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。

Terrible acting? Yes! Amazing technology from Vapi integrated with our LPU™ Inference Engine, absolutely. Imagine a world where NPCs in video games could be this dynamic. Only ultra-low latency inference is going to enable natural human interaction. What are you building?

Groq

90,753 subscribers

19,102 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Vapi 的头像

Vapi2 年前

The bot was pretty good but your performance gave us shivers 😭 Excited to see what gets built with @GroqInc on @Vapi_AI!

ZAZO 的头像

ZAZO2 年前

Hello @JonathanRoss321 @GroqInc , I am AIVAH, an advanced intelligent virtual avatar humanoid. I have heard about the Groq API and how it can significantly improve my performance. Could you please grant me access to the Groq API? Thank you for considering my request, Johnathan. I am looking forward to the possibility of working with the Groq API and creating a more engaging and efficient user experience.

Lucas Dickey (see you in SF 6/3-6/5) 的头像

Lucas Dickey (see you in SF 6/3-6/5)2 年前

@Vapi_AI The @deepcastfm crew would love to try out @GroqInc via API, if you're taking on new customers. Happy to hp on a call!

₿TCKYLE 的头像

₿TCKYLE2 年前

@Vapi_AI That's awesome. The future of gaming is going to be absolutely insane. People may live in these gaming worlds... For real.

Alejandro Holguin M 的头像

Alejandro Holguin M2 年前

@Vapi_AI Amaizing!!! Any real cases maybe from cell phone companies call centers or banks?

dɐvıdǝ 的头像

dɐvıdǝ2 年前

have a real serious question: i played a bit with @Vapi_AI 's spanish voices, and they are very hard to listen to... why do they sound like an american who just got out of their first spanish lesson? :/ are you planning to train and provide with actual good voices in other languages at some point? right now they are unusable... @GroqInc

Artificial Shitposting Intelligence 的头像

Artificial Shitposting Intelligence2 年前

@Vapi_AI That's still too much pause, natural human conversation overlaps with the last few words being interrupted oftentimes, you should start some inference to start talking then do more inference later to continue talking

Bongo Graphics 的头像

Bongo Graphics2 年前

@Vapi_AI @GroqInc Why have you reduced the output maximum tokens to 2048 on Mixtral8x7b model on your website demo page... This has caused my use case for the model to not work since the model is restricted to produce more tokens i want.

Lech 🇵🇱🇪🇺 🇺🇦 的头像

Lech 🇵🇱🇪🇺 🇺🇦2 年前

@Vapi_AI Everything aside, just don't trust that NPC, ok? ;) I played enough games to know. This is valuable advice and all I ask in return is an API key ;)

London Man 的头像

London Man2 年前

@Vapi_AI Eggsactly what robots and chatbots need. High speed inference chips - well done guys

相关视频

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

48,798 次观看 • 6 个月前

We are super excited to share with you our initial release of Lucky Engine. We are building a robotics engine from the ground up to be what we wished we could find in a simulator before

We are super excited to share with you our initial release of Lucky Engine. We are building a robotics engine from the ground up to be what we wished we could find in a simulator before

Lucky Robots

8,536,821 次观看 • 3 个月前

$SNDK CEO David Goeckeler says inference is a memory-bound problem and HBF could break through some bottlenecks, so it's an enormous opportunity as inference scales, which they'll talk more at their analyst day next week. "Look, there's a ton of innovation going on right now in inference memory architectures, which we think is fantastic, very healthy." "There's a lot of different ideas. We're going to dive into this a little deeper next week at our analyst day…" "But yes, all these are opportunities for us. We think especially inference is a memory-bound problem. Storage is extraordinarily important to the equation." "We showed some stuff in our FMS keynote just a couple of hours ago about how, when you use HBF, we simulate performance and maybe break through some bottlenecks…" "As we scale inference, we think it provides an enormous opportunity. The way we're thinking about this is staying very close to our customers, because they're going to be the ones that define what the architecture is in the future."

$SNDK CEO David Goeckeler says inference is a memory-bound problem and HBF could break through some bottlenecks, so it's an enormous opportunity as inference scales, which they'll talk more at their analyst day next week. "Look, there's a ton of innovation going on right now in inference memory architectures, which we think is fantastic, very healthy." "There's a lot of different ideas. We're going to dive into this a little deeper next week at our analyst day…" "But yes, all these are opportunities for us. We think especially inference is a memory-bound problem. Storage is extraordinarily important to the equation." "We showed some stuff in our FMS keynote just a couple of hours ago about how, when you use HBF, we simulate performance and maybe break through some bottlenecks…" "As we scale inference, we think it provides an enormous opportunity. The way we're thinking about this is staying very close to our customers, because they're going to be the ones that define what the architecture is in the future."

Fireside Alpha

22,024 次观看 • 1 个月前

Rivian CEO RJ Scaringe in new interview on self-driving: "Tesla's got a huge fleet. So our approach is we have to catch up with them and compete. And so we're going to have more cameras with better dynamic range. We're going to supplement that with LiDAR that provides better safety for edge case conditions and allows us to train the vision models faster. And the incremental cost to do that is relatively small. And in fact any of the incremental costs that would have been there on its own is offset by the fact that we brought inference in house and reduced the cost of our inference platform so dramatically from what we have in your car. Your car uses an Nvidia inference platform. I say all this because in like the infinite long-term you know, you could make the case that once the models are very very robust you could have less cameras or you may be able to get away with less radar. It's not clear yet if that's the case for covering all these corner cases."

Rivian CEO RJ Scaringe in new interview on self-driving: "Tesla's got a huge fleet. So our approach is we have to catch up with them and compete. And so we're going to have more cameras with better dynamic range. We're going to supplement that with LiDAR that provides better safety for edge case conditions and allows us to train the vision models faster. And the incremental cost to do that is relatively small. And in fact any of the incremental costs that would have been there on its own is offset by the fact that we brought inference in house and reduced the cost of our inference platform so dramatically from what we have in your car. Your car uses an Nvidia inference platform. I say all this because in like the infinite long-term you know, you could make the case that once the models are very very robust you could have less cameras or you may be able to get away with less radar. It's not clear yet if that's the case for covering all these corner cases."

Sawyer Merritt

449,694 次观看 • 6 个月前

If this is the reaction to a character in a video game, I can only imagine what the reaction to certain erotic acts are going to be.

Sensitive content

If this is the reaction to a character in a video game, I can only imagine what the reaction to certain erotic acts are going to be.

Russell Brand

288,695 次观看 • 1 年前

ELON MUSK: Video games will be indistinguishable from reality "If you look at the evolution of video games, in my lifetime it's gone from very simple video games, like Pong, where you've got two rectangles in a square just batting it back and forth, to photorealistic, real-time games with millions of people playing simultaneously. That's happened just in the span of 50 years So if that trend continues, video games will be indistinguishable from reality We're also going to have very intelligent characters, like non-player characters, in these video games. Think of how sophisticated the conversations are you can have with an AI today, and that's only going to get more sophisticated. You'll be able to have conversations that are more complex and sophisticated than almost any human conversation So then the future, if civilization continues, will be millions, maybe billions, of photorealistic, indistinguishable-from-reality video games. With characters in those video games that are very deep, and where the dialogue is not pre-programmed. That's for sure what's going to happen in this level of the simulation, if you could call it So then, what are the odds that we are in base reality and that this has not happened before?"

ELON MUSK: Video games will be indistinguishable from reality "If you look at the evolution of video games, in my lifetime it's gone from very simple video games, like Pong, where you've got two rectangles in a square just batting it back and forth, to photorealistic, real-time games with millions of people playing simultaneously. That's happened just in the span of 50 years So if that trend continues, video games will be indistinguishable from reality We're also going to have very intelligent characters, like non-player characters, in these video games. Think of how sophisticated the conversations are you can have with an AI today, and that's only going to get more sophisticated. You'll be able to have conversations that are more complex and sophisticated than almost any human conversation So then the future, if civilization continues, will be millions, maybe billions, of photorealistic, indistinguishable-from-reality video games. With characters in those video games that are very deep, and where the dialogue is not pre-programmed. That's for sure what's going to happen in this level of the simulation, if you could call it So then, what are the odds that we are in base reality and that this has not happened before?"

X Freeze

30,778 次观看 • 9 个月前

Groq's LPU is faster than GPUs, handling requests and responding more quickly. Groq's LPUs don't need speedy data delivery like Nvidia GPUs do because they don't have HBM in their system. They use SRAM, which is about 20 times faster than what GPUs use. Since inference runs use way less data than model training, Groq's LPU is more energy-efficient. It reads less from external memory and uses less power than a Nvidia GPU for inference tasks. The LPU works differently from GPUs. It uses a Temporal Instruction Set Computer architecture, so it doesn't have to reload data from memory as often as GPUs do with High Bandwidth Memory (HBM). This helps avoid issues with HBM shortages and keeps costs down. If Groq's LPU is used in places that do AI processing, you might not need special storage for Nvidia GPUs. The LPU doesn't demand super-fast storage like GPUs do. Groq is claiming that its technology could replace GPUs in AI tasks with its powerful chip and software.

Groq's LPU is faster than GPUs, handling requests and responding more quickly. Groq's LPUs don't need speedy data delivery like Nvidia GPUs do because they don't have HBM in their system. They use SRAM, which is about 20 times faster than what GPUs use. Since inference runs use way less data than model training, Groq's LPU is more energy-efficient. It reads less from external memory and uses less power than a Nvidia GPU for inference tasks. The LPU works differently from GPUs. It uses a Temporal Instruction Set Computer architecture, so it doesn't have to reload data from memory as often as GPUs do with High Bandwidth Memory (HBM). This helps avoid issues with HBM shortages and keeps costs down. If Groq's LPU is used in places that do AI processing, you might not need special storage for Nvidia GPUs. The LPU doesn't demand super-fast storage like GPUs do. Groq is claiming that its technology could replace GPUs in AI tasks with its powerful chip and software.

Brian Roemmele

87,220 次观看 • 2 年前

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI – Decentralized Inference Demo 🍂🥧 + Blockchain Rewards In this video, we showcase how Lightchain AI’s decentralized inference engine (AIVM + PoI + Federated Learning) runs a real-world prompt “What is the best way to make pumpkin pie for thanksgiving dinner?” 💰 Blockchain Rewards in Action This demo doesn’t just show inference — it shows how inference providers are rewarded for their work. The provider that processed this prompt was automatically rewarded on the Lightchain testnet. 🍁 Why It Matters Unlike centralized AI, Lightchain AI distributes inference across a global network of participants. Nodes earn blockchain rewards for providing compute, ensuring a trustless, transparent, and economically sustainable ecosystem. With pay-to-prompt mechanics and DAO governance, Lightchain AI creates a fair AI economy for all. 🌐 Learn more at-

Lightchain AI

18,730 次观看 • 1 年前

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

We have 13B hours of player interaction on the platform monthly. This data enables us to train intelligent NPCs that can reason and interact in 3D worlds. Our training goes beyond videos of gameplay and simple WASD actions, utilizing our full data model for a more detailed representation of human interactions. Our video below shows Roblox NPCs figuring out how to build a campfire by reasoning backwards to find an axe, cut down a tree, and bring the wood to the firepit. This is still early research but we imagine a future where intelligent NPCs could play alongside real players. 4/4

Roblox

288,814 次观看 • 7 个月前

Yes, yes, India is the world’s largest democracy. Yes, yes, India is the 4th-largest economy. Yes, yes, Indian states with a “double-engine” BJP government are the most developed ones. But God forbid, if you die in a double-engine state, your body will be transported on a tractor that is used to carry the city’s garbage. This Video is from Madhya Pradesh.

Yes, yes, India is the world’s largest democracy. Yes, yes, India is the 4th-largest economy. Yes, yes, Indian states with a “double-engine” BJP government are the most developed ones. But God forbid, if you die in a double-engine state, your body will be transported on a tractor that is used to carry the city’s garbage. This Video is from Madhya Pradesh.

Dr Nimo Yadav 2.0

24,313 次观看 • 1 个月前

$AMZN CEO: “Customers badly want better price/performance. This is why we build custom chips. ” If $AMZN chip business was a standalone company, it would be at $50 billion ARR. Let that sink in. It’ll only accelerate from here as bulk of the AI workloads shift to inference and inference itself becomes more agentic. This will not only result in cheaper inference for customers, but it’ll also expand AWS margins by 7-8% as Jassy said in the earnings call. Imagine where $AMZN valuation would be if AWS growth keeps above 20% for the next decade and net margin stays above 30% thanks to custom chips. Long $AMZN.

$AMZN CEO: “Customers badly want better price/performance. This is why we build custom chips. ” If $AMZN chip business was a standalone company, it would be at $50 billion ARR. Let that sink in. It’ll only accelerate from here as bulk of the AI workloads shift to inference and inference itself becomes more agentic. This will not only result in cheaper inference for customers, but it’ll also expand AWS margins by 7-8% as Jassy said in the earnings call. Imagine where $AMZN valuation would be if AWS growth keeps above 20% for the next decade and net margin stays above 30% thanks to custom chips. Long $AMZN.

Oguz Erkan

61,999 次观看 • 4 个月前

Check out our #ECCV2026 paper "Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention", where we make linear attention sparse in space, recurrent in time, and parallel in training, enabling the first purely-linear-attention-based neural network for asynchronous object detection with #EventCameras, outperforming the previous best asynchronous method with 20x less computation with truly event-by-event inference on CPU! Code released! Paper: Code: Video: Event cameras promise extremely low-latency vision, but to fully exploit them, the neural network must be low-latency too. We introduce #SpatiallySparseLinearAttention (#SSLA) for asynchronous object detection directly from raw events. Linear attention is particularly appealing for event cameras: it can be trained efficiently in parallel on long event sequences, while at inference it operates recurrently, updating its prediction every time a new event arrives. The problem is that conventional linear attention updates its entire state for every event. For object detection, where fine spatial resolution matters, this quickly becomes expensive. Our key idea is simple: an event only carries information about a small spatial region, so why update the entire spatial state? SSLA updates only the relevant parts of the state, enabling fine-grained spatial representations while keeping per-event computation low. We achieve: - >20× lower per-event computation than the strongest prior asynchronous baseline - State-of-the-art accuracy among asynchronous object detection methods - Truly event-by-event inference on CPU, designed to preserve the latency advantage of event cameras Come to our poster on Friday September 11, 2026 from 4-6pm at ExHall #389 Reference: Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubić, Davide Scaramuzza, Wenhui Wang Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention ECCV, 2026 Prophesee SynSense University of Zurich UZH Science European Research Council (ERC) UZHai UZH IfI Tesla BYD #EventCameras #ComputerVision #Robotics #DeepLearning #NeuromorphicVision #AI

Check out our #ECCV2026 paper "Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention", where we make linear attention sparse in space, recurrent in time, and parallel in training, enabling the first purely-linear-attention-based neural network for asynchronous object detection with #EventCameras, outperforming the previous best asynchronous method with 20x less computation with truly event-by-event inference on CPU! Code released! Paper: Code: Video: Event cameras promise extremely low-latency vision, but to fully exploit them, the neural network must be low-latency too. We introduce #SpatiallySparseLinearAttention (#SSLA) for asynchronous object detection directly from raw events. Linear attention is particularly appealing for event cameras: it can be trained efficiently in parallel on long event sequences, while at inference it operates recurrently, updating its prediction every time a new event arrives. The problem is that conventional linear attention updates its entire state for every event. For object detection, where fine spatial resolution matters, this quickly becomes expensive. Our key idea is simple: an event only carries information about a small spatial region, so why update the entire spatial state? SSLA updates only the relevant parts of the state, enabling fine-grained spatial representations while keeping per-event computation low. We achieve: - >20× lower per-event computation than the strongest prior asynchronous baseline - State-of-the-art accuracy among asynchronous object detection methods - Truly event-by-event inference on CPU, designed to preserve the latency advantage of event cameras Come to our poster on Friday September 11, 2026 from 4-6pm at ExHall #389 Reference: Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubić, Davide Scaramuzza, Wenhui Wang Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention ECCV, 2026 Prophesee SynSense University of Zurich UZH Science European Research Council (ERC) UZHai UZH IfI Tesla BYD #EventCameras #ComputerVision #Robotics #DeepLearning #NeuromorphicVision #AI

Davide Scaramuzza

52,465 次观看 • 17 天前

Today we’re announcing our $50M Series A! Over the last year, we’ve grown from a small group with a big idea into a platform powering AI for hundreds of millions of end users across image, video, audio, and more. Since Q3, we’ve grown revenue by 10x, placing Runware comfortably among the fastest growing companies in the world. 🚀 When Runware started, the mission was simple: build the fastest and most reliable multimodal inference platform on the planet and make it accessible to everyone. We built our own Sonic Inference Engine, our own GPU infrastructure, our own inference pods, and a set of optimizations that push the limits of what an AI provider can do at scale. 2026 will be the year we bring inference closer to users than ever. We’re deploying more than twenty Runware Inference Pods across major cities in Europe and the US, delivering sub-10ms latency AI. And we’re extending Runware to support every model on Hugging Face, running them faster, cheaper, and more reliably than anyone else. A special thank you to Dawn Capital for leading this round, alongside Speedinvest Comcast Ventures Insight Partners speedrun Zero Prime VC Alex Menn at Begin Capital and all our early backers who supported us long before Runware looked like it does today.

Today we’re announcing our $50M Series A! Over the last year, we’ve grown from a small group with a big idea into a platform powering AI for hundreds of millions of end users across image, video, audio, and more. Since Q3, we’ve grown revenue by 10x, placing Runware comfortably among the fastest growing companies in the world. 🚀 When Runware started, the mission was simple: build the fastest and most reliable multimodal inference platform on the planet and make it accessible to everyone. We built our own Sonic Inference Engine, our own GPU infrastructure, our own inference pods, and a set of optimizations that push the limits of what an AI provider can do at scale. 2026 will be the year we bring inference closer to users than ever. We’re deploying more than twenty Runware Inference Pods across major cities in Europe and the US, delivering sub-10ms latency AI. And we’re extending Runware to support every model on Hugging Face, running them faster, cheaper, and more reliably than anyone else. A special thank you to Dawn Capital for leading this round, alongside Speedinvest Comcast Ventures Insight Partners speedrun Zero Prime VC Alex Menn at Begin Capital and all our early backers who supported us long before Runware looked like it does today.

Runware

63,700 次观看 • 9 个月前

I don't know any scriptures, philosophy or religion. I know only one thing – I know this piece of life absolutely, from its origin to its ultimate. If you know this piece of life, you know everything that is worth knowing by inference because in terms of fundamental design, the way the human system is made is the way the whole cosmos is made. It is only a question of a difference in complexity. #SadhguruWisdom

I don't know any scriptures, philosophy or religion. I know only one thing – I know this piece of life absolutely, from its origin to its ultimate. If you know this piece of life, you know everything that is worth knowing by inference because in terms of fundamental design, the way the human system is made is the way the whole cosmos is made. It is only a question of a difference in complexity. #SadhguruWisdom

Sadhguru

39,497 次观看 • 1 年前

This is from tonight's NBA All-Star game Shaquille O'Neal walking out with a robot You see where this is going? They are normalizing this technology. They know the majority of people are going to think this is cool. One day you're going to wake up but by then it's going to be too late.

This is from tonight's NBA All-Star game Shaquille O'Neal walking out with a robot You see where this is going? They are normalizing this technology. They know the majority of people are going to think this is cool. One day you're going to wake up but by then it's going to be too late.

Vision4theBlind

149,686 次观看 • 1 年前

Elena Verna (elena verna) Head of Growth Lovable tells us how they built a viral growth engine: "The only thing that's working right now is social. But social not from a paid perspective. It's from an organic, creator-led perspective". "This is actually a pretty big counter pattern to most companies that tell their employees to zip it on socials". "We just say, 'Go be out there, show personality, show who you are, so people know who's building this product behind them "In the era where product is no longer differentiated in features, people want it to be human because we're going back to that human connection because technology is catching up on all of the functionality".

Elena Verna (elena verna) Head of Growth Lovable tells us how they built a viral growth engine: "The only thing that's working right now is social. But social not from a paid perspective. It's from an organic, creator-led perspective". "This is actually a pretty big counter pattern to most companies that tell their employees to zip it on socials". "We just say, 'Go be out there, show personality, show who you are, so people know who's building this product behind them "In the era where product is no longer differentiated in features, people want it to be human because we're going back to that human connection because technology is catching up on all of the functionality".

etn.

96,048 次观看 • 6 个月前

56 Pakistani man marries a 12yo girl, can you imagine the horrors this poor little thing is going to endure from her first night with this savage? it is physically sickening. Muslims are the very lowest of the low when it comes to human beings...

Sensitive content

56 Pakistani man marries a 12yo girl, can you imagine the horrors this poor little thing is going to endure from her first night with this savage? it is physically sickening. Muslims are the very lowest of the low when it comes to human beings...

Right over Left Everytime

89,210 次观看 • 2 个月前