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.

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These... videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shottonshow more

Alex Kendall

17,385 subscribers

631,844 views • 2 years ago •via X (Twitter)

Science & Technology Education #GAIA1

Anya Rossi• Live Now

Private livecam show

10 Comments

Alex Kendall2 years ago

Here's a thread with some of my favourite examples!

Hamid Abdollahi2 years ago

Exciting advancements with #GAIA1, @alexgkendall! However, how will we ensure the synthetic data's diversity truly represents real-world scenarios without bias? How do we validate the correctness of AI-imagined outcomes against real-world driving nuances? Isn't there a risk of overfitting to the generated scenarios, and how do we bridge the gap between synthetic training and real-world robustness? While the promise is grand, isn't real-world data still invaluable for nuances hard to replicate synthetically?

Alex Kendall2 years ago

You're right these are the key questions and where we've been focused to make sure these aren't just pretty videos but can accelerate the robustness of our driving policies. With the right approach, you can build a world model which can balance realism and diversity (and even able to train your policy adversarially).

Furkan Gözükara2 years ago

the videos are really coherent how many seconds it can generate? do you use any driving video or just from text to video?

Alex Kendall2 years ago

It can keep generating videos perpetually, so no limit to the length... here's an example of a long scene

Ivan Kirigin2 years ago

Very impressive

Yash2 years ago

You guys should be training AI's on the roads of India The model will be way better than any made up till this date.

SolarSailor.eth2 years ago

This is awesome. Now we can generate the most absurd cases that would be at the tails of standard deviation of occurrence. Major unlock

Captain Hype 🦊 🇺🇦 ❤️2 years ago

@WholeMarsBlog Next level !! ♥️♥️

Morlock2 years ago

I think you are off by several orders of magnitude on the amount of training data, but having said that, the fundamental issue is the need for variance in the data, rather than just the amount of data.

Related Videos

Introducing GAIA-2 🌎Generative world modeling just stepped up a gear. GAIA-2 is the latest development of Wayve’s video-generative world model tailored for driving. GAIA-2 offers richer, more realistic, and highly controllable synthetic driving scenarios, accelerating Wayve’s path to safe driver assistance and automated driving at scale. Learn more about GAIA-2 in our Blog: #GAIA2 #GAIA #EmbodiedAI

Introducing GAIA-2 🌎Generative world modeling just stepped up a gear. GAIA-2 is the latest development of Wayve’s video-generative world model tailored for driving. GAIA-2 offers richer, more realistic, and highly controllable synthetic driving scenarios, accelerating Wayve’s path to safe driver assistance and automated driving at scale. Learn more about GAIA-2 in our Blog: #GAIA2 #GAIA #EmbodiedAI

Wayve

41,626 views • 1 year ago

Data is 👑 Our foundation model learns from globally diverse, unlabelled data. Without telling it how to drive or naming different scene elements, our AI learns patterns and behaviours. Our results this week demonstrate how rapidly our AI can learn new behaviours, finding that with hundreds of hours worth of country-specific data, our foundation model learns new skills, like driving on the right in the US! See how our Wayve AI Driver improves driving in the US with data from 0-10-100-250-500 hours worth of additional US-specific data. 👇 By leveraging diverse data, we are building a highly generalizable AI that enables safe, adaptable, and scalable autonomy—we’ve taken it to the US and Germany but stay tuned for where is next 🌎⁉️

Data is 👑 Our foundation model learns from globally diverse, unlabelled data. Without telling it how to drive or naming different scene elements, our AI learns patterns and behaviours. Our results this week demonstrate how rapidly our AI can learn new behaviours, finding that with hundreds of hours worth of country-specific data, our foundation model learns new skills, like driving on the right in the US! See how our Wayve AI Driver improves driving in the US with data from 0-10-100-250-500 hours worth of additional US-specific data. 👇 By leveraging diverse data, we are building a highly generalizable AI that enables safe, adaptable, and scalable autonomy—we’ve taken it to the US and Germany but stay tuned for where is next 🌎⁉️

Alex Kendall

17,178 views • 1 year ago

Here's some footage from my Tesla's dashcam. Just kidding. Did you believe me? The truth is, this video is completely fake. It was generated by Tesla's world simulator, a generative AI model that not only allows Tesla to generate realistic synthetic training data, but also validate new versions of their self-driving model.

Here's some footage from my Tesla's dashcam. Just kidding. Did you believe me? The truth is, this video is completely fake. It was generated by Tesla's world simulator, a generative AI model that not only allows Tesla to generate realistic synthetic training data, but also validate new versions of their self-driving model.

Whole Mars Catalog

226,004 views • 8 months ago

Autonomous driving with Chain of Thought - autopilot thinking out loud in text! LINGO-1 is the most interesting work I've read in autodriving for a while. Before: perception -> driving action After: perception -> textual reasoning -> action LINGO-1 trains a video-language model that comments on the ongoing scene. You can ask it to explain its decisions ("why are you stopped?") and planning ("what are you gonna do next?"). The explicit reasoning step comes with key benefits: - Explainability: driving models are no longer a mysterious blackbox that you pray for safety. - Counterfactuals: it's able to imagine scenarios that are not in the training data, and reason through how to handle them correctly. - Long-tail programming: there are soooo many edge cases in driving. It's impossible to have good data coverage on everything. Instead of collecting 1000s of examples to "neural program" a case, you can now have a human teacher write prompts to explain a handful of examples. LINGO-1 is closely related to a few works in game AI: - MineDojo (my team's work at NVIDIA, learns a reward model that aligns Minecraft gameplay videos with their transcripts. The model, called "MineCLIP", is able to ground commentary text in the video pixels. - Thought Cloning (Jeff Clune): pixel -> language -> action loop in gridworlds.

Autonomous driving with Chain of Thought - autopilot thinking out loud in text! LINGO-1 is the most interesting work I've read in autodriving for a while. Before: perception -> driving action After: perception -> textual reasoning -> action LINGO-1 trains a video-language model that comments on the ongoing scene. You can ask it to explain its decisions ("why are you stopped?") and planning ("what are you gonna do next?"). The explicit reasoning step comes with key benefits: - Explainability: driving models are no longer a mysterious blackbox that you pray for safety. - Counterfactuals: it's able to imagine scenarios that are not in the training data, and reason through how to handle them correctly. - Long-tail programming: there are soooo many edge cases in driving. It's impossible to have good data coverage on everything. Instead of collecting 1000s of examples to "neural program" a case, you can now have a human teacher write prompts to explain a handful of examples. LINGO-1 is closely related to a few works in game AI: - MineDojo (my team's work at NVIDIA, learns a reward model that aligns Minecraft gameplay videos with their transcripts. The model, called "MineCLIP", is able to ground commentary text in the video pixels. - Thought Cloning (Jeff Clune): pixel -> language -> action loop in gridworlds.

Jim Fan

552,738 views • 2 years ago

NEWS: Waymo has introduced the Waymo World Model, "a frontier generative model built on Google DeepMind’s Genie 3 that sets a new bar for large-scale, hyper-realistic autonomous driving simulation." "By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes to planes landing on freeways—long before it encounters them in the real world. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data. This combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments. In the following sections we showcase the Waymo World Model in action, featuring simulations of the Waymo Driver navigating diverse rare edge-case scenarios." More info below.

NEWS: Waymo has introduced the Waymo World Model, "a frontier generative model built on Google DeepMind’s Genie 3 that sets a new bar for large-scale, hyper-realistic autonomous driving simulation." "By simulating the “impossible”, we proactively prepare the Waymo Driver for some of the most rare and complex scenarios—from tornadoes to planes landing on freeways—long before it encounters them in the real world. The model’s architecture offers high controllability, allowing our engineers to modify simulations with simple language prompts, driving inputs, and scene layouts. Notably, the Waymo World Model generates high-fidelity, multi-sensor outputs that include both camera and lidar data. This combination of broad world knowledge, fine-grained controllability, and multi-modal realism enhances Waymo’s ability to safely scale our service across more places and new driving environments. In the following sections we showcase the Waymo World Model in action, featuring simulations of the Waymo Driver navigating diverse rare edge-case scenarios." More info below.

Sawyer Merritt

133,168 views • 4 months ago

I’m really proud of the results Wayve released today. 📊 For the first time we share quantitative results of our global generalisation journey. What did we learn? 💡 Over our first 8-weeks training in the US, our AI has rapidly adapted to its unique driving environment with just 500 hours worth of incremental US-specific training data, on top of our large scale foundation model's learning. What’s more, we just launched in Germany and first results are already 3x better — generalisation just keeps improving with new data. It is clear to me the future of autonomy will be unlocked by Embodied AI capable of generalising to new countries, vehicles and able to safely navigate challenging edge cases it has never seen before during training. Now we’re excited to kick things up a gear and work with the world’s leading automotive manufacturers to collect the data necessary to validate this technology and deploy it in consumer vehicles worldwide. Embodied AI is a generational opportunity and the pace of progress I'm seeing is incredible. We're building the strongest team in AI for automated driving. If you're excited about this mission, join us!

I’m really proud of the results Wayve released today. 📊 For the first time we share quantitative results of our global generalisation journey. What did we learn? 💡 Over our first 8-weeks training in the US, our AI has rapidly adapted to its unique driving environment with just 500 hours worth of incremental US-specific training data, on top of our large scale foundation model's learning. What’s more, we just launched in Germany and first results are already 3x better — generalisation just keeps improving with new data. It is clear to me the future of autonomy will be unlocked by Embodied AI capable of generalising to new countries, vehicles and able to safely navigate challenging edge cases it has never seen before during training. Now we’re excited to kick things up a gear and work with the world’s leading automotive manufacturers to collect the data necessary to validate this technology and deploy it in consumer vehicles worldwide. Embodied AI is a generational opportunity and the pace of progress I'm seeing is incredible. We're building the strongest team in AI for automated driving. If you're excited about this mission, join us!

Alex Kendall

21,933 views • 1 year ago

I was impressed when my team showed me this example of intelligence and behavioural generalisation. Watch this — seeing a person bow to welcome our car to move forward is definitely not something I've seen outside of Japan. Yet in this clip you can see our AI Driver recognise that this person is asking us to stop. We have the intelligence to understand the context that we shouldn't nudge around them, rather hold in place, despite no signage or red light. Then, if you keep watching, you'll see we recognise the bow and a wave as permission to drive through the road works. Less than 1% of our training data is from Japan. Our AI is trained end-to-end. There are no explicit rules or labelling, no explicit gesture or body pose recognition, this is all learned capability that is scalable and data-driven. This is how Wayve will scale autonomous driving to the world and address the long-tail of edge cases.

I was impressed when my team showed me this example of intelligence and behavioural generalisation. Watch this — seeing a person bow to welcome our car to move forward is definitely not something I've seen outside of Japan. Yet in this clip you can see our AI Driver recognise that this person is asking us to stop. We have the intelligence to understand the context that we shouldn't nudge around them, rather hold in place, despite no signage or red light. Then, if you keep watching, you'll see we recognise the bow and a wave as permission to drive through the road works. Less than 1% of our training data is from Japan. Our AI is trained end-to-end. There are no explicit rules or labelling, no explicit gesture or body pose recognition, this is all learned capability that is scalable and data-driven. This is how Wayve will scale autonomous driving to the world and address the long-tail of edge cases.

Alex Kendall

68,096 views • 7 months ago

1/ BREAKING – DePIN's Biggest New Deal: Valeo x NATIX Network with Alireza Ghods Host: Connor Lovely 🎬 We discuss: - Why a $3B, Fortune 500 company wants Natix data - What is a World Foundational Model? - Why autonomous driving needs synthetic data Timestamps: 00:00 - Introduction 01:14 - Updates on VX360 and Data Sales 02:09 - Vision Language Model and Its Applications 04:39 - Importance of Diverse Data for World Models 06:20 - Details on the Valeo Deal 08:15 - Use Cases and Future Plans for World Models 10:45 - Synthetic Data and Real-World Applications 19:37 - Future of Physical AI and Autonomous Driving 23:51 - Conclusion Watch on other platforms below ⬇️

1/ BREAKING – DePIN's Biggest New Deal: Valeo x NATIX Network with Alireza Ghods Host: Connor Lovely 🎬 We discuss: - Why a $3B, Fortune 500 company wants Natix data - What is a World Foundational Model? - Why autonomous driving needs synthetic data Timestamps: 00:00 - Introduction 01:14 - Updates on VX360 and Data Sales 02:09 - Vision Language Model and Its Applications 04:39 - Importance of Diverse Data for World Models 06:20 - Details on the Valeo Deal 08:15 - Use Cases and Future Plans for World Models 10:45 - Synthetic Data and Real-World Applications 19:37 - Future of Physical AI and Autonomous Driving 23:51 - Conclusion Watch on other platforms below ⬇️

Proof of Coverage | Tech’s Creative Agency

11,852 views • 5 months ago

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

This is THE moment of Physical AI! We are officially announcing Cosmos 3: Omnimodal World Models for Physical AI 🚀 - Cosmos 3 is an omnimodal world model: within a unified architecture, it can understand and generate language, images, video, audio, and actions. - It is not just a VLM, not just a video generator, not just an audio-visual generative model, and not just a physics simulator / world-action model. It can understand images and videos, generate images, videos, and audio, simulate future worlds, predict actions, and generate robot policies—enabling models to truly begin to “touch the world.” - Cosmos 3 is the #1 open-weight reasoner / T2I / I2V / robot policy across many benchmarks. Huge thanks to every teammate who fought side by side on this journey—from architecture, data, training, infra, serving, and evaluation to post-training. Every part of this project carries an incredible amount of hard work. This was my first time leading a project as Tech Lead, and I feel truly fortunate. The future of Physical AI needs models that can not only “see” and “describe” the world, but also “imagine,” “simulate,” and “act”—and eventually close the loop with the real world. I hope Cosmos 3 can become an important starting point for this direction, and I’m excited to push Physical AI into its next stage together with the open-source community. Welcome to the era of Physical AI. HuggingFace: Project Website: Code:

Max Zhaoshuo Li 李赵硕

1,077,546 views • 1 month ago

3-months ago we went from only driving in the UK, California and Germany, to driving in seven different countries with very different climates. 🌍 🇺🇸 In the US, we went from driving in one state to driving in ten! From the sunny streets of California to the snowy mountain passes in Wyoming, the Wayve AI Driver is navigating a diversity of environments in the US on our journey to driving in 500 cities around the world. ~400 cities to go before the end of the year - all enabled by one global foundation model 🌍 #AI500 #GlobalRoadTrip #EmbodiedAI

3-months ago we went from only driving in the UK, California and Germany, to driving in seven different countries with very different climates. 🌍 🇺🇸 In the US, we went from driving in one state to driving in ten! From the sunny streets of California to the snowy mountain passes in Wyoming, the Wayve AI Driver is navigating a diversity of environments in the US on our journey to driving in 500 cities around the world. ~400 cities to go before the end of the year - all enabled by one global foundation model 🌍 #AI500 #GlobalRoadTrip #EmbodiedAI

Wayve

32,943 views • 1 year ago

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

AI for robotics has some monumental challenges, like high dimensionality and reasoning with the physical world. Ashok Elluswamy, AI lead at Tesla, thinks the hardest problem is Evaluation. - Loss isn't a perfect indicator of Policy Neural Network's quality. - Testing in the real world for all the long-tail failure cases is not possible. To solve the evaluation challenge, Tesla has developed a World Simulator Model. It is trained on state and action pairs, so for a given current camera feed and current action, the model generates the next frame in the cameras. Once the world simulation is good enough, it can be hooked up to the policy network for a closed-loop simulation. In this setup, the model generates the next video frames, and based on those, the policy network comes up with the next action, which feeds back into the world simulation; this continuous loop creates a coherent simulation. The world simulation neural network is not just applicable to self-driving but also to humanoids, because Tesla trains it on common data. The examples show Optimus navigating or manipulating inside the world simulation, with all the pixels being generated by the world simulation model. The robotic agents can be tested in an accurately reproduced edge case and in other potential variations of the same edge case.

The Humanoid Hub

16,591 views • 4 months ago

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."

NEWS: NVIDIA just announced Alpamayo, what CEO Jensen Huang calls the world’s first thinking, reasoning autonomous vehicle AI, launching on U.S. roads later this year, starting with the Mercedes CLA. Jensen: "It's trained end-to-end. Literally from camera in to actuation out; It reasons what action it is about to take, the reason by which is came about that action, and the trajectory." Alpamayo introduces Vision-Language-Action (VLA) models, which enable self-driving systems to interpret what they see, reason about complex driving scenarios, and generate driving actions. The platform includes large reasoning models, simulation tools for testing rare and edge-case scenarios, and open datasets for training and validation. NVIDIA says the approach improves transparency, safety, and robustness in autonomous systems, particularly in complex real-world environments, and supports progress toward higher levels of vehicle autonomy: "With a 10-billion-parameter architecture, Alpamayo 1 uses video input to generate trajectories alongside reasoning traces, showing the logic behind each decision. Developers can adapt Alpamayo 1 into smaller runtime models for vehicle development, or use it as a foundation for AV development tools such as reasoning-based evaluators and auto-labeling systems. Alpamayo 1 provides open model weights and open-source inferencing scripts. Future models in the family will feature larger parameter counts, more detailed reasoning capabilities, more input and output flexibility, and options for commercial usage."

Sawyer Merritt

1,603,176 views • 5 months ago

XPENG is thrilled to introduce X-World, our controllable multi-view generative world model powered by video diffusion technology. Pushing the boundaries of smart mobility, X-World delivers real-time response and continuous multi-view generation to simulate complex driving environments. Xianming Liu, Head of XPENG’s General AI Center, emphasizes: "Beyond generation, X-World serves as the scalable infrastructure critical for training and validating the next leap in autonomous driving." $XPEV

XPENG is thrilled to introduce X-World, our controllable multi-view generative world model powered by video diffusion technology. Pushing the boundaries of smart mobility, X-World delivers real-time response and continuous multi-view generation to simulate complex driving environments. Xianming Liu, Head of XPENG’s General AI Center, emphasizes: "Beyond generation, X-World serves as the scalable infrastructure critical for training and validating the next leap in autonomous driving." $XPEV

XPENG

4,070,681 views • 3 months ago

🚨ELON: FULLY AUTONOMOUS DRIVING IN TEXAS AND CALIFORNIA BY NEXT YEAR "We expect to start fully autonomous, unsupervised full self-driving (FSD) in Texas and California next year with the Model 3 and Model Y. As for the CyberCab, which is highly optimized for autonomous transport, we expect it to be in production by 2026—well, before 2027." Source: Tesla

🚨ELON: FULLY AUTONOMOUS DRIVING IN TEXAS AND CALIFORNIA BY NEXT YEAR "We expect to start fully autonomous, unsupervised full self-driving (FSD) in Texas and California next year with the Model 3 and Model Y. As for the CyberCab, which is highly optimized for autonomous transport, we expect it to be in production by 2026—well, before 2027." Source: Tesla

Mario Nawfal

211,268 views • 1 year ago

Video #2. Every day this week we are posting an hour long video of zero shot AI Driving in a different country all around the world. This time we're in Germany, driving around the rolling hills and into Stuttgart. 🇩🇪 Check it out! What matters now is scaled autonomy performance. We built our first world model in 2018. First VLA reasoning model in 2022. First generative simulator in 2023. Today we have integrated these into safe and compliant product ready for global scale. We're delighted to be partnering with the German ecosystem to bring autonomy to the rich heritage of brands. Together, we will build market-leading products for both consumer vehicles and robotaxis.

Video #2. Every day this week we are posting an hour long video of zero shot AI Driving in a different country all around the world. This time we're in Germany, driving around the rolling hills and into Stuttgart. 🇩🇪 Check it out! What matters now is scaled autonomy performance. We built our first world model in 2018. First VLA reasoning model in 2022. First generative simulator in 2023. Today we have integrated these into safe and compliant product ready for global scale. We're delighted to be partnering with the German ecosystem to bring autonomy to the rich heritage of brands. Together, we will build market-leading products for both consumer vehicles and robotaxis.

Alex Kendall

23,998 views • 3 months ago

$AI agents are about to redefine the internet. The mistake we made with Large Language Models? We let a handful of corporations capture all the value. Action Model is building a different path. By training through our extension, users gain fractional ownership in the Large Action Model, giving them a real stake in the future of AI. When LLMs emerged, the upside flowed to Big Tech. This time, it doesn’t have to. They’re building AI on our data, and keeping the upside for themselves. Community-owned Large Action Model is how we take it back.$

AI agents are about to redefine the internet. The mistake we made with Large Language Models? We let a handful of corporations capture all the value. Action Model is building a different path. By training through our extension, users gain fractional ownership in the Large Action Model, giving them a real stake in the future of AI. When LLMs emerged, the upside flowed to Big Tech. This time, it doesn’t have to. They’re building AI on our data, and keeping the upside for themselves. Community-owned Large Action Model is how we take it back.

Action Model

76,645 views • 4 months ago

The Atlas Miner is finally here and Drive2Earn 2.0 is rolling out with an excellent explanation given by Chico Crypto-"The Most Trustless Name in News" in his 5 minute video. This is how the Atlas Miner works: 1. Dedicated DePIN + AI hardware device 2. Connects to any dash camera 3. Collects driving footage, which is anonymized and shared with vehicle manufacturers to train their self driving vehicles (we have such a vehicle for testing already). 4. Uses custom A.I. computer vision algorithms to detect traffic issues (accidents, congestion, road closures, road work, potholes, police cars) and sends these detections to other drivers on the Atlas Navi app rerouting them to avoid those areas 5. Price $300 + shipping, payable in $NAVI only. 6. Get paid for every beneficial data point you collect. This data is very valuable to drivers using Atlas Navi, to car manufacturers and smart cities. Owners of Atlas Miner are rewarded for every mile driven on top of regular NFT rewards. The Autonomous Driving market is expected to reach $6T within the next eight years and we aim to be the main provider of driving data for training these algorithms and real time traffic notification / routing for such vehicles. We are opening the whitelist for a limited quantity of Atlas Miners. Sign up to the whitelist and get rewarded for every mile driven: #NAVI #DePIN #AtlasMiner

The Atlas Miner is finally here and Drive2Earn 2.0 is rolling out with an excellent explanation given by Chico Crypto-"The Most Trustless Name in News" in his 5 minute video. This is how the Atlas Miner works: 1. Dedicated DePIN + AI hardware device 2. Connects to any dash camera 3. Collects driving footage, which is anonymized and shared with vehicle manufacturers to train their self driving vehicles (we have such a vehicle for testing already). 4. Uses custom A.I. computer vision algorithms to detect traffic issues (accidents, congestion, road closures, road work, potholes, police cars) and sends these detections to other drivers on the Atlas Navi app rerouting them to avoid those areas 5. Price $300 + shipping, payable in $NAVI only. 6. Get paid for every beneficial data point you collect. This data is very valuable to drivers using Atlas Navi, to car manufacturers and smart cities. Owners of Atlas Miner are rewarded for every mile driven on top of regular NFT rewards. The Autonomous Driving market is expected to reach $6T within the next eight years and we aim to be the main provider of driving data for training these algorithms and real time traffic notification / routing for such vehicles. We are opening the whitelist for a limited quantity of Atlas Miners. Sign up to the whitelist and get rewarded for every mile driven: #NAVI #DePIN #AtlasMiner

ATLAS NAVI | AI Navigation APP with 1M Downloads

360,303 views • 2 years ago

ELON: OUR IN-HOUSE SELF-DRIVING SOFTWARE AND HARDWARE ARE UNBEATABLE “Our strategy, which we started a little over three years ago, is to design and build a computer that is fully optimized and aiming for full self-driving, then write software that is designed to work specifically on that computer and get the most out of that computer. You have tailored hardware that is a master of one trade, self-driving. Nvidia is a great company, but they have many customers, and so they apply their resources to do a generalized solution. We care about one thing: Self-driving. So it was designed to do that incredibly well. The software is also designed to run on that hardware incredibly well. The combination of the software and the hardware, I think, is unbeatable.” Source: Tesla Autonomy Day, April 22, 2019

ELON: OUR IN-HOUSE SELF-DRIVING SOFTWARE AND HARDWARE ARE UNBEATABLE “Our strategy, which we started a little over three years ago, is to design and build a computer that is fully optimized and aiming for full self-driving, then write software that is designed to work specifically on that computer and get the most out of that computer. You have tailored hardware that is a master of one trade, self-driving. Nvidia is a great company, but they have many customers, and so they apply their resources to do a generalized solution. We care about one thing: Self-driving. So it was designed to do that incredibly well. The software is also designed to run on that hardware incredibly well. The combination of the software and the hardware, I think, is unbeatable.” Source: Tesla Autonomy Day, April 22, 2019

Mario Nawfal

90,564 views • 1 year ago

Elon Musk: “In order to solve full self-driving properly, you have to solve real-world AI. The road networks are designed to work with a biological neural net — our brains — and with vision — our eyes. So, in order to make it work with computers, you need to solve real-world AI and vision. We need cameras and silicon neural nets for self-driving to work in a system designed for eyes and biological neural nets. When you put it that way, it’s quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision.”

Elon Musk: “In order to solve full self-driving properly, you have to solve real-world AI. The road networks are designed to work with a biological neural net — our brains — and with vision — our eyes. So, in order to make it work with computers, you need to solve real-world AI and vision. We need cameras and silicon neural nets for self-driving to work in a system designed for eyes and biological neural nets. When you put it that way, it’s quite obvious that the only way to solve full self-driving is to solve real-world AI and sophisticated vision.”

Elonogy

14,228 views • 16 days ago

GROK AI Grok—the advanced AI model by Elon Musk’s is now officially integrated with AGIX! 🎉 What this means: 🌐 Real-time X data processing, making AGIX smarter and faster. 🤖 Adaptive learning capabilities, driving more powerful decisions. 🚀 A leap forward in our mission to deliver the most cutting-edge AI in Web3 and beyond. Together, GROK and AGIX are shaping the future of AI!

GROK AI Grok—the advanced AI model by Elon Musk’s is now officially integrated with AGIX! 🎉 What this means: 🌐 Real-time X data processing, making AGIX smarter and faster. 🤖 Adaptive learning capabilities, driving more powerful decisions. 🚀 A leap forward in our mission to deliver the most cutting-edge AI in Web3 and beyond. Together, GROK and AGIX are shaping the future of AI!

AGIX | $AGX

25,514 views • 1 year ago