Uploaded July 2026 | Updated September 2026, 2 weeks ago

---

Rhoda AI is betting the future of robotics starts with internet video, not lab data. We visited the company’s headquarters to see how its Direct Video Action model learns physics from hundreds of millions of clips.


0:00 Introduction: Training Robots via Video
0:41 The Direct Video Action (DVA) Model
1:20 Where Does the Training Data Come From?
1:50 Demo: Complex Decanting and Sorting Tasks
2:35 Inspecting and Organizing Parts
2:51 Real-Time Adaptability Test
3:38 Predicting the Future: Reasoning and Scoring
4:02 Industry Partners and Future Outlook

Add CNET as a trusted news source google.com/preferences/source?q=cnet.com
Never miss a deal again! See CNET’s browser extension 👉 bit.ly/3lO7sOU
Check out CNET’s Amazon Storefront: amazon.com/shop/cnet
Subscribe to CNET on YouTube: youtube.com/cnet
Follow us on TikTok: tiktok.com/@cnetdotcom
Follow us on Instagram: instagram.com/cnet
Follow us on Bluesky: https://bsky.app/profile/cnet.com
Like us on Facebook: facebook.com/cnet
CNET's AI Atlas: cnet.com/ai-atlas
Follow us on X: x.com/cnet
Visit CNET.com: cnet.com

#Robot #AI #WTF