00:02:56 · Brandon Basso, Ruby Justice Thelot
[00:02:56] S0: Yeah. So, I mean, let's start today with the status quo. The status quo today for driving is not great. It is, a very risky thing that we do. It's costly in terms of time, but also just insurance costs for minor accidents. And then, you know, we don't even need to motivate the the major safety challenges and the populations affected by vehicular accidents in The United States everywhere throughout the world. So it is, I think, incumbent upon us as engineers, as scientists, as product managers, researchers, to think about how we improve all of those problems. So it kinda is one of those things that really, I think, needs no motivation, And why it's such an intent focus for Wayve, well, I mean, it's a focus of every self driving car company out there, whether you're working on l two or l four. We have this novel approach to self driving that we refer to as AV two point o or end to end systems, And there hasn't been a lot of rigorous thinking yet about how we prove the safety of those systems. It's exactly the same problem that folks at Anthropic and OpenAI think about when they are thinking about frontier safety. How do they prove that what the model is outputting is correct performance, not going to mislead you, not going to deceive you, aligned with human expectations. It's the same problem, but the physical interpretation of it. [00:04:18] S1: So there isn't this golden North Star benchmark for what this means. What does that look like when you're trying to innovate at the frontier to define what safety means?
00:04:18 · Ruby Justice Thelot, Brandon Basso
[00:04:18] S1: So there isn't this golden North Star benchmark for what this means. What does that look like when you're trying to innovate at the frontier to define what safety means? [00:04:29] S0: Yeah. So many things. So we we break it down into four core concepts. So safety, of course, has to do with the safety of road users outside of the car, but also the people in the car. There's a comfort element, which is sometimes safety related or adjacent. You know, if you're heartbreaking or swerving or things like that, doing uncomfortable things, sometimes those are precursors of safety. Honestly, equally important is compliance. So there is a dizzying array of traffic rules throughout the world. How you behave with certain signs in Japan versus in Germany is quite different. [00:05:06] S1: Because you're doing London and all across
00:05:06 · Ruby Justice Thelot, Brandon Basso
[00:05:06] S1: Because you're doing London and all across [00:05:08] S0: the city. Literally everywhere. Literally... Quite literally everywhere. When we're operating like we've done with our road show last year in the Arctic Circle or just around the world, it's it's crazy how different it is. And regulators and our customers expect that we're performing safely, comfortably, compliantly, and competently. Meaning that when you ask the car to do a lane change, it does it in a way that people expect. Now your question is, well, how do we grade all those things? And that is the challenge, and there's no one answer. There's no one metric just in the way that you go to any AI leaderboard today. There's a ton of different metrics, but we try our very best to make sure that those metrics are aligned with human expectation, our expectation when we say what it means for a driver to be safe. [00:05:55] S1: Yeah. Something you alluded to at the start of our conversation is you mentioned a tough piece is gathering enough data to train how... These cars to drive autonomously. Famously, even a decade ago, I remember I grew up here in the Bay Area, and you would see the people inside the Waymo cars just gathering data about what's happening on the streets. Where are we now? What's different about 2026 about how we gather all the simulation data?
00:06:21 · Brandon Basso
[00:06:21] S0: Yeah. Absolutely. So one of the core advantages, and I I would say core aspects of Wayve's approach going back to a decade ago, is we very much recognize both the driving problem and the validation problem as a data problem, and we secured all sorts of interesting diverse data early on. We did this roadshow campaign where we drove well north of... I I forget if it's the Arctic Circle or not, so I'm not geography expert, where it was very cold, and collected diverse data. And that is so critical because our system is fundamentally one that gets better with data just like any frontier LLM today. And people in robotics, general robotics will tell you this. There is no general dataset for robotics today, for physical AI. There's no general dataset like there is for language. You know, humans have developed all this language data throughout the years, books and, you know, videos and stuff. And we don't have a corpus yet of driving data, so we work very hard on collecting that. That's both our first party collection, purchasing data going back to ten years ago, and then partnering with our fantastic OEM partners and working with them on getting the data so that we can deliver back to them the best the best products.
00:07:34 · Ruby Justice Thelot, Brandon Basso
Ad[00:07:34] S1: I wanna shout out our sponsor, Lovable. You know that app you've been meaning to build? The internal tool, side project, or product you'd otherwise lose a weekend to? With Lovable, you get software you can ship today. That includes an editable code base you can inspect and change, plus two way GitHub sync. Lovable also handles the backend and infrastructure, including managed Postgres, auth, storage, hosting, payments, and more, so you don't have to wire it all up yourself. And through Lovable's MCP server, you can create and deploy your project directly from the agents you already use. Turn ideas into software people love with Lovable, lovable. Dev. Now onto the episode. So I know today during our interview, you brought along a demo. Ad[00:08:18] S0: Tons of demos. [00:08:19] S1: Tell us a little bit about what this demo is supposed to be. [00:08:22] S0: Yeah. Let's talk about demos. Let's talk about data. So I'm gonna jump to to one to just highlight that last point. This is in Mhmm. The center blog, the validation blog. So we'll come back to some of these videos. But just speaking to the diversity Yeah. Here is a very simple scene that you can see anywhere in the world, and it's behave... It's stopping at a stoplight. Now the way that those stoplights look in The US and Germany is slightly different. The nuance behavior for how far you might stop behind a stop line is not only geography dependent, but it's also local rules dependent style [00:09:00] S1: You know, they say it is a California stop compared to
00:09:00 · Ruby Justice Thelot, Brandon Basso
[00:09:00] S1: You know, they say it is a California stop compared to [00:09:03] S0: Yeah. And this really gets back to sort of the the overall thrust of what we're putting out there and we're trying to say, which is there... It is literally impossible to write rules for how this should work. We didn't learn to drive by digesting... We digested a... Well, it depends on where you grew up. But we digested a rules book that said, okay, here's the driver test, and we took it. But ever since then, when we were 16 or 14 or whatever, we've learned, we've extrapolated from those rules. We've taken trips to countries where you drive on the other side of the road road, and we've become better drivers. And that's exactly how we view the driving problem for Wayve. I wanna highlight one other great example in here where... I think it might be in the first post. Here we go. Okay. So this this example is about many things, but I just wanna highlight one thing that is kind of a little bit different, but also a little bit Yeah. The same throughout the world, which is construction scenes. So I think when you look at these scenes, you probably have a sense of what to do from just looking at the image. Okay. It's like there's [00:10:09] S1: a light of a driver. So, honestly, I look at these scenes. I'm like, thank god I'm not driving in London or Japan right now. Well,