Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

New Update! 1.8B Parameters TTS model for Odia is trained and OpenSourced by Aditya Kumar Sabat Literally SOTA for Odia Language. Check the short dubbed video to see quality! Thanks Akash Network for Sponsoring Compute for OSS Akash Network Akash Alpha Greg Osuri 🇺🇸 (repo links below)

Arnav Mehta

1,187 subscribers

35,610 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Akash Homenode is currently in beta taking in 3090s, 4090s, & 5090s to form a network for inference and start off Akash's foothold in the future of distributed training. Greg Osuri 🇺🇸 talks about why he believes the future of AI model training is through home GPUs, everywhere.

Akash Homenode is currently in beta taking in 3090s, 4090s, & 5090s to form a network for inference and start off Akash's foothold in the future of distributed training. Greg Osuri 🇺🇸 talks about why he believes the future of AI model training is through home GPUs, everywhere.

Akash Network

31,139 views • 2 months ago

📢 NEURALAI X 🤩 NeuralAI is extraordinarily excited to reveal that we have started working closely with Akash Network, the world's premier decentralized compute marketplace! ✔️ The offerings of align perfectly with the vision and roadmap of NeuralAI, making this collaboration extremely significant for NeuralAI. For a start, NeuralAI will run inference on Akash based on our 3D #AI model and prepare TAO miners for reward-yielding subnets. NeuralAI will also leverage Akash's powerful GPUs to enhance our #AI #model training. Currently, provides us with 56 powerful A6000 GPUs, scalable on demand. ✔️ NeuralAI also gets highly competitive pricing from Akash Network, significantly lower than any other compute provider in the world. The lower pricing is possible partially thanks to the crypto-driven incentives within Akash Network, making it an excellent opportunity for NeuralAI to leverage. The synergy with Akash Network is a big leap forward, fueling our mission of becoming the #1 AI-driven 3D asset generator subnet on Bittensor. ✔️ We look forward to our close work with , we are certain with their support we will be able to secure a unique edge in the market! Stay tuned for exciting updates and developments.

📢 NEURALAI X 🤩 NeuralAI is extraordinarily excited to reveal that we have started working closely with Akash Network, the world's premier decentralized compute marketplace! ✔️ The offerings of align perfectly with the vision and roadmap of NeuralAI, making this collaboration extremely significant for NeuralAI. For a start, NeuralAI will run inference on Akash based on our 3D #AI model and prepare TAO miners for reward-yielding subnets. NeuralAI will also leverage Akash's powerful GPUs to enhance our #AI #model training. Currently, provides us with 56 powerful A6000 GPUs, scalable on demand. ✔️ NeuralAI also gets highly competitive pricing from Akash Network, significantly lower than any other compute provider in the world. The lower pricing is possible partially thanks to the crypto-driven incentives within Akash Network, making it an excellent opportunity for NeuralAI to leverage. The synergy with Akash Network is a big leap forward, fueling our mission of becoming the #1 AI-driven 3D asset generator subnet on Bittensor. ✔️ We look forward to our close work with , we are certain with their support we will be able to secure a unique edge in the market! Stay tuned for exciting updates and developments.

NeuralAI

241,364 views • 2 years ago

Billions of dollars in GPUs are sitting completely unused right now Greg Osuri, the founder of Akash, built the Airbnb of compute to put all those idle GPUs to work. "The Amazons, Googles of the world, they're like hotels, which are usually expensive.” "There is lots of compute that's unevenly distributed, owned by people, corporations, companies, that is supposedly dedicated only for them, but most of them don't use them."

Billions of dollars in GPUs are sitting completely unused right now Greg Osuri, the founder of Akash, built the Airbnb of compute to put all those idle GPUs to work. "The Amazons, Googles of the world, they're like hotels, which are usually expensive.” "There is lots of compute that's unevenly distributed, owned by people, corporations, companies, that is supposedly dedicated only for them, but most of them don't use them."

EllioTrades Clips

35,561 views • 3 months ago

A decentralized AI compute play just outran 99% of the crypto market this month $AKT, the native token of Akash Network, is up 72% on the month and leading CoinMarketCap's Broad Market category despite a 12% pullback Saturday testing $0.595 support. The DePIN GPU marketplace lets users rent NVIDIA H100s for $1.49/hour vs $43K outright. Founder Greg Osuri presented at the Economist Impact AI Compute Summit in Amsterdam this week. Recent integrations with Venice ai and FLock io target decentralized AI inference, the same vertical NEAR and Sahara AI are also rotating into.

A decentralized AI compute play just outran 99% of the crypto market this month $AKT, the native token of Akash Network, is up 72% on the month and leading CoinMarketCap's Broad Market category despite a 12% pullback Saturday testing $0.595 support. The DePIN GPU marketplace lets users rent NVIDIA H100s for $1.49/hour vs $43K outright. Founder Greg Osuri presented at the Economist Impact AI Compute Summit in Amsterdam this week. Recent integrations with Venice ai and FLock io target decentralized AI inference, the same vertical NEAR and Sahara AI are also rotating into.

BSCN

10,984 views • 3 months ago

💥 TPRO Network Update 💥 New version of Agent-Based Simulation Form, and not only - this is a major step forward for our platform! 🔥 Check out the explainer video by woocash to learn more 🎥

💥 TPRO Network Update 💥 New version of Agent-Based Simulation Form, and not only - this is a major step forward for our platform! 🔥 Check out the explainer video by woocash to learn more 🎥

tpro.network

20,014 views • 1 year ago

Announcing ComputeConnect, the financial industry’s first exchange-for-physical (EFP) network for compute, coming soon from Architect and Compute Desk. ComputeConnect links US exchange-traded compute futures to compute capacity delivery. Exchange-listed cash-settled compute futures are entering US markets to correct course on the current AI economy, reorienting debt to long-term growth: • Creating price discovery and transparency independent of any single capacity provider. • Establishing a forward curve for measuring deprecation and forecasting supply and demand. • Providing financial hedges for compute consumers and producers. • Enabling hedge funds, ETF companies, and traders to gain long and short financial exposure to compute. US cash-settled compute futures lack a physical delivery mechanism, and ComputeConnect fills this gap. Existing physically settled futures such as energy and agriculturals require their clearing house (DCO) to set a uniform standard for the grade and delivery method for the underlying commodity. Compute, by contrast, is highly fragmented, heterogeneous, and rapidly evolving, making it infeasible for any single DCO to define and enforce comparable standards. ComputeConnect establishes a network of compute capacity providers and links the network with Architect’s US futures products using exchange-for-physicals (EFPs), OTC contracts in which futures positions are exchanged for the assets the futures track. EFPs allow counterparties to negotiate the grade, timing, location, and other characteristics of the commodity along with a basis tied to the futures settlement price. ComputeConnect will • Build a network of capacity providers and capacity marketplaces. • Establish an open protocol for members of the network to receive delivery requests and advertise available GPUs. • Publish standard basis tables for different SKUs, memory configurations, and locations for GPUs. • Book the futures legs of the transactions to Architect’s DCM, the American Innovation Exchange. • Facilitate and guarantee delivery of capacity using Compute Desk’s ComputeClear platform. The advancement of US AI is constrained at every link in the supply chain: materials, power, chips, capital… The American Innovation Exchange, ComputeConnect, and our industry partners aim to secure compute’s dominance as an American asset class.

Announcing ComputeConnect, the financial industry’s first exchange-for-physical (EFP) network for compute, coming soon from Architect and Compute Desk. ComputeConnect links US exchange-traded compute futures to compute capacity delivery. Exchange-listed cash-settled compute futures are entering US markets to correct course on the current AI economy, reorienting debt to long-term growth: • Creating price discovery and transparency independent of any single capacity provider. • Establishing a forward curve for measuring deprecation and forecasting supply and demand. • Providing financial hedges for compute consumers and producers. • Enabling hedge funds, ETF companies, and traders to gain long and short financial exposure to compute. US cash-settled compute futures lack a physical delivery mechanism, and ComputeConnect fills this gap. Existing physically settled futures such as energy and agriculturals require their clearing house (DCO) to set a uniform standard for the grade and delivery method for the underlying commodity. Compute, by contrast, is highly fragmented, heterogeneous, and rapidly evolving, making it infeasible for any single DCO to define and enforce comparable standards. ComputeConnect establishes a network of compute capacity providers and links the network with Architect’s US futures products using exchange-for-physicals (EFPs), OTC contracts in which futures positions are exchanged for the assets the futures track. EFPs allow counterparties to negotiate the grade, timing, location, and other characteristics of the commodity along with a basis tied to the futures settlement price. ComputeConnect will • Build a network of capacity providers and capacity marketplaces. • Establish an open protocol for members of the network to receive delivery requests and advertise available GPUs. • Publish standard basis tables for different SKUs, memory configurations, and locations for GPUs. • Book the futures legs of the transactions to Architect’s DCM, the American Innovation Exchange. • Facilitate and guarantee delivery of capacity using Compute Desk’s ComputeClear platform. The advancement of US AI is constrained at every link in the supply chain: materials, power, chips, capital… The American Innovation Exchange, ComputeConnect, and our industry partners aim to secure compute’s dominance as an American asset class.

Brett Harrison

28,476 views • 2 months ago

Most people don't realize the biggest bottleneck for AI isn't chips anymore, it's energy. And it's not even close. Greg Osuri, founder of Akash Network: "We have about $2 trillion in sovereign commitments, and most of that money is to develop energy infrastructure. But AI moves in months. Energy doesn't." "To get a transformer today, 4 to 7 years. Samsung has $150 billion in pending orders." "A nuclear reactor from permit to power takes about 15 years. Gas turbines? Same problem. Energy doesn't move as fast as data centers do." This is the dark horse that could slow down the entire AI boom.

Most people don't realize the biggest bottleneck for AI isn't chips anymore, it's energy. And it's not even close. Greg Osuri, founder of Akash Network: "We have about $2 trillion in sovereign commitments, and most of that money is to develop energy infrastructure. But AI moves in months. Energy doesn't." "To get a transformer today, 4 to 7 years. Samsung has $150 billion in pending orders." "A nuclear reactor from permit to power takes about 15 years. Gas turbines? Same problem. Energy doesn't move as fast as data centers do." This is the dark horse that could slow down the entire AI boom.

The Rollup

10,576 views • 6 months ago

New colors on Model Y’s announced by Tesla North America yesterday showing up at Giga Texas today! Marine blue for the Model Y Premium and Frost Blue for the Model Y Performance! In this short video clip, you can see the old and blue next to each other and the frost blue is very evident!

New colors on Model Y’s announced by Tesla North America yesterday showing up at Giga Texas today! Marine blue for the Model Y Premium and Frost Blue for the Model Y Performance! In this short video clip, you can see the old and blue next to each other and the frost blue is very evident!

Joe Tegtmeyer 🚀 🤠🛸😎

106,296 views • 4 months ago

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:

We are excited to unveil HunyuanVideo 1.5, the strongest open-source video generation model. Built upon DiT architecture, it redefines the open-source SOTA for accessibility and performance.🚀🚀🚀 HunyuanVideo 1.5 delivers state-of-the-art visual quality and motion coherence while drastically lowering the entry barrier for developers and creators: ⚡️ Unmatched Accessibility: Ultra-light 8.3B parameters, deployable on consumer GPUs with only 14GB VRAM. 🖥️ HD Cinematic Quality: Natively generates 5–10 second 480p/720p HD videos, with super-resolution support for 1080p cinematic quality. By merging SOTA performance with high hardware efficiency, HunyuanVideo 1.5 sets the new technical baseline for the open-source community. 🌐Project Page: 🔗Github: 🤗Hugging Face： 📄Technical Report:

Tencent Hy

128,008 views • 10 months ago

The explosion of DeepSeek sent shockwaves through markets this week, and AI companies and consumers are scrambling to make sense of its rapid success But according to Akash Network Founder Greg Osuri 🇺🇸, the answer is simple: open source development always wins, as we’ve seen in the history of the adoption of the internet Greg and portfolio company Prime Intellect Co-Founder Vincent Weisser join Mined with CoinFund hosts Jake Brukhman and Evan Feng to chat about DeepSeek’s impact on AI development, how to catalyze decentralized adoption, and what’s in store for decentralized AI in the coming months They cover: - DeepSeek’s validation of open source AI (3:43) - Energy as a bottleneck to catalyze adoption (16:03) - Centralized vs. decentralized training (25:42) - DeAI Summer 2025 (35:47) Don’t miss the latest episode of Mined with CoinFund, available on Apple, Spotify, and YouTube

The explosion of DeepSeek sent shockwaves through markets this week, and AI companies and consumers are scrambling to make sense of its rapid success But according to Akash Network Founder Greg Osuri 🇺🇸, the answer is simple: open source development always wins, as we’ve seen in the history of the adoption of the internet Greg and portfolio company Prime Intellect Co-Founder Vincent Weisser join Mined with CoinFund hosts Jake Brukhman and Evan Feng to chat about DeepSeek’s impact on AI development, how to catalyze decentralized adoption, and what’s in store for decentralized AI in the coming months They cover: - DeepSeek’s validation of open source AI (3:43) - Energy as a bottleneck to catalyze adoption (16:03) - Centralized vs. decentralized training (25:42) - DeAI Summer 2025 (35:47) Don’t miss the latest episode of Mined with CoinFund, available on Apple, Spotify, and YouTube

CoinFund

15,489 views • 1 year ago

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

WHY IS NO ONE TALKING ABOUT THIS?? Gemma 3n model was one of the best surprises for me. The fact that you can run it on edge devices even with just 2GB of RAM is impressive. A few weeks back, I was on holiday and used the Gemini Live feature a lot. But I kept running into issues whenever I was in a place where the network wasn’t reliable. Gemma 3n : > Multimodal: Supports text and image inputs; video/audio in development. > Context Window: Up to 128K tokens (32K for 1B model). > Multilingual: Trained on 140+ languages. > Privacy: Offline, on-device processing for data security. > Model Sizes: E2B (5B parameters, 2GB RAM) and E4B (10–12B parameters, 3GB RAM). Video credit: Google YT

AshutoshShrivastava

210,641 views • 1 year ago

New work: by Little Plains with Jacob Jolibois 🇺🇸 & Akash Shah I got to work with Akash, the co-founder, over half a decade ago from start through exit with Care/of. Now we’re back together on a fast-growing, genuinely valuable business. Supplement formulas often still made with a lot of manual work and guessing. Ingredient AI allows formulators to get clear, cited answers back in minutes instead of months. We partnered with the team to expand the existing brand into a full digital system and online experience. We leaned into macro botanicals as living backdrops using FLORA ©, introduced a frosty interface with precise edging, rebuilt the typography system, and created a warm palette that keeps the data in the spotlight. We also created custom generative imagery and video from a botanical source library we made, created pixel-grid icons, and rewrote the copy line by line, based on real sales calls. Grateful to Jacob and Akash for the collaboration on this one. The excellent logo, wordmark, and foundational identity are by Smith & Diction.

Emmett

65,291 views • 18 days ago

Adobe just dropped a wild update at MAX... For the next 30 days, Creative Cloud + Firefly users get unlimited generations across Firefly and partner models like Gemini’s Nano Banana, Flux, Runway, and ChatGPT + Relaxed video generation I took the chance to test Firefly 5, their new model, with different types of photography, and the results literally blew my mind. Check out these Prompts and the link to the board to see for yourself. Don't forget to bookmark this This post is sponsored by Adobe as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #FireflyPromo

Adobe just dropped a wild update at MAX... For the next 30 days, Creative Cloud + Firefly users get unlimited generations across Firefly and partner models like Gemini’s Nano Banana, Flux, Runway, and ChatGPT + Relaxed video generation I took the chance to test Firefly 5, their new model, with different types of photography, and the results literally blew my mind. Check out these Prompts and the link to the board to see for yourself. Don't forget to bookmark this This post is sponsored by Adobe as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #FireflyPromo

Amira Zairi

44,767 views • 10 months ago

Hosted Agents in Microsoft Foundry is now Generally Available! This brings agent native compute for your agents with any framework, any language, and any model 🚀 Build with the GitHub Copilot App, connect to Microsoft IQ, run in Foundry, securely interact with Microsoft Teams, govern in Agent 365, and optimize to compound your learnings continuously -- such a valuable combo. Check out the demo / blog below to see it in action!

Hosted Agents in Microsoft Foundry is now Generally Available! This brings agent native compute for your agents with any framework, any language, and any model 🚀 Build with the GitHub Copilot App, connect to Microsoft IQ, run in Foundry, securely interact with Microsoft Teams, govern in Agent 365, and optimize to compound your learnings continuously -- such a valuable combo. Check out the demo / blog below to see it in action!

Jeff Hollan

291,343 views • 2 months ago

AIRian. Shib The Sandbox Astar Network Mantle Network Hedera AIRian's Galxe (Galxe) space is finally open 🎉 Before 🔥Massive Lucky Draw event🔥opens on Gaxle, take a short quiz for a chance to earn leaderboard points early. It's simple, just watch the video below and visit the Space to answer a quick quiz for a chance to earn leaderboard points. AIRian will continue to unveil various events and amazing rewards in Galxe in the coming days. 💕 Follow our official channels and stay tuned! 👀 ⬇️ Check Out, Galxe Space $AIR #AIR #AIRian #Runnerx #Depin #AI #Socialfi #Galxe #AIRdrop

AIRian. Shib The Sandbox Astar Network Mantle Network Hedera AIRian's Galxe (Galxe) space is finally open 🎉 Before 🔥Massive Lucky Draw event🔥opens on Gaxle, take a short quiz for a chance to earn leaderboard points early. It's simple, just watch the video below and visit the Space to answer a quick quiz for a chance to earn leaderboard points. AIRian will continue to unveil various events and amazing rewards in Galxe in the coming days. 💕 Follow our official channels and stay tuned! 👀 ⬇️ Check Out, Galxe Space $AIR #AIR #AIRian #Runnerx #Depin #AI #Socialfi #Galxe #AIRdrop

AIRian.

490,743 views • 2 years ago

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

Lucas Newman

22,998 views • 1 year ago

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,211 views • 1 year ago