Building 32: Why AI Still Can't Load the Dishwasher

In this episode

When The Jetsons imagined life in 2062, Rosey the robot maid seemed like pure science fiction. Today, chatbots can answer questions, analyze data and even crack jokes. But they still can't load the dishwasher.


In this episode of Building 32, MIT CSAIL associate professor Vincent Sitzmann explains why building AI that understands and interacts with the physical world is a fundamentally different challenge. Sitzmann explains why today's AI still struggles with seemingly simple physical tasks and how researchers are teaching machines to see, predict, and interact with the world around them.


Episode Resources:
😃 Learn more about Vincent Sitzmann
🎥 And the Scene Representation Group
📖 Read the Nature article Karen referenced
🤖 Watch the Jetsons and meet Rosey
 

About the speakers

Assistant Professor, MIT EECS

Vincent Sitzmann is an Assistant Professor at MIT EECS, where he is leading the Scene Representation Group. Previously, he did his Ph.D. at Stanford University as well as a Postdoc at MIT CSAIL. His research interest lies in building models that perceive and model the world the way that humans do. Specifically, Vincent works towards models that can learn to reconstruct a rich state description of their environment, such as reconstructing its 3D structure, materials, semantics, etc. from vision. More importantly, these models should then also be able to model the impact of their own actions on that environment, i.e., learn a "mental simulator" or "world model". Vincent is particularly interested in models that can learn these skills fully self-supervised only from video and by self-directed interaction with the world.

Host of Building 32

Karen Given is an award-winning podcast showrunner, story editor and coach. A veteran of public radio, Karen is the former executive producer and host of NPR’s Only A Game. She won the national Edward R. Murrow award twice, in 2007 and 2017. Since leaving public radio, Karen has focused on the podcast space, most notably on Believable: The Coco Berthmann Story, one of The Atlantic’s top 25 podcasts of 2023. Karen’s other projects include, The Afghan Impasse, a special season of The Negotiators, from Foreign Policy and Doha Debates; Before We Go, and What Takes Root: Stories of Resistance and Reclamation. Given teaches narrative storytelling workshops and writes Narrative Beat, a free newsletter for journalists and podcast makers who want to tell better stories.