Robots Just Had Their GPT-3 Moment - YouTube :: www.youtube.com/

Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.

In-context learning for robots has been a long-anticipated capability, as it could allow robots to quickly adapt to new tasks without additional training, and Gen-1.5 might have just demonstrated that it is possible for robots at complex tasks. Gen-1.5 [Blog] https://generalistai.com/blog/gen-1.5 my latest project: Intuitive AI Academy We just wrote a new piece on Linear Attention!! https://intuitiveai.academy/ limited time code "BACK2SCHOOL" for 50% off yearly plan My Newsletter (weekly top research papers) https://mail.bycloud.ai/ My Patreon https://www.patreon.com/c/bycloud Try…

saved by

• Lingfei Tang

related reading

• GEN-1.5: Embodied Foundation Models are One-Shot Learners - Generalist AIgeneralistai.com
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• Generalist - GEN-1: Scaling Embodied Foundation Models to Masterygeneralistai.com
• The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
• A Steerable Model with Emergent Capabilitiespi.website
• how we accidentally solved robotics by watching 1 million hours of YouTube – atharva's blogksagar.bearblog.dev
• How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
• How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
• All Roads Lead to Robotics | Eric Jangevjang.com
• The ‘ChatGPT Moment’ in Robotics and beyondparitoshmohan.substack.com
• Frontier of General-Purpose Robotics (2025)adampatni.com
• GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com