00:13:00 · Adam Miller, Anastasis Germanidis
[00:13:00] S0: And for the future vision, do you see a world in maybe a few years' time, five years' time, where people will be making major movies just with products like Runway, doing all the scripting in there and having all the generation of many different frames in there, doing the post in there and we'll be able to go to the cinema and watch a movie made on Runway. [00:13:19] S2: I hope so. Think that's definitely like I don't see any reason why it won't happen like if you look at the improvement of the models and the ability to generate kind of longer and longer sequences the ability to keep consistency of, you know, character settings, environments, I think the... It's it's very likely that, you know, you'd be able to... And you... Already, we have a large community of of filmmakers that are that are using Runway to make to make films, less so feature length films at this point, but there is no fundamental reason where the models are not gonna improve and get there. [00:13:55] S0: And under that world, if we are making fully AI generated films, those films aren't going to need, you know, the hundreds, sometimes thousands of people which are needed to make films now, so do you think what will offset that is that we'll just be making far more films into the future so that there'll be so many more creators, more films being made, and on net, we just have more artists.
00:13:55 · Adam Miller, Anastasis Germanidis, Sachin
[00:13:55] S0: And under that world, if we are making fully AI generated films, those films aren't going to need, you know, the hundreds, sometimes thousands of people which are needed to make films now, so do you think what will offset that is that we'll just be making far more films into the future so that there'll be so many more creators, more films being made, and on net, we just have more artists. [00:14:14] S2: There are roughly, like, thousands of films being released every year and millions of books being published. Like, why does that gap exist? Because it's so hard and so, you know, resource intensive to make a film. So it's exactly what you said that the the number of... We're we're more bottlenecked by supply than demand. There is, I think, a lot more latent demand to watch amazing stories that are not being told. And so I think that's what we're gonna see, that we're gonna see way more way more films in the in the world and then way more new kinds of experiences that are powered by those models. [00:14:47] S1: At the kind of deepest level, I'm sure there's been many times over the last few years where it felt impossible or it felt like you may not get there. What is the thing that has kept you going? Like, what is the world you wanna see with Runway that has kept you going? Because it seems like you're quite a philosophical person. So, know, what what is that kind of vision?
00:14:47 · Sachin, Anastasis Germanidis
[00:14:47] S1: At the kind of deepest level, I'm sure there's been many times over the last few years where it felt impossible or it felt like you may not get there. What is the thing that has kept you going? Like, what is the world you wanna see with Runway that has kept you going? Because it seems like you're quite a philosophical person. So, know, what what is that kind of vision? [00:15:06] S2: The vision is so there's a lot of things that are very motivating internally as we you know it's building those models is difficult as you're saying and it requires a lot of iteration and a lot of false starts and and challenges. I think one thing that is always motivating for the team is like the, you know, the outputs of your work are empowering people to make really really compelling amazing stories And I think that's always, like, a big part of, like, what makes Runway a very motivating place to to work is that you you get to see, like, the fruits of of your work be... Be... Being translated into films, which is quite amazing. I think we're very inspired by this idea of simulating the world, of essentially being able to build models that can deeply understand and help us solve real world problems. And that's a broader application from storytelling, which is our core. We think those models are far more powerful and they can... The the ability to, as we scale those models, are gonna be useful kind of beyond film, beyond kind of storytelling and towards solving real world problems.
00:15:06 · Anastasis Germanidis, Adam Miller
[00:15:06] S2: The vision is so there's a lot of things that are very motivating internally as we you know it's building those models is difficult as you're saying and it requires a lot of iteration and a lot of false starts and and challenges. I think one thing that is always motivating for the team is like the, you know, the outputs of your work are empowering people to make really really compelling amazing stories And I think that's always, like, a big part of, like, what makes Runway a very motivating place to to work is that you you get to see, like, the fruits of of your work be... Be... Being translated into films, which is quite amazing. I think we're very inspired by this idea of simulating the world, of essentially being able to build models that can deeply understand and help us solve real world problems. And that's a broader application from storytelling, which is our core. We think those models are far more powerful and they can... The the ability to, as we scale those models, are gonna be useful kind of beyond film, beyond kind of storytelling and towards solving real world problems. [00:16:25] S0: On that last point, you are talking a lot about world models these days. Silicon Valley is also talking a lot about that and companies are raising huge seed rounds for them. Could you explain from your perspective what a world model actually is and how Runway are going to be utilising them and just sort of juxtapose them against the sort of previous generations of models that you've built.
00:16:25 · Adam Miller, Anastasis Germanidis
[00:16:25] S0: On that last point, you are talking a lot about world models these days. Silicon Valley is also talking a lot about that and companies are raising huge seed rounds for them. Could you explain from your perspective what a world model actually is and how Runway are going to be utilising them and just sort of juxtapose them against the sort of previous generations of models that you've built. [00:16:46] S2: So, world models are systems that build representations of environment and help to predict what happens as a result of a specific action. So the biggest change from video models, so video model, you type in a prompt, you wait for a bit, you get back a full video. With a world model is interactive and that means you're continuously providing control, so you're continuously moving around in a space or you're continuously interacting with a character or you're continuously, controlling a robot arm so the ability to try different actions and see the effect and of of of the... Of your the... Your actions, that's what makes... That's the main differentiation from, from video models, which are a bit more, like, offline use of just you type in a prompt, you get a packet output, and you're not continuously influencing. [00:17:41] S0: And what would be the practical application of that for Runway? Like, how would somebody eventually engage with, a world model?
00:17:41 · Adam Miller, Anastasis Germanidis
[00:17:41] S0: And what would be the practical application of that for Runway? Like, how would somebody eventually engage with, a world model? [00:17:49] S2: So even if you take the use case of, filmmaking and storytelling and making videos, imagine the experience of essentially being on set right, and being able to continuously kind of direct the camera continuously direct the the actors in in the scene, that's that's something that's a very different experience from the experience of typing a prompt and getting back an output. It's it's something that allows for much greater degree of control. So even if we take the use cases that of, like, video generation, it's a much better experience if you actually can walk on set and just be able to direct the scene. But the the the applications are far broader than that. So if we if we take... We're very excited about how we're seeing our models already being used in physical AI and robotics. So collecting data for robotics is very, very expensive, very time consuming, very, unsafe in a little... In in in in some ways, in some domains. Being able to generate data to train robots is a big application of our models that we're very excited about. Being able to simulate how robots perform without having to test them in the real world is another application that we're seeing really promising results as well.