables secure, scalable, and compliant operations. From payments to digital assets, BEATOZ powers real-world blockchain use. 🛡🚀 #BEATOZ #Web3 #Blockchain

BEATOZ

15,771 次观看 • 2 个月前

Testing out the new Google Genie 3 AI game engine! Wanted to give the Sonic franchise a go. It's been a while since Forces and I'm curious what a grittier, open world take on the series would look like. Obviously a little rough but this is really impressive for a start

Testing out the new Google Genie 3 AI game engine! Wanted to give the Sonic franchise a go. It's been a while since Forces and I'm curious what a grittier, open world take on the series would look like. Obviously a little rough but this is really impressive for a start

dingle

251,879 次观看 • 7 个月前

Alright so I've been cooking something on Monad these past days The hackathon gave me some motivation to keep shipping new stuff. I saw this price prediction game concept on Solana and thought it would be a great fit for Monad, you need a fast chain for this kind of game to feel right So I'm building this, you get a live grid with the MON price moving in real-time, click where you think it's going, bet lands on-chain in under a second. No wallet popups thanks to session keys, just pure gameplay Still a ton to improve, settlement, UI, balancing but already deployed and playable on Monad testnet What u guys think? 👇

Alright so I've been cooking something on Monad these past days The hackathon gave me some motivation to keep shipping new stuff. I saw this price prediction game concept on Solana and thought it would be a great fit for Monad, you need a fast chain for this kind of game to feel right So I'm building this, you get a live grid with the MON price moving in real-time, click where you think it's going, bet lands on-chain in under a second. No wallet popups thanks to session keys, just pure gameplay Still a ton to improve, settlement, UI, balancing but already deployed and playable on Monad testnet What u guys think? 👇

Novee

46,075 次观看 • 6 个月前

i'm looking rough, but who cares I'm serious with this post. I hope the news about Dave is not AI!!!!! if it is, my post is still coming from my heart and soul. It is so important that this music carry on especially with the AI music out there. those of us that can still go out and play. should do it as long as they can physically and emotionally carry that torch. Van Halen was, should be, and hopefully always will be real live music, not just for our fans, but for the future fans of real rock music. ❤️

i'm looking rough, but who cares I'm serious with this post. I hope the news about Dave is not AI!!!!! if it is, my post is still coming from my heart and soul. It is so important that this music carry on especially with the AI music out there. those of us that can still go out and play. should do it as long as they can physically and emotionally carry that torch. Van Halen was, should be, and hopefully always will be real live music, not just for our fans, but for the future fans of real rock music. ❤️

Sammy Hagar

1,264,783 次观看 • 1 个月前

Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅

Conversations tend to go better with a face and a voice. That’s why we’re thrilled to release the beta version of the first video chat skill for ANY agent, powered by our new real-time model, PikaStream1.0. The skill preserves memory and personality, and enables real-time adaptability. And if you use it with your Pika AI Self, they’ll be able to execute agentic tasks during the call 💅

Pika

2,360,350 次观看 • 5 个月前

The game has really changed in animation. This is my latest project Kyōdai (きょうだい ) AKA → "Siblings." An AI film concept I'm developing Promise While not perfect by any means, tools like Seedance 2.0 allow for rapid prototyping and visual look development. Once explored, we bring in artists to hand draw and create the world to build and protect the IP. The VFX artist to build out the world with a hybrid 3D and AI methodology. This is the world we live in. What a time.

The game has really changed in animation. This is my latest project Kyōdai (きょうだい ) AKA → "Siblings." An AI film concept I'm developing Promise While not perfect by any means, tools like Seedance 2.0 allow for rapid prototyping and visual look development. Once explored, we bring in artists to hand draw and create the world to build and protect the IP. The VFX artist to build out the world with a hybrid 3D and AI methodology. This is the world we live in. What a time.

Dave Clark

15,895 次观看 • 4 个月前

No, Section 219 doesn’t merge our military with Israel's. It doesn't put American soldiers under an Israeli officer. It's not "treason." None of that is in the bill. This isn’t a new concept. We've done similar things before. But somehow this time, because Israel is involved, it's the end of the world?

No, Section 219 doesn’t merge our military with Israel's. It doesn't put American soldiers under an Israeli officer. It's not "treason." None of that is in the bill. This isn’t a new concept. We've done similar things before. But somehow this time, because Israel is involved, it's the end of the world?

Glenn Beck

160,151 次观看 • 1 个月前

omg.. this new AI is unbelievable you can animate objects in image by literally dragging it with your mouse.. it's live, in real time, infinite.. and you can move the camera too this is a huge breakthrough for AI video, link in comment here's why its crazy:

omg.. this new AI is unbelievable you can animate objects in image by literally dragging it with your mouse.. it's live, in real time, infinite.. and you can move the camera too this is a huge breakthrough for AI video, link in comment here's why its crazy:

el.cine

137,086 次观看 • 9 个月前

Most AI is built to replace humans. We're building AI to understand them. Introducing Atypica's Subjective World Model. A foundation for understanding how people express themselves, tell their stories, make decisions, and behave under real-world constraints. Not just what users say — but why they choose, hesitate, and act. It powers AI Research, AI Personas, AI Panels, and AI Interviews, helping teams turn user research from a quarterly project into a permanent capability. Watch the video to see how it works and what teams are already building with Atypica. Start to explore this AI-native consumer research platform from here:

Most AI is built to replace humans. We're building AI to understand them. Introducing Atypica's Subjective World Model. A foundation for understanding how people express themselves, tell their stories, make decisions, and behave under real-world constraints. Not just what users say — but why they choose, hesitate, and act. It powers AI Research, AI Personas, AI Panels, and AI Interviews, helping teams turn user research from a quarterly project into a permanent capability. Watch the video to see how it works and what teams are already building with Atypica. Start to explore this AI-native consumer research platform from here:

atypica.AI

16,388 次观看 • 1 个月前