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 iteration on Parallel Timelines (working title). FLUX.2-Klein 4B now runs at a satisfactory real-time speed, balancing performance and visual quality. Hand tracking controls the split, letting me define where the transformed output appears; a more gestural and playful approach than the previous eye-tracked version. #ai #realtime #realtimeai #StableDiffusion

Hugues Bruyère

8,081 subscribers

20,818 views • 5 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

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.

New AI research from Meta – CoTracker3 Simpler and Better Point Tracking by Pseudo-Labelling Real Videos. More details ➡️ Demo on Hugging Face ➡️ Building on our previous work on CoTracker, this new model demonstrates impressive tracking results where points can be tracked for a long time even when they're occluded or leave the field of view. CoTracker3 achieves state-of-the-art, outperforming all recent point tracking approaches on standard benchmarks — often by a substantial margin. We've released the research paper, code and a demo on Hugging Face — along with models available under an A-NC license to support further research in this space.

AI at Meta

219,026 views • 1 year ago

Interestingly, as we have AI agents that run in the background, the speed of AI becomes incrementally less important than the core underlying capability level. When you could only give AI small bits of work, then the speed of response mattered a ton. The rate at which you can go back and forth with AI in real-time was the determining factor on how useful it is. But as AI agents can perform more complex and useful tasks in parallel behind the scenes, you can much more easily afford to wait longer for work to get done assuming it’s valuable. Now the focus becomes more on how you review and orchestrate the agents’ work. And the main factor is just how useful and usable is the output that the agent came back with.

Interestingly, as we have AI agents that run in the background, the speed of AI becomes incrementally less important than the core underlying capability level. When you could only give AI small bits of work, then the speed of response mattered a ton. The rate at which you can go back and forth with AI in real-time was the determining factor on how useful it is. But as AI agents can perform more complex and useful tasks in parallel behind the scenes, you can much more easily afford to wait longer for work to get done assuming it’s valuable. Now the focus becomes more on how you review and orchestrate the agents’ work. And the main factor is just how useful and usable is the output that the agent came back with.

Aaron Levie

103,811 views • 11 months ago

The latest update from NemoVideo sets a new benchmark for AI-powered video creation. With NemoVideo now integrated with Seedance 2, the workflow is seamless—structured scripting, refined visual generation, and production-ready output within minutes. A meaningful advancement for creators focused on efficiency and quality. Explore it here: #NemoVideo #Seedance2

The latest update from NemoVideo sets a new benchmark for AI-powered video creation. With NemoVideo now integrated with Seedance 2, the workflow is seamless—structured scripting, refined visual generation, and production-ready output within minutes. A meaningful advancement for creators focused on efficiency and quality. Explore it here: #NemoVideo #Seedance2

Aryan Rakib

250,353 views • 6 months ago

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

THIS IS HOW A SENIOR ENGINEER ACTUALLY SCALES THEMSELVES WITH CLAUDE CODE the biggest change with AI isn't coding faster. it's where you actually spend your time now. more detailed prompts, more code review, more planning, less typing, etc. here's the workflow: this guy has been shipping code since the days of cgi and perl. he uses a compound engineering plugin that runs 5 separate agents on every task. one brainstorms, one plans the technical implementation, one executes, one reviews, one checks different verticals. every step is documented in markdown files. it's slow and way more waiting. but the output quality is way higher because each agent is focused on one thing. then the REAL multiplier is in git worktrees if Claude Code made you 10x faster, worktrees multiplies that again depending on how many agents you can manage in parallel his team runs 4-8 Claude Code sessions at the same time across different worktrees with each one working on a separate task. the skill is managing multiple AI agents in parallel without losing track, that's the next evolution of engineering

Om Patel

159,514 views • 4 months ago

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs

Taking talking shop to a whole new level. We just shipped Glean’s real-time voice capability, powered by OpenAI’s newest speech model GPT-Realtime-2. Grounded in the context across your org, it feels like a real AI coworker and can keep up with how work gets finished. In internal evals, GPT-Realtime-2 delivered a 42.9% relative increase in helpfulness over its previous version. Give it a try. It speaks for itself. OpenAIDevs

Glean

16,588 views • 3 months ago

METAL EDEN LAUNCHES SEPTEMBER 2 Along with the release, we will update the PC, PS5, and Xbox demos. We’ve introduced numerous improvements enhancing the game’s performance and stability. Visual quality and overall player experience have been significantly improved. On PC, performance has increased by at minimum 30%. On PS5 and Xbox Series X, the game now runs at a stable 60fps in Performance Mode. We’ve also refined mouse settings, controller support, and the interface. Video by 𝗩𝗢𝗬𝗔𝗚𝗘𝗥𝗦 𝗥𝗘𝗩𝗘𝗡𝗚𝗘 Music by @wiolation_ & Sascha Dikiciyan

METAL EDEN LAUNCHES SEPTEMBER 2 Along with the release, we will update the PC, PS5, and Xbox demos. We’ve introduced numerous improvements enhancing the game’s performance and stability. Visual quality and overall player experience have been significantly improved. On PC, performance has increased by at minimum 30%. On PS5 and Xbox Series X, the game now runs at a stable 60fps in Performance Mode. We’ve also refined mouse settings, controller support, and the interface. Video by 𝗩𝗢𝗬𝗔𝗚𝗘𝗥𝗦 𝗥𝗘𝗩𝗘𝗡𝗚𝗘 Music by @wiolation_ & Sascha Dikiciyan

REIKON | RUINER 2

35,968 views • 1 year ago

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

38,606 views • 1 year ago

GraphAI × Fetch.ai - ASI-1 Integration Demo Akhil Verghese, our Head AI Scientist, walks through how Fetch.ai 's ASI-1 LLM now runs natively inside GraphEngine, answering real on-chain analysis queries in natural language; from wallet tracking to token flow interpretation. This demo is more than a feature showcase, it’s the first visible milestone in the GraphAI × Fetch.ai collaboration, illustrating how ASI-1 and GraphEngine together can power agentic systems that understand, reason over, and act on decentralised finance in real time. A first glimpse at an AI-driven, on-chain future where intelligence and decentralised execution converge. Watch the demo.

GraphAI × Fetch.ai - ASI-1 Integration Demo Akhil Verghese, our Head AI Scientist, walks through how Fetch.ai 's ASI-1 LLM now runs natively inside GraphEngine, answering real on-chain analysis queries in natural language; from wallet tracking to token flow interpretation. This demo is more than a feature showcase, it’s the first visible milestone in the GraphAI × Fetch.ai collaboration, illustrating how ASI-1 and GraphEngine together can power agentic systems that understand, reason over, and act on decentralised finance in real time. A first glimpse at an AI-driven, on-chain future where intelligence and decentralised execution converge. Watch the demo.

GraphAI

29,810 views • 8 months ago

CHAMATH: FSD CAN ELIMINATE ALL UNNECESSARY ROAD DEATHS “Elon has an AI brain inside the Tesla, and the ability to drive safely on the highway became 7.5 times better than his previous version. And his previous version was already ten times better than a normal car. Which means when you get on the highway and engage FSD, it was already ten times better, now it's seven times better than that ten times. The idea about using AI now to just eliminate all the unnecessary deaths that happen because of traffic mishaps, there's the potential where that goes to zero. His issue isn't technological. His issue is going to be regulatory. At what speed will people be able to be comfortable letting him take people from point A to point B?” Source: Tucker Carlson Show, January 23, 2025

CHAMATH: FSD CAN ELIMINATE ALL UNNECESSARY ROAD DEATHS “Elon has an AI brain inside the Tesla, and the ability to drive safely on the highway became 7.5 times better than his previous version. And his previous version was already ten times better than a normal car. Which means when you get on the highway and engage FSD, it was already ten times better, now it's seven times better than that ten times. The idea about using AI now to just eliminate all the unnecessary deaths that happen because of traffic mishaps, there's the potential where that goes to zero. His issue isn't technological. His issue is going to be regulatory. At what speed will people be able to be comfortable letting him take people from point A to point B?” Source: Tucker Carlson Show, January 23, 2025

Mario Nawfal

1,565,980 views • 1 year ago

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

This is crazy, I can talk to OpenAI's realtime API, and it'll respond back with voice, and then help call Codex to help me code! Got curious about Codex and its realtime integration, and found codex's feature flag `realtime_conversation` integrated for the codex app-server. How it works: - launch codex app-server with realtime - connect a client to realtime through WebRTC voice connection - Codex app-server is also attached on the side - talk to realtime - realtime decides whether coding is needed, and responds back with events - Codex app-server takes these events and runs codex agent turns - codex writes code like your codex cli exp Keep in mind OpenAI hasn't released this officially, they're still actively working on it, I just created a fork. This is a completely new UX than the usual chat interface for agentic coding. For example, when the agent responds back in voice, it's actually faster for me to read the response, and I don't actually find voice response that useful unless it does so in the background. But image realtime working in the background, you can talk to it, realtime keeps track of the different agents working on your tasks and your status. More to come on demo side, i'll make a more polished version and include voice, but thought this was cool to share. You can see in the responses the distinction between my voice input, realtime response, and realtime calling Codex to do work!

Matthew Lam

17,674 views • 3 months ago

Quick Play Hacked is back for a limited time with the new 6v6 Dynamic Queue 👾 Experiment with better match quality and queue times by shifting between traditional 2-2-2 Role Queue and more flexible team compositions based on real-time player demand. Jump in now through Aug 2.

Quick Play Hacked is back for a limited time with the new 6v6 Dynamic Queue 👾 Experiment with better match quality and queue times by shifting between traditional 2-2-2 Role Queue and more flexible team compositions based on real-time player demand. Jump in now through Aug 2.

Overwatch

240,433 views • 23 days ago

Metroid Prime, running native and stable on iPhone and iPad for the first time. No emulator. No streaming from a Mac. This is EctoPad. Built on Metaforce, the native Metroid Prime engine developed by AxioDL and its contributors, it plays great on both devices and runs at full speed on iPhone 14 and newer. Touch controls, controller support, and 4x internal res. I am still working through a visual issue that causes some textures and lighting to render inaccurately, along with a smaller problem affecting the first tutorial door. Sol 5.6 was used to make this possible. Open sourcing it below.

Metroid Prime, running native and stable on iPhone and iPad for the first time. No emulator. No streaming from a Mac. This is EctoPad. Built on Metaforce, the native Metroid Prime engine developed by AxioDL and its contributors, it plays great on both devices and runs at full speed on iPhone 14 and newer. Touch controls, controller support, and 4x internal res. I am still working through a visual issue that causes some textures and lighting to render inaccurately, along with a smaller problem affecting the first tutorial door. Sol 5.6 was used to make this possible. Open sourcing it below.

Kahris

446,604 views • 5 days ago

GROK 4.1 THE BIGGEST LEAP IN AI HISTORY xAI’s Grok 4.1 isn’t just faster, it’s transformative. Trained on the Colossus supercluster with more than 200,000 GPUs, each version now uses up to ten times more compute than before. Real-time X data and reinforcement learning have refined Grok’s empathy, coherence, and human-like nuance. Hallucinations are down to a third, emotional replies feel authentic, and its creative output is wildly engaging. For the first time, Grok’s most advanced model is free to everyone. Source: Grok, 36KR

GROK 4.1 THE BIGGEST LEAP IN AI HISTORY xAI’s Grok 4.1 isn’t just faster, it’s transformative. Trained on the Colossus supercluster with more than 200,000 GPUs, each version now uses up to ten times more compute than before. Real-time X data and reinforcement learning have refined Grok’s empathy, coherence, and human-like nuance. Hallucinations are down to a third, emotional replies feel authentic, and its creative output is wildly engaging. For the first time, Grok’s most advanced model is free to everyone. Source: Grok, 36KR

Mario Nawfal

128,304 views • 9 months ago

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

THIS GUY BUILT REAL FLYING SWORD DRONES AND CONTROLS THEM WITH HAND GESTURES fan shisan is a physics student in chengdu who coded and built flying drones shaped like actual swords he controls them entirely with hand gestures. no controller or a phone. just his hands wave your hand and the sword follows. point and it flies where you direct it. multiple swords in the air at the same time responding to different gestures he built the gesture recognition system HIMSELF and coded the flight control algorithms. designed the drone hardware in the shape of swords. the gesture tracking uses sensors that read the position and movement of his hands in real time and translate them into flight commands for each drone independently he even built one large enough to ride on a physics student with coding skills just brought something straight out of a kung fu movie into the real world the line between science fiction and side projects is getting thinner every month

Om Patel

307,609 views • 3 months ago

The vision behind $HABE is no longer a theory. It’s real. It’s active. And now, you can see it for yourself. The HABEVERSE is more than a platform. It’s a system built to move ideas into the real world, and it runs on four powerhouse zones: The HABE Innovation Zone: where raw ideas are shaped into structured proposals using HABEAI and a proven process that goes from seed to launch. The HABE Voting Zone: Where your vote helps decide what gets built, and every action earns $HABE. The HABE Marketplace: A new way to invest. Back real products, grow with innovation, and build a portfolio that reflects what you believe in. The HABE Profile Zone: Your personal dashboard. Everything you do is tracked and managed in one place. This prototype is just the first glimpse of what’s coming, and what’s already working. 👉 Check out the prototype on Figma: Start where it still counts: Final hour before the price shifts.

HABE

14,864 views • 1 year ago

My entry for Runway's #aiff2025 is an upgraded version of a short I released a few months back. This is a visual poem generated 100% with ai tools and human creativity. I've been working on a new cinematic universe with original IP, this is the first one out the gate, much more to come. ✨S T A R L I G H T ✨ ✔️ Real actors for voice over and dialogue ✔️ Performance capture with Runway Act-One ✔️ Crazy new shots from Higgsfield AI 🧩

My entry for Runway's #aiff2025 is an upgraded version of a short I released a few months back. This is a visual poem generated 100% with ai tools and human creativity. I've been working on a new cinematic universe with original IP, this is the first one out the gate, much more to come. ✨S T A R L I G H T ✨ ✔️ Real actors for voice over and dialogue ✔️ Performance capture with Runway Act-One ✔️ Crazy new shots from Higgsfield AI 🧩

GenMagnetic

71,698 views • 1 year ago

We've tested the Qwen 3.8 Max preview and it absolutely rocks! Each scene is built in one shot, a single Three.js file with nothing else added: • Odysseus' war galley riding the waves • Trojan horse • Greek war helmet Qwen managed to execute the task faster than the other models, while output quality is relatively the same across all of them. If the pricing stays close to Alibaba's previous flagships, we'll get one of the best speed/quality ratios on the market — perfect for running agents at scale. Soon live on AI/ML API.

We've tested the Qwen 3.8 Max preview and it absolutely rocks! Each scene is built in one shot, a single Three.js file with nothing else added: • Odysseus' war galley riding the waves • Trojan horse • Greek war helmet Qwen managed to execute the task faster than the other models, while output quality is relatively the same across all of them. If the pricing stays close to Alibaba's previous flagships, we'll get one of the best speed/quality ratios on the market — perfect for running agents at scale. Soon live on AI/ML API.

AI/ML API

132,425 views • 1 month ago

Simulation-first approach to robotic production lines! 👾 At Hannover Messe, Amazon Web Services (AWS) and SoftServe are demonstrating a fully autonomous, AI-powered manufacturing workflow. Design a product using generative AI, then watch it move through the entire process: engraving, inspection, and delivery, handled by a mix of robots working together powered by physical AI on AWS. The interesting part is how the system is built. Getting robots into production is usually where things fall apart. SoftServe takes a simulation-first approach using AWS. They build and test the entire system virtually: robot behavior, production flow, before deploying anything physically. This enables faster iteration, safe edge case testing, and significantly reduced sim-to-real gap. Their demo includes AMRs handling transport, cobots doing precise manipulation, AI-driven quality inspection, and humanoid interaction at the end. All connected through a unified, software-defined layer powered by AWS. It's about building a system where robots can adapt, coordinate, and scale without rebuilding everything from scratch every time. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Simulation-first approach to robotic production lines! 👾 At Hannover Messe, Amazon Web Services (AWS) and SoftServe are demonstrating a fully autonomous, AI-powered manufacturing workflow. Design a product using generative AI, then watch it move through the entire process: engraving, inspection, and delivery, handled by a mix of robots working together powered by physical AI on AWS. The interesting part is how the system is built. Getting robots into production is usually where things fall apart. SoftServe takes a simulation-first approach using AWS. They build and test the entire system virtually: robot behavior, production flow, before deploying anything physically. This enables faster iteration, safe edge case testing, and significantly reduced sim-to-real gap. Their demo includes AMRs handling transport, cobots doing precise manipulation, AI-driven quality inspection, and humanoid interaction at the end. All connected through a unified, software-defined layer powered by AWS. It's about building a system where robots can adapt, coordinate, and scale without rebuilding everything from scratch every time. ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

17,709 views • 4 months ago

A 27B parameter model used to need a server room. Now it runs on: • iPhone • Android • Mac PrismML's Bonsai makes it possible. • 1-bit weights • 27B params in just 3.9GB • ~90% of full precision quality (PrismML evals) • Better than the 2-bit version at less than half the size The entire Bonsai family is now live in RunAnywhere. • 1.7B to 27B models • 1-bit + 2-bit ternary • Thinking mode On iOS and Mac, Bonsai runs through ggml's llama.cpp and Apple's MLX. On Android, Bonsai runs through ggml's llama.cpp and directly on the Qualcomm Hexagon NPU through QHexRT, our proprietary inference runtime. We built custom silicon kernels to make 1-bit inference on an NPU possible for the first time. Two years ago this needed a data center. Now it thinks in airplane mode. Now available in the RunAnywhere app on the App Store and Google Play.

A 27B parameter model used to need a server room. Now it runs on: • iPhone • Android • Mac PrismML's Bonsai makes it possible. • 1-bit weights • 27B params in just 3.9GB • ~90% of full precision quality (PrismML evals) • Better than the 2-bit version at less than half the size The entire Bonsai family is now live in RunAnywhere. • 1.7B to 27B models • 1-bit + 2-bit ternary • Thinking mode On iOS and Mac, Bonsai runs through ggml's llama.cpp and Apple's MLX. On Android, Bonsai runs through ggml's llama.cpp and directly on the Qualcomm Hexagon NPU through QHexRT, our proprietary inference runtime. We built custom silicon kernels to make 1-bit inference on an NPU possible for the first time. Two years ago this needed a data center. Now it thinks in airplane mode. Now available in the RunAnywhere app on the App Store and Google Play.

RunAnywhere (YC W26)

16,421 views • 1 month ago