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.

🚨 BREAKING: Apple just acquired Meta's SAM team! On-device segmentation now ships natively in macOS 26.x This is what it looks like when you run SAM3 on MLX locally. Every car. Every fire. Real-time. M2 laptop. No cloud.

Maziyar PANAHI

16,809 subscribers

329,986 views • 4 months ago •via X (Twitter)

News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Wow! This is amazing! Segmented every car locally in real time with Meta's SAM3 converted to MLX. Just on-device (M2 laptop) vision getting absurdly good. Local AI is moving faster than most people realize! What other models should we test? what kind of videos?

Wow! This is amazing! Segmented every car locally in real time with Meta's SAM3 converted to MLX. Just on-device (M2 laptop) vision getting absurdly good. Local AI is moving faster than most people realize! What other models should we test? what kind of videos?

Maziyar PANAHI

177,188 views • 4 months ago

Gemma 4 just dropped. I had it captioning video in real-time within an hour. Running locally on a MacBook. No cloud. No API. Real-time scene understanding. Oh and SAM3 is segmenting every object in the same frame. Same laptop.

Gemma 4 just dropped. I had it captioning video in real-time within an hour. Running locally on a MacBook. No cloud. No API. Real-time scene understanding. Oh and SAM3 is segmenting every object in the same frame. Same laptop.

Maziyar PANAHI

196,846 views • 3 months ago

From parked cars to an Airbus A321 at cruising altitude. Same laptop. MLX & Torch. SAM3 segments every vehicle on the ground. Yes, just cars. RF-DETR spots the Austrian Airlines jet overhead. Real-time detection. Two open-source models running locally. No cloud. No API.

From parked cars to an Airbus A321 at cruising altitude. Same laptop. MLX & Torch. SAM3 segments every vehicle on the ground. Yes, just cars. RF-DETR spots the Austrian Airlines jet overhead. Real-time detection. Two open-source models running locally. No cloud. No API.

Maziyar PANAHI

46,612 views • 4 months ago

Jets. Helicopters. Wildfire. Traffic. Crowds. Falcon Perception. 0.6B parameters. "Find every person." It finds every person. "Find the fire." It finds the fire. +21.9 over SAM 3 on spatial understanding. Running locally via MLX. No cloud. What should I throw at it next?

Jets. Helicopters. Wildfire. Traffic. Crowds. Falcon Perception. 0.6B parameters. "Find every person." It finds every person. "Find the fire." It finds the fire. +21.9 over SAM 3 on spatial understanding. Running locally via MLX. No cloud. What should I throw at it next?

Maziyar PANAHI

18,191 views • 3 months ago

I showed you SAM 3 all week. This is a 0.6B model that outperforms it. Falcon Perception. Type "detect the plane" and it segments every plane in the frame. Pixel-accurate masks from natural language. Fighter jets. Fire. Crowds. All on a MacBook via MLX. No cloud.

I showed you SAM 3 all week. This is a 0.6B model that outperforms it. Falcon Perception. Type "detect the plane" and it segments every plane in the frame. Pixel-accurate masks from natural language. Fighter jets. Fire. Crowds. All on a MacBook via MLX. No cloud.

Maziyar PANAHI

63,029 views • 3 months ago

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Introducing MLX-Swift-TS An SDK for running time series foundation models fully on-device on Apple Silicon. When I joined Datadog, Inc. , I was introduced to Toto, our time series foundation model, and got excited about zero-shot forecasting across different domains. While building a health copilot app, I realized there wasn’t a simple way to run models like these locally on device. So I built one. MLX-Swift-TS exposes a common TimeSeriesForecaster interface for loading and running multiple time series architectures directly in Swift using MLX. No server required. The attached video shows on-device forecasting running inside a native Swift app. Huge thanks to Awni Hannun and the MLX team for building MLX and its Swift API, Prince Canuma for inspiration on MLX SDK patterns, and Ameet Talwalkar and the Datadog team for Toto.

Kunal Batra

12,585 views • 5 months ago

Just one rain and this is what Bangalore looks like! The so-called IT hub is now looking more like a water world. Despite a massive ₹19,930 Cr budget, the city sinks every time it rains—no planning, no proper infrastructure. When will this ever change? #Bangalore #Karnataka #bangluru

Just one rain and this is what Bangalore looks like! The so-called IT hub is now looking more like a water world. Despite a massive ₹19,930 Cr budget, the city sinks every time it rains—no planning, no proper infrastructure. When will this ever change? #Bangalore #Karnataka #bangluru

Suniel garg

52,744 views • 1 year ago

🚨 BREAKING BLACKROCK JUST WENT ALL-IN ON CRYPTO AHEAD OF TRUMP'S EMERGENCY ANNOUNCEMENT TODAY! THEY’RE NONSTOP BUYING MILLIONS OF BITCOIN AND ETHEREUM EVERY FEW MINUTES RIGHT NOW. LOOKS LIKE THEY KNOW THE BULL RUN HAS OFFICIALLY STARTED 👀

🚨 BREAKING BLACKROCK JUST WENT ALL-IN ON CRYPTO AHEAD OF TRUMP'S EMERGENCY ANNOUNCEMENT TODAY! THEY’RE NONSTOP BUYING MILLIONS OF BITCOIN AND ETHEREUM EVERY FEW MINUTES RIGHT NOW. LOOKS LIKE THEY KNOW THE BULL RUN HAS OFFICIALLY STARTED 👀

0xNobler

74,498 views • 2 months ago

Nobody announces it They don't post about it on their story. They just quietly open their laptop, follow a system, and watch YouTube deposit dollars into their account every month. That's what faceless YouTube looks like in real life. Start your quiet $2k YT channel today.

Nobody announces it They don't post about it on their story. They just quietly open their laptop, follow a system, and watch YouTube deposit dollars into their account every month. That's what faceless YouTube looks like in real life. Start your quiet $2k YT channel today.

Bright Afeno | Fenoxx

3,701,661 views • 3 months ago

Nvidia just put a $250,000 cloud workload on your desk for $2,999 - and killed your $1,900/month AWS bill in the process You don't rent it, you don't manage it, you don't pay a single cloud bill - you just plug it in and let it eat the workloads you used to wire to AWS every month It looks like a small Mac mini, it's actually a full GB10 Grace Blackwell stack with 128GB of unified memory running models up to 200B parameters It's called DGX Spark, the consumer version of the rack Nvidia ships to OpenAI The reason Nvidia did this is simple Cloud GPU pricing is a tax on every developer building AI right now $1,900/month per seat, billions in margin flowing to AWS, Lambda, and CoreWeave Nvidia just cut themselves in by removing the cloud entirely Their solution is to skip the middleman, ship the rack to your desk, and let you keep every dollar of margin you used to wire to a hyperscaler This is much cheaper, faster, and you own the asset at the end But there is still a question nobody is answering yet, what happens to AWS, GCP, and Lambda when 500,000 developers move their inference back to a $2,999 box on their desk Also, technically you can stack four of these and run a 1.6 trillion parameter model locally for under $12,000 Even a single Spark out-performs the cloud subscription Anthropic engineers were running two years ago bookmark this, it pays back in 60 days 👇

Nvidia just put a $250,000 cloud workload on your desk for $2,999 - and killed your $1,900/month AWS bill in the process You don't rent it, you don't manage it, you don't pay a single cloud bill - you just plug it in and let it eat the workloads you used to wire to AWS every month It looks like a small Mac mini, it's actually a full GB10 Grace Blackwell stack with 128GB of unified memory running models up to 200B parameters It's called DGX Spark, the consumer version of the rack Nvidia ships to OpenAI The reason Nvidia did this is simple Cloud GPU pricing is a tax on every developer building AI right now $1,900/month per seat, billions in margin flowing to AWS, Lambda, and CoreWeave Nvidia just cut themselves in by removing the cloud entirely Their solution is to skip the middleman, ship the rack to your desk, and let you keep every dollar of margin you used to wire to a hyperscaler This is much cheaper, faster, and you own the asset at the end But there is still a question nobody is answering yet, what happens to AWS, GCP, and Lambda when 500,000 developers move their inference back to a $2,999 box on their desk Also, technically you can stack four of these and run a 1.6 trillion parameter model locally for under $12,000 Even a single Spark out-performs the cloud subscription Anthropic engineers were running two years ago bookmark this, it pays back in 60 days 👇

ZEUS⚡️

85,803 views • 2 months ago

Cancelled ChatGPT -> Built JARVIS -> Pays $0 -> it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.

Cancelled ChatGPT -> Built JARVIS -> Pays $0 -> it works offline + it's smarter than the $20/month version. No WiFi needed, no cloud, no API keys, no rate limits, no queues, no $20/month just to ask a server in Virginia for the weather. Just a local model running directly on the laptop hardware, voice activated, system integrated, controlling apps, answering questions, doing the work. Iron Man had JARVIS embedded in his suit, this guy has it embedded in his MacBook and it works on a plane, in a basement, on a remote cabin with zero signal. OpenAI is burning $700,000 a day on infrastructure to deliver something this guy runs for free. Anthropic charges $200/month for unlimited Claude access, microsoft built Copilot into every product they sell. This guy skipped all of it, downloaded a model and made his laptop the smartest device in the room. No subscription. No login. No internet. No data sent anywhere ever. The most powerful AI assistant on earth is now the one running locally on hardware you already own. ChatGPT charges you to think slower, he pays nothing and thinks alone, he made it himself.

Defileo🔮

154,009 views • 3 months ago

🚨 CARNEY TURNS ON TRUMP — AND GETS APPLAUSE “The days of sending 70 cents of every defence dollar to the United States are over.” That’s not just policy. That’s a break. America’s closest ally— stepping back… while tensions rise. And the crowd? Cheering it on. This is what betrayal looks like: Turning away when it matters most. Because at a time like this— You don’t distance yourself from your allies. You stand with them. Instead— Carney just drew a line.

🚨 CARNEY TURNS ON TRUMP — AND GETS APPLAUSE “The days of sending 70 cents of every defence dollar to the United States are over.” That’s not just policy. That’s a break. America’s closest ally— stepping back… while tensions rise. And the crowd? Cheering it on. This is what betrayal looks like: Turning away when it matters most. Because at a time like this— You don’t distance yourself from your allies. You stand with them. Instead— Carney just drew a line.

Jim Ferguson

109,170 views • 3 months ago

"You feel like your swag coming back every single time one hits?" LaMelo Ball: "Oh no, I always got that. Even when I wake up I just feel great for real. I don't know what it is." Melo's confidence is unmatched 😅

"You feel like your swag coming back every single time one hits?" LaMelo Ball: "Oh no, I always got that. Even when I wake up I just feel great for real. I don't know what it is." Melo's confidence is unmatched 😅

ClutchPoints

671,909 views • 1 year ago

🚨 BREAKING: you can now turn your laptop into a CIA command center World Monitor is the ultimate real-time dashboard for global events—conflicts, earthquakes, traffic infra, flights and more. Updates live on your screen. • Tracks 100+ data sources instantly • Customisable for every screen size • 100% Open-source & free to use link in comment

🚨 BREAKING: you can now turn your laptop into a CIA command center World Monitor is the ultimate real-time dashboard for global events—conflicts, earthquakes, traffic infra, flights and more. Updates live on your screen. • Tracks 100+ data sources instantly • Customisable for every screen size • 100% Open-source & free to use link in comment

Farhan

172,812 views • 4 months ago

🤔 Imagine if your backend worked like `useState`. No API calls. No fetching. Just reactive, real-time state that syncs across devices. That’s what InstantDB is doing. With Instant your frontend gets a real-time database. You write queries that stay in sync and work offline. Every save updates immediately, and it comes with built-in auth and permissions. See how InstantDB looks in action in this deeply technical blog post from Stopa ↓

🤔 Imagine if your backend worked like `useState`. No API calls. No fetching. Just reactive, real-time state that syncs across devices. That’s what InstantDB is doing. With Instant your frontend gets a real-time database. You write queries that stay in sync and work offline. Every save updates immediately, and it comes with built-in auth and permissions. See how InstantDB looks in action in this deeply technical blog post from Stopa ↓

Expo

53,481 views • 1 year ago

🚨 NOW: Trump and Japan’s PM Sanae Takaichi just sat down for dinner at the White House and you can see the vibe instantly Trump in full control, hosting like always, and she’s clearly enjoying every second of it This isn’t just dinner, this is what a strong alliance actually looks like These two are locked in 🇺🇸🇯🇵

🚨 NOW: Trump and Japan’s PM Sanae Takaichi just sat down for dinner at the White House and you can see the vibe instantly Trump in full control, hosting like always, and she’s clearly enjoying every second of it This isn’t just dinner, this is what a strong alliance actually looks like These two are locked in 🇺🇸🇯🇵

ⁿᵉʷˢ Barron Trump 🇺🇸

36,909 views • 4 months ago

Our open-source RAG app, Verba, can now run Ollama models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little Verba-ception, asking Verba what Verba is 🤤 You can also use open-source models like Mistral, Claude, or your own custom LLMs. This will make doing RAG with sensitive data possible since you won't depend on APIs anymore. Looking forward to everyone trying it out 🤗 Update's coming next week!

Our open-source RAG app, Verba, can now run Ollama models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little Verba-ception, asking Verba what Verba is 🤤 You can also use open-source models like Mistral, Claude, or your own custom LLMs. This will make doing RAG with sensitive data possible since you won't depend on APIs anymore. Looking forward to everyone trying it out 🤗 Update's coming next week!

Edward

125,565 views • 2 years ago

No bc Ana Kasparian that is WHY I can’t fucking stand Batya Ungar-Sargon. She literally lies like that ALL THE TIME. Am I losing my mind??? Every single day on X, on her show, when she guest hosts, she just straight up LIES! And the most maddening part is that she’s never corrected or called out in real time.

No bc Ana Kasparian that is WHY I can’t fucking stand Batya Ungar-Sargon. She literally lies like that ALL THE TIME. Am I losing my mind??? Every single day on X, on her show, when she guest hosts, she just straight up LIES! And the most maddening part is that she’s never corrected or called out in real time.

B L A K E L E Y™℠©® LLC

150,281 views • 8 months ago

This is what trading looks like now. No order forms. No tabs. You just tell your agent what you want and it handles the rest. The whole thing took 18 seconds. Creating your own agent takes under a minute. ATLAS is live on Forkast today! 🚀

This is what trading looks like now. No order forms. No tabs. You just tell your agent what you want and it handles the rest. The whole thing took 18 seconds. Creating your own agent takes under a minute. ATLAS is live on Forkast today! 🚀

FORKAST

75,004 views • 9 days ago

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

🚨 NVIDIA just flipped the entire AI game… and this is NOT about gaming. DeepSeek-V4-Pro is now live on their build platform. 1.6 TRILLION parameters. Yes… the largest open-source model on the planet right now. And here’s the crazy part: They’re letting you run it FREE On Blackwell GPUs in the cloud. This is the same level of hardware companies like Google, Meta, and Microsoft fight billions to access. Now it’s just… available. No waitlist. No insane setup. Just raw power. We’re watching the shift happen in real time: → From closed AI → open domination → From GPU scarcity → free access → From Big Tech control → builders winning This isn’t an update. It’s a warning shot. Who’s already testing this? Link👇

divyansh tiwari

29,941 views • 3 months ago