What is Runway and how is it shaping the future of AI video? In this conversation, Premji Invest sits down with Cris Valenzuela, Co-Founder and CEO of Runway, to discuss how generative AI is transforming video creation, simulation, and world modeling.
Runway is a leading AI research and product company building state-of-the-art video generation and simulation models. In this interview, Cris shares how Runway’s original vision, formed in 2018, has remained consistent as AI video has gone mainstream, and how advances in compute, data, and model design led to breakthroughs like Gen-4.5, one of t...
What Cristóbal Valenzuela said
Written from the verified transcript and checked against it. Every figure links to the moment it was said.
Cristóbal Valenzuela, CEO and co-founder of Runway, said the company's vision has not changed since its founding seven years ago: using deep learning and AI as the backbone to generate and simulate anything, now moving from text tokens to frames, world understanding, and physics. He attributed Runway's progress from Gen-1 to Gen-4.5 to algorithmic improvements, better data curation, and increased compute, plus what he called 'research taste.' He said Gen-4.5 excels at prompt adherence, allowing complex scenes and camera movements, with realistic physics. Valenzuela argued video models will become the foundation for simulation, including personalized learning experiences and computer interfaces. On data, he said video data is not fully consumed and synthetic data is being explored. He described AI as a great equalizer, with users ranging from a 9-year-old in Peru to filmmakers in LA and Japan. He said Runway wins despite fewer resources due to consistent vision and execution.
Key takeaways
Runway's vision has remained unchanged for 7 years: using AI to generate and simulate anything, now moving from text to video frames and physics.
Gen-4.5 excels at prompt adherence, enabling complex scenes, camera movements, and realistic physics.
Runway is exploring synthetic data but believes video data has not been fully consumed.
Valenzuela said Runway wins against larger competitors due to consistent vision and execution, not resources.
0:34So would love to understand sort of what problem did you see back in 2018 that convinced you that the world needed Runway and how that original thesis has evolved as AI video generation has gone mainstream?
5:28As you think about us hitting the limits on what data we can collect, do you think we have to move towards synthetic data, or how does the data collection process evolve?
7:16How do you guys continue to stay at the top of those leaderboards? Right?
AI is like a great equalizer and it can allow anyone with access to the internet to use state-of-the-art technologies that weren't really imaginable just a couple of years ago.
Chris, thanks a lot for taking the time. Excited to be doing this podcast with you and Premji Invest is very excited to be partnered with you all. Would love to start with just the genesis of Runway. So would love to understand sort of what problem did you see back in 2018 that convinced you that the world needed Runway and how that original thesis has evolved as AI video generation has gone mainstream?
The vision of Runway hasn't really changed since we started the company 7 years ago, which is a very remarkable thing. And the vision back then and more of a problem that we saw — I think we saw an opportunity — which is neural networks and deep learning was starting to work really well across different modalities. We started to see really good progress in both captioning and video understanding and computer vision. And our, I guess, opportunity that we saw back then was, and it still is, the opportunity that we see right now is using the advantages and the progress of deep learning and AI as the backbone on which you basically generate and simulate anything you want. We're starting with the basic. We started with text first. I think the last couple of years have been very good for language models. But now is the era of video. We're moving beyond just tokens for text and we're moving to frames, to world understanding, to physics. And so the vision of the company has been the same. It's this idea that you can take these models. If you train them well enough, if you scale them well enough, they're going to start solving all these problems, sort of opportunities around creating, simulating, generating content. And now we're getting to the point where it's actually working pretty well.
So Chris, what I think we'd love to understand maybe the evolution of Runway from Gen-1 to Gen-2 to Gen-3 and now Gen-4.5 which is really just blown us away. What has changed under the hood?
That's a good question. I think there's a couple of nature changes that we have seen over time. There's first of all algorithmic improvements and changes on the way we train the models. The second one is the data has been improved significantly. There's better ways of annotating, there's more data sources. We've also gotten better at kind of selecting and curating what and how you train the models. And then we say the third and most important perhaps is compute. We've gotten more compute, and I mean, it's Runway of course, but also the industry at large has gotten much better at building infrastructure that's needed to scale these models. The additional aspect that I would say of how we particularly have gotten to create the best model in the world right now with as you were saying Gen-4.5 is by, I would say, having a lot of good research taste. And taste doesn't come in the form of aesthetics or styles, although that definitely involves, but I think it's mostly about what problems do you want to solve and why those problems are important and how you solve them.
Maybe you can just help the audience understand a little bit what are some of the new features that you have in Gen-4.5 that you couldn't do before. For example, some of the realistic physics that I've seen or just unbelievable.
9 more exchanges in this transcript
Sign in free to read the rest of this interview. No card required.
Valenzuela, C. (2026, July 7). CEO Series | Runway | A new frontier for video generation [Interview transcript]. Premji Invest US. CEOInterviews.AI. https://ceointerviews.ai/interview/1083677/
MLA
Cristóbal Valenzuela. "CEO Series | Runway | A new frontier for video generation." Premji Invest US, 7 Jul. 2026. Transcript, CEOInterviews.AI, https://ceointerviews.ai/interview/1083677/.
BibTeX
@misc{valenzuela2026_1083677,
author = {Cristóbal Valenzuela},
title = {CEO Series | Runway | A new frontier for video generation},
howpublished = {Interview transcript, Premji Invest US. CEOInterviews.AI},
year = {2026},
month = {jul},
url = {https://ceointerviews.ai/interview/1083677/},
note = {Speaker-attributed transcript with timestamps}
}
