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.

Introducing PROWL! We’ve built RL agents that explore game environments, tasked with discovering failures in world models across physics, visuals, and actions. Those failures then become training data in an automated loop that advances world model performance.

Odyssey

34,535 subscribers

64,154 views • 3 months ago •via X (Twitter)

Gaming Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in robotics, healthcare, and other areas "then scale them toward a universal world model"

Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in robotics, healthcare, and other areas "then scale them toward a universal world model"

Haider.

201,090 views • 3 months ago

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.

Today I’m excited to introduce micro1 Intelligence, the world’s most advanced platform for training frontier AI models. Achieving AGI is bottlenecked by one main thing: high-quality data. Data based on real-world environments that capture human expert workflows, complex decision-making, and reward signals models need to learn. With micro1 Intelligence, frontier labs can train on RL environments across every subject matter all in one place.

Ali Ansari

332,850 views • 9 months ago

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

51,726 views • 9 days ago

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️ These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. →

Google DeepMind

1,441,767 views • 1 year ago

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

Odyssey

2,185,951 views • 4 months ago

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).

the micro1 robotics lab: real world data for intelligent models that co-exist in the physical world. we’re in-the-wild across 75 countries in 6,000+ unique environments collecting data. diverse movements, objects, and settings. the future of AI is as human as you can imagine. join us to start training robots today (link in comments).

Ali Ansari

208,233 views • 5 months ago

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

263,337 views • 5 months ago

AGNOST AI (YC S26) JUST LAUNCHED ON PRODUCT HUNT! AI agents don’t fail like traditional software. They return 200. They pass evals. And they still quietly frustrate & churn users. Agnost AI finds those silent failures that evals miss & only show up in production conversations. Then we turn those failures into harness improvements & better models.

AGNOST AI (YC S26) JUST LAUNCHED ON PRODUCT HUNT! AI agents don’t fail like traditional software. They return 200. They pass evals. And they still quietly frustrate & churn users. Agnost AI finds those silent failures that evals miss & only show up in production conversations. Then we turn those failures into harness improvements & better models.

shubham

193,897 views • 4 days ago

Weekends are for research. Inside OptimAI labs, we’ve been pushing agents beyond the screen. A first glimpse of OptimAI Prime. Not just agents that think, but agents that operate. Learning through reinforcement, coordinating across the network, and executing in real-world environments. From digital workflows → to physical actions. This is the next step for the agent-native internet.🤖 Still early. But already in motion.

Weekends are for research. Inside OptimAI labs, we’ve been pushing agents beyond the screen. A first glimpse of OptimAI Prime. Not just agents that think, but agents that operate. Learning through reinforcement, coordinating across the network, and executing in real-world environments. From digital workflows → to physical actions. This is the next step for the agent-native internet.🤖 Still early. But already in motion.

OptimAI Network

20,846 views • 3 months ago

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

Wenli Xiao

185,486 views • 10 months ago

Every roboticist knows the pain of "Day 1." Real-world training: ❌ Fragile hardware & constant failures ❌ High latency & slow iteration ❌ Narrow data diversity Axis is breaking the cycle. We’ve built the first browser-based, infra-level platform that decouples assets, tasks, and high-fidelity rendering. Through our protocol-level abstraction, we’re moving beyond simple simulation to a unified data engine: ✅ Low-barrier collection with infinite data diversity. ✅ Cross-simulator operations, unified. ✅ End-to-end acceleration: Task -> Data -> Train -> Deployment in one loop. Coming soon.

Every roboticist knows the pain of "Day 1." Real-world training: ❌ Fragile hardware & constant failures ❌ High latency & slow iteration ❌ Narrow data diversity Axis is breaking the cycle. We’ve built the first browser-based, infra-level platform that decouples assets, tasks, and high-fidelity rendering. Through our protocol-level abstraction, we’re moving beyond simple simulation to a unified data engine: ✅ Low-barrier collection with infinite data diversity. ✅ Cross-simulator operations, unified. ✅ End-to-end acceleration: Task -> Data -> Train -> Deployment in one loop. Coming soon.

Axis Robotics

39,586 views • 7 months ago

Wow. That's cool. Researchers just released World, an open-source Unreal Engine 5 simulator for training and testing LLM and VLM agents in realistic 3D environments. The platform supports RGB, depth, and segmentation sensors, along with navigation, vehicles, pedestrians, robots and procedural city generation. It's built with a Gym-like Python interface, it allows AI agents to learn physical and social reasoning in complex virtual worlds before real world deployment. We're moving from AI that only understands information to AI that can perceive, reason and act inside realistic simulated environments.

Wow. That's cool. Researchers just released World, an open-source Unreal Engine 5 simulator for training and testing LLM and VLM agents in realistic 3D environments. The platform supports RGB, depth, and segmentation sensors, along with navigation, vehicles, pedestrians, robots and procedural city generation. It's built with a Gym-like Python interface, it allows AI agents to learn physical and social reasoning in complex virtual worlds before real world deployment. We're moving from AI that only understands information to AI that can perceive, reason and act inside realistic simulated environments.

SciTech Era

47,510 views • 2 months ago

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO

The World Model as NEO's Cognitive Core 1X has revealed a major AI development where the NEO humanoid can translate any natural language prompt into robotic action. It demonstrates this capability even for novel tasks, objects, and environments not found in its robot dataset. - the 1X World Model is trained on internet-scale human interaction videos and fine-tuned with robot data to ground its understanding in physics and in NEO's embodiment - from a simple voice or text prompt, the world model generates a visualization of future actions - a built-in inverse dynamics model then translates these into precise motor movements for NEO

The Humanoid Hub

68,453 views • 7 months ago

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

Prime Intellect engineers explained how they train reasoning models over the open internet in 30 minutes - better than $3000 distributed training courses. split policy and rollouts across nodes -> run agents in parallel envs -> verify with LLM judges -> gradient-sync over the internet -> train Llama, Qwen, Gemma at cluster scale on rented GPUs. That loop is why open reasoning models are catching closed labs without owning a data center. Prime-RL + verifiers + distributed rollouts + LLM judges + multi-cloud GPUs - that's the stack. Watch and save it, then launch your first distributed RL run this week.

h100envy

40,022 views • 1 month ago

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Today we are announcing Genie 3, a general purpose world model by Google DeepMind that can generate dynamic, interactive environments with a single text prompt. World models are AI that understand facets of the world (like Veo's knowledge of intuitive physics or Genie's mastery of new environments), and serve as a key stepping stone on the path to AGI. Genie 3 is our first world model to allow interaction in real-time, while also improving consistency and realism compared to Genie 2. Learn more ➡️

Google AI

102,711 views • 1 year ago

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics

Xiaomi Tech

22,591 views • 1 month ago

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."

TBPN

76,696 views • 1 year ago

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.

Liquid AI's head of post-training explained how they built a small model that runs on-device under 1 GB in 20 minutes - better than $2500 small-model bootcamps. pick LFM2.5 base -> on-policy preference alignment -> agentic reinforcement learning -> curriculum training -> iterative model merging -> ship a 1B model that reliably calls tools on your phone. That loop is why frontier small models now beat 70B models on the tasks that actually matter. LFM2.5 + on-policy DPO + agentic RL + curriculum training + iterative merging - that's the stack. Watch and save it, then run a 1B agent on your phone tonight.

h100envy

86,872 views • 1 month ago

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

A model is only as good as its data, and we’ve long since exhausted the internet. From here on out, model progress is gated by data production. ’s Brendan (can/do) joined us at our Sovereign AI event to talk about how RL environments get built, and why your data might be your real moat: 00:00 Introduction 00:47 A short history of the data market: crowdsourcing to agentic data 02:29 What an RL environment is: worlds, apps, tasks 03:57 Why only humans can measure the frontier 05:35 Building verifiers is the hard part 06:44 Walkthrough: a real legal RL environment 08:18 Leaderboards — and what open weights change 09:45 Post-training results on Apex Agents 11:17 Three ways companies buy data 12:49 Q&A: How do you price data? 14:17 Q&A: What "data quality" actually means 16:42 Q&A: The misunderstanding about synthetic data 18:17 Q&A: Why RL environments now — and what comes after 21:20 Q&A: Can you scale rubric generation with models? 23:00 Q&A: RL environments for cyber defense 25:33 Q&A: Build data in-house or partner?

Pat Grady

65,487 views • 17 days ago