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.

Try pi-05 from Physical Intelligence today on your robot. One click fine-tuning and inference from phosphobot. No code and no GPU required. -> docs .phospho .ai

Pierre-Louis Biojout (PLB)

9,038 subscribers

12,394 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

8 Comments

Pierre-Louis Biojout (PLB)1 year ago

Credits: @IliaLarchenko @JunyaoShi @shreyasgite

C12s1 year ago

@physical_int Robotics just got way more accessible.

Abhishek Ramnath1 year ago

@physical_int Does it support open arms bimanual setup?

Pierre-Louis Biojout (PLB)1 year ago

@physical_int Not yet. What's your use case?

Abhishek Ramnath1 year ago

@physical_int We are planning to explore use cases of VLA models inside warehouses. Openarm seems to be at the right price point and specs to do this and your platform will help with quick experimentation to validate use cases.

Pierre-Louis Biojout (PLB)1 year ago

@physical_int You should DM me

clem 🤗1 year ago

@physical_int You should add it to the HF hub!

phospho 🧪1 year ago

@physical_int 🧪🧪🧪

Related Videos

now opus 5.5 visualized how Physical Intelligence π0.5 inference works on DROID, built from open code and paper

now opus 5.5 visualized how Physical Intelligence π0.5 inference works on DROID, built from open code and paper

Dmytro Hrybov

14,676 views • 1 month ago

Centralized AI inference runs on one provider. NEAR AI's confidential inference draws from multiple compute partners distributed across regions instead of a single data center. No KYC required. No visibility into what you're running. Intelligence owned by the user.

Centralized AI inference runs on one provider. NEAR AI's confidential inference draws from multiple compute partners distributed across regions instead of a single data center. No KYC required. No visibility into what you're running. Intelligence owned by the user.

NEAR Protocol

73,204 views • 4 months ago

The future of artificial intelligence is physical. Physical Intelligence runs robotic control inference on Modal with >2x lower latency than the lag between your brain and your finger.

The future of artificial intelligence is physical. Physical Intelligence runs robotic control inference on Modal with >2x lower latency than the lag between your brain and your finger.

Modal

95,966 views • 7 months ago

Run StableDAW on your PC with 1 click (No GPU needed) A full AI music studio powered by Stable Audio 3: generate tracks from text, edit them on a timeline, master them, even DJ them --- 100% local. Created by GANTASMO No GPU required. All OS supported: Windows, Linux, and Mac.

Run StableDAW on your PC with 1 click (No GPU needed) A full AI music studio powered by Stable Audio 3: generate tracks from text, edit them on a timeline, master them, even DJ them --- 100% local. Created by GANTASMO No GPU required. All OS supported: Windows, Linux, and Mac.

cocktail peanut

16,905 views • 5 months ago

The missing piece for the ChatGPT moment of robotics is finally here Today, we are releasing phosphobot, an open-source app to control robots intuitively and train the most powerful AI models for the cheapest robots possible -> phospho-app/phosphobot 🧵 What we are building:

The missing piece for the ChatGPT moment of robotics is finally here Today, we are releasing phosphobot, an open-source app to control robots intuitively and train the most powerful AI models for the cheapest robots possible -> phospho-app/phosphobot 🧵 What we are building:

Pierre-Louis Biojout (PLB)

35,860 views • 1 year ago

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon

Paolo Ardoino 🤖

42,133 views • 1 year ago

Introducing Relay Nodes ✷ No GPU required ✷ Keep inference nodes connected Apply ↓

Introducing Relay Nodes ✷ No GPU required ✷ Keep inference nodes connected Apply ↓

Fortytwo

12,775 views • 11 months ago

Physical AI gets so complicated at times ... We just launched the easiest way to run frontier physical AI models on your robots - the UI can't get any simpler: I want to run a on a to No GPU, pure real-time inference over the cloud. Live now at:

Physical AI gets so complicated at times ... We just launched the easiest way to run frontier physical AI models on your robots - the UI can't get any simpler: I want to run a on a to No GPU, pure real-time inference over the cloud. Live now at:

Chris Yoo ⚡ CoRL

16,467 views • 28 days ago

Claude Code is already incredible. We gave it one more superpower. /docs fetch <url> Live docs from any site. Cached in your repo. Right in your terminal. No more coding against outdated docs. Powered by Hyperbrowser MCP.

Claude Code is already incredible. We gave it one more superpower. /docs fetch <url> Live docs from any site. Cached in your repo. Right in your terminal. No more coding against outdated docs. Powered by Hyperbrowser MCP.

Hyperbrowser

299,002 views • 10 months ago

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU

running Claude Code w/ local models on my own GPUs at home > vLLM serving GLM-4.5 Air > on 4x RTX 3090s > nvtop showing live GPU load > Claude Code generating code + docs > end-to-end on my AI cluster this is what local AI actually looks like Buy a GPU

Ahmad

262,712 views • 10 months ago

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.

.Kimi.ai K3 from Moonshot AI is now live on DigitalOcean Inference Engine. 1M-token context, native vision, built to run agentic tasks for hours. Supported on Inference Router and model synthesis to maximize intelligence per dollar. No setup, no model ops.

DigitalOcean

672,368 views • 3 months ago

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

Paolo Ardoino 🤖

142,902 views • 1 year ago

what’s new in AI Studio: - workspace integration: build with the Google ecosystem of apps (Docs, Sheets, Gmail, and more) - Android apps: vibe code and test apps on your phone - publish your first two apps live on Cloud Run, no credit card required

what’s new in AI Studio: - workspace integration: build with the Google ecosystem of apps (Docs, Sheets, Gmail, and more) - Android apps: vibe code and test apps on your phone - publish your first two apps live on Cloud Run, no credit card required

Google AI Studio

158,447 views • 5 months ago

Lip Sync 2.0 from VEED | AI Video Creation is now live on fal. Swap the audio on any video and automatically match the lips, emotion, style and timing. No training or fine-tuning required. - Process footage up to 4K - Clips up to 10 minutes - Controllable sync strength

Lip Sync 2.0 from VEED | AI Video Creation is now live on fal. Swap the audio on any video and automatically match the lips, emotion, style and timing. No training or fine-tuning required. - Process footage up to 4K - Clips up to 10 minutes - Controllable sync strength

fal

11,612 views • 4 months ago

Theta offers GPU compute matched to your workload, instant and affordable. No more paying for what you don't use. No more H100s when distributed inference will do. Sign up at No call required. 🖥️

Theta offers GPU compute matched to your workload, instant and affordable. No more paying for what you don't use. No more H100s when distributed inference will do. Sign up at No call required. 🖥️

Theta Network

15,381 views • 6 months ago

H100s, Blackwell & the GPU Revolution GPU supply is tight and demand is surging. We aggregate thousands of H100s, A100s, L40S, MI300X & more into one on-demand pool. One click and you’re training LLMs or vision models—no sticker shock. Skip the shortage. Build on NodeAI today. ⚡️ #AI #GPU #NODEAI

H100s, Blackwell & the GPU Revolution GPU supply is tight and demand is surging. We aggregate thousands of H100s, A100s, L40S, MI300X & more into one on-demand pool. One click and you’re training LLMs or vision models—no sticker shock. Skip the shortage. Build on NodeAI today. ⚡️ #AI #GPU #NODEAI

Node AI | $GPU

12,982 views • 1 year ago

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,928 views • 8 months ago

🚀 Container-as-a-Service is now live! Launch production-grade containers in seconds. What it means: ⚙️ One-line deploys for validators, inference endpoints, and light services 🖥️ GPU and CPU-aware scheduling 🧰 Built-in autoscaling, networking, and health checks 🧠 No cluster setup. No YAML. No burnout. Whether you’re spinning up a validator or hosting a model, CaaS gives you the fastest path from code to container. → Try it now: io.net accelerates AI

🚀 Container-as-a-Service is now live! Launch production-grade containers in seconds. What it means: ⚙️ One-line deploys for validators, inference endpoints, and light services 🖥️ GPU and CPU-aware scheduling 🧰 Built-in autoscaling, networking, and health checks 🧠 No cluster setup. No YAML. No burnout. Whether you’re spinning up a validator or hosting a model, CaaS gives you the fastest path from code to container. → Try it now: io.net accelerates AI

io.net

17,345 views • 1 year ago

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

23,504 views • 4 months ago