Alex Kendall's banner

Alex Kendall

@alexgkendall • 17,915 subscribers

CEO at @wayve_ai teaching cars how to drive with machine learning 🇳🇿

Shorts

With GAIA-4 we've been able to deploy world models for safety critical simulation. Here are some nice counter-factual replay examples with cyclist and pedestrian interactions. All running in closed-loop. Read more in our new blog:

With GAIA-4 we've been able to deploy world models for safety critical simulation. Here are some nice counter-factual replay examples with cyclist and pedestrian interactions. All running in closed-loop. Read more in our new blog:

29,204 views

We’ve only had access to GAIA-1 for a few weeks and are discovering new capabilities every day. The results are phenomenal! GAIA isn't just a generative video model, it is a world model, ie. controllable by video, text & action prompts Why is this huge for self driving? Thread:

We’ve only had access to GAIA-1 for a few weeks and are discovering new capabilities every day. The results are phenomenal! GAIA isn't just a generative video model, it is a world model, ie. controllable by video, text & action prompts Why is this huge for self driving? Thread:

185,472 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

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 Shotton

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 Shotton

631,869 views • 2 years ago

Another major milestone in Wayve's history. Proud to say we’ve secured $1.5 billion Series D investment at $8.6 billion valuation. We started a decade ago with a contrarian technical thesis: that self-driving is an AI problem, and Embodied AI will enable autonomy to scale without rules, HD-maps and using mass-produced hardware. Now we're entering commercialisation, we're taking a contrarian commercial strategy too, selecting the business model with the largest opportunity to scale. We're not selling our own cars, which limits scale to one brand. We're not operating our own fleets, which limits autonomy to city-by-city expansion. We're licensing autonomy to any vehicle, anywhere. This new business model is only possible now because we've built a general purpose AI driver, which is flexible to work with any vehicle architecture and proven to drive all around the world. This unlocks a high margin software licensing model, which we're now excited to be deploying with global partners with the strength of this new funding round. Thank you to our new and returning financial investors for backing our vision all the way: Eclipse, Balderton Capital, SoftBank, Ontario Teachers' Pension Plan, Baillie Gifford, British Business Bank, Icehouse Ventures and Schroders among other global institutional investors. We're deepening our partnerships with Microsoft and NVIDIA to build and deploy Embodied AI at global scale, and with Uber, who are announcing supervised robotaxi trials in 10 cities around the world, starting with London this year. To top it off, three top-10 global automakers across Europe, Japan and USA are backing and believing in our technology for consumer vehicles and robotaxis: Mercedes-Benz, Nissan and Stellantis. I’ve always believed that our end-to-end AI approach would lead the way in autonomy. This latest investment and the endorsement that comes with it make me believe that the industry is also now converging on that idea too. What's next? We have a busy next few years of commercial delivery: supervised robotaxi trials around the world in 2026 and consumer vehicle sales from 2027. Thank you to the incredible Wayve team for making this all possible. Check out all details here:

91,679 views • 6 months ago

We had an unbelievable demo at CES. Wayve drove autonomously in Las Vegas zero-shot — no prior training on the city, no disengagements all week. We brought three vehicles from our Silicon Valley fleet to Vegas. Despite driving in 500 cities last year, our AI had never seen Las Vegas before. Guests chose their own routes across urban streets and highways, and the system performed flawlessly. I was there for 24 hours and saw: * Confident lane changes to overtake slower traffic * Correct handling of a blinking yellow left turn (not used in California) * Robust navigation through frequent roadworks * Seamless compliance with traffic marshals' hand signals directing vehicles leaving the convention center — my favourite moment in the video below! More evidence our AI can drive any vehicle, anywhere.

We had an unbelievable demo at CES. Wayve drove autonomously in Las Vegas zero-shot — no prior training on the city, no disengagements all week. We brought three vehicles from our Silicon Valley fleet to Vegas. Despite driving in 500 cities last year, our AI had never seen Las Vegas before. Guests chose their own routes across urban streets and highways, and the system performed flawlessly. I was there for 24 hours and saw: * Confident lane changes to overtake slower traffic * Correct handling of a blinking yellow left turn (not used in California) * Robust navigation through frequent roadworks * Seamless compliance with traffic marshals' hand signals directing vehicles leaving the convention center — my favourite moment in the video below! More evidence our AI can drive any vehicle, anywhere.

80,036 views • 8 months ago

Day 4, video #4. This hour-long, zero-shot autonomy video is a route I've done many times: from our London HQ to Heathrow 🇬🇧 Starting in London forced us to build autonomy that could scale. Compared to SF, London has 10x more cyclists, 15x more pedestrians and 20x more roadworks. This is what we've built at Wayve. Check it out!

Day 4, video #4. This hour-long, zero-shot autonomy video is a route I've done many times: from our London HQ to Heathrow 🇬🇧 Starting in London forced us to build autonomy that could scale. Compared to SF, London has 10x more cyclists, 15x more pedestrians and 20x more roadworks. This is what we've built at Wayve. Check it out!

54,578 views • 5 months 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.

68,160 views • 10 months ago

Here's my favourite scenario from autonomous driving in Tokyo last week! 🇯🇵

Here's my favourite scenario from autonomous driving in Tokyo last week! 🇯🇵

87,399 views • 1 year ago

Language is the future for how we interact with robots. Today Wayve is sharing a first look at LINGO-1, a new vision-language-action AI model. To give you a glimpse of its capabilities, here is a video of me playing with LINGO-1 yesterday morning.

Language is the future for how we interact with robots. Today Wayve is sharing a first look at LINGO-1, a new vision-language-action AI model. To give you a glimpse of its capabilities, here is a video of me playing with LINGO-1 yesterday morning.

154,803 views • 3 years 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.

24,594 views • 6 months ago

Exciting to see how far the industry has come since we gave our first end-to-end AI driving demo a decade ago. But what matters now is scaled deployment. Every day this week we are releasing a new hour long video of zero shot driving all around the world 🌏 To start #1 this video is in San Jose, California. We're here for NVIDIA GTC and offering demo drives all week through the city and surrounding freeways. Book a ride here: This week we're also unveiling more details about our Nissan Motor Leaf robotaxi we're building on NVIDIA DRIVE Hyperion platform. We'll launch supervised trials in Tokyo with Uber later this year. It has already been a busy week - today I was live on the main stream right before Jensen's keynote. Join me tomorrow for my keynote at 9am PT in person or live streamed here: 📢

Exciting to see how far the industry has come since we gave our first end-to-end AI driving demo a decade ago. But what matters now is scaled deployment. Every day this week we are releasing a new hour long video of zero shot driving all around the world 🌏 To start #1 this video is in San Jose, California. We're here for NVIDIA GTC and offering demo drives all week through the city and surrounding freeways. Book a ride here: This week we're also unveiling more details about our Nissan Motor Leaf robotaxi we're building on NVIDIA DRIVE Hyperion platform. We'll launch supervised trials in Tokyo with Uber later this year. It has already been a busy week - today I was live on the main stream right before Jensen's keynote. Join me tomorrow for my keynote at 9am PT in person or live streamed here: 📢

22,960 views • 6 months ago

🤯 Incredible to see Wayve Embodied AI generalise to new environments. Here's a clip from my autonomous drive last week in Stuttgart, Germany 🇩🇪 2:18 thru a tunnel, 8:45 reading German lane markings for navigation, 12:30 busy traffic, 17:30 overtaking double parked vehicles

🤯 Incredible to see Wayve Embodied AI generalise to new environments. Here's a clip from my autonomous drive last week in Stuttgart, Germany 🇩🇪 2:18 thru a tunnel, 8:45 reading German lane markings for navigation, 12:30 busy traffic, 17:30 overtaking double parked vehicles

34,353 views • 1 year ago

Simulation provides the ability to unlock autonomy at scale. Our new blog shows how multi-agent reinforcement learning allows us to populate our Wayve Infinity Simulator with the emergent behaviour critical to represent dynamic urban cities in the real world.

Simulation provides the ability to unlock autonomy at scale. Our new blog shows how multi-agent reinforcement learning allows us to populate our Wayve Infinity Simulator with the emergent behaviour critical to represent dynamic urban cities in the real world.

66,941 views • 3 years ago

Day 3, video #3. Every day this week we are releasing a new hour-long, zero-shot autonomous drive from a new country around the world. Do you recognise this location? It is Japan! 🇯🇵 Yokohama in wet conditions from highways to tight, bustling urban roads. Check it out!

Day 3, video #3. Every day this week we are releasing a new hour-long, zero-shot autonomous drive from a new country around the world. Do you recognise this location? It is Japan! 🇯🇵 Yokohama in wet conditions from highways to tight, bustling urban roads. Check it out!

13,096 views • 5 months ago

2025 was a defining year for Wayve. We founded Wayve on the belief that embodied intelligence would unlock autonomy at scale. After eight years of pioneering deep tech research, this year marked a true inflection where Wayve became global and commercial. Wayve went global 🌍 * A year ago we were just driving in central London. In 2025 we drove autonomously in 500+ cities across Europe, Asia, and North America — 43% with zero prior training data, showcasing the generalisation of AV2.0 * Expanded operations across London, Silicon Valley, Tokyo, Vancouver, Tel Aviv, and Stuttgart, welcoming exceptional talent and partnering with the world’s leading automotive manufacturers Wayve went commercial 🚗 * Started work with global fleets and automakers to deploy our AI Driver in applications across all levels L1–L5 autonomy * Announced a landmark deal with Nissan, one of the largest global automakers, to bring our AI Driver to their global consumer vehicles from FY2027 * Partnered with Uber to launch robotaxis on their marketplace in cities around the world, starting in London Grateful to our team, investors, and partners for making this possible. Bring on 2026!

2025 was a defining year for Wayve. We founded Wayve on the belief that embodied intelligence would unlock autonomy at scale. After eight years of pioneering deep tech research, this year marked a true inflection where Wayve became global and commercial. Wayve went global 🌍 * A year ago we were just driving in central London. In 2025 we drove autonomously in 500+ cities across Europe, Asia, and North America — 43% with zero prior training data, showcasing the generalisation of AV2.0 * Expanded operations across London, Silicon Valley, Tokyo, Vancouver, Tel Aviv, and Stuttgart, welcoming exceptional talent and partnering with the world’s leading automotive manufacturers Wayve went commercial 🚗 * Started work with global fleets and automakers to deploy our AI Driver in applications across all levels L1–L5 autonomy * Announced a landmark deal with Nissan, one of the largest global automakers, to bring our AI Driver to their global consumer vehicles from FY2027 * Partnered with Uber to launch robotaxis on their marketplace in cities around the world, starting in London Grateful to our team, investors, and partners for making this possible. Bring on 2026!

16,724 views • 8 months ago