Proactive Agents for the Web with Devi Parikh - #756

We will no longer be interacting with the web in the same way that we do right now. We won't be clicking buttons, fiddling with forms on websites and browsers. We'll be interacting with the web one level higher in the abstraction where we're describing what needs to be done. Maybe our assistant is proactively noticing what needs to be done and sort of agents in the background are starting to execute these workflows, on the web on on your behalf. Alright, everyone. Welcome to another episode of the TwinWell AI podcast. I am your host, Sam Charrington. Today, I'm joined by Davey Parikh. Davey is cofounder and co CEO of Uturi. Before we get going, be sure to take a moment to hit that subscribe button wherever you're listening to today's show. Davey, it has been a while since we caught up last. Welcome back to the podcast. Thank you. Thank you for having me again. Yeah. Five years later, not much has happened at all. Right? In in some ways, a lot has happened, but in some ways, I'm like, wow. It's been five years. So yeah. I know. I know. I know. So we're going to be talking a bit about AI browsers and browser use agents, and what you're building at YouTory, but I'd love to have you take a few minutes and catch us all up on what you've been up to recently. Yeah. Yeah. And I can I can go, a little bit further back than than five years, just to talk about my background a little bit? So I've been working in AI for about twenty years now. Originally, my PhD thesis was in computer vision. And then over time, I got interested in seeing if we can find ways in which people can interact with these systems more naturally. And that's how I move towards multimodal problems at the intersection of vision and language. So things like given an image, can you describe it in a sentence? Can you answer questions about it? Can you have a conversation going back and forth, about the content of an image? And this was back in 2014 or so. So it was after that initial excitement of deep learning models, but it was starting to feel like, wait. These models are doing something. Stuff is actually starting to work. But it was well before all of the current excitement around Gen AI and other lens and so on. So these models weren't really as good, as they are today. And yeah. So it was it was kind of fun to tinker on the boundaries of of what's possible. And then I started getting interested in seeing if we can find ways in which we can use AI as a tool for creative expression. And that's how I got involved with generative models for images and videos and music and and other modalities, like that. I was in academia for a while, faculty at Virginia Tech …