• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Generalist's Gen 1.5 is said to learn a new task from a single demonstration

    The Change Agents host describes a robot using a banana instead of a brush to sweep a cube into a bowl.

    2 Sources, 3h ago, first seen 3h ago

    TLDR

    The host of Greylock's Change Agents says Generalist CEO Pete Florence compares Gen 1.5's single-demonstration learning to GPT-3's moment for language. She describes a robot substituting a banana for a brush; when given a dustpan, it used both hands to move a cube into a bowl. She says neither behavior was explicitly trained. The discussion also covers adapting models to new robot hands and using customer feedback to guide Generalist's research.

    Combined views

    —

    2 Sources, first seen 3h ago

    Combined views

    —

    2 Sources, first seen 3h ago

    — likes
    — likes
    — comments
    — saves
    — reposts
    — comments
    — saves
    — reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Corinne Marie Riley@CorinneMRileyFeels like every week in robotics there’s a new ‘this is the GPT-3 moment for robotics 🤖’ announcement. We brought on @GeneralistAI CEO & Co-Founder @peteflorence on @GreylockVC Change Agents to dig into what’s going on at the frontier of robotics models. We covered the company’s latest Gen 1.5 model, few-shot learning, training robots on different embodiments, and the milestones towards a more generalized physical model. Timestamps: 00:51 The inception of Generalist 04:13 Long-term goal of the company 05:47 Parallels and differences between robotics and language models 12:05 Key differentiation in 1.5 Gen model 12:48 Robot vs banana 14:49 Emergent capabilities not explicitly trained for 17:13 Cross-embodiment and the importance of hands 22:26 Research vs working with customers 24:58 Beyond VLA vs world model 28:50 Future-looking milestones Some of the top takeaways: - One-shot and few-shot learning emerged without being trained for. Gen 1.5 can learn a new task from a single demonstration, and Pete compares it to the GPT-3 moment in language. In one example, a robot taught to sweep a cube into a bowl with a brush used a banana instead. Given a dustpan, it held the pan with one hand, swept with the other, then tipped the cube into the bowl. Neither behavior was explicitly trained, and Pete sees this as a signal of where the model's generalization is headed. -Generalizing to new hands remains a challenging problem for cross-embodiment. Physical hardware doesn’t stay static, and so cross-embodiment - the ability of a physical AI model to adapt to different hardware systems - is vital for success. -Customer deployments are a valuable source of research inputs. Generalist actively partners with their customers for feedback, which they use to inform their research and make real-world evaluations. -Generalist doesn't think in terms of "VLA vs. world model." Pete helped create early VLAs and has worked on world models, but he argues the goals matter more than the label, and the team is trained to think in a first-principled way when considering new research directions. Watch the full episode at the link in the comments. Thank you to @peteflorence for joining us!3h
    Greylock Partners@GreylockVCRT @CorinneMRiley: Feels like every week in robotics there’s a new ‘this is the GPT-3 moment for robotics 🤖’ announcement. We brought on…2h

    2 Sources

    Corinne Marie Riley@CorinneMRileyFeels like every week in robotics there’s a new ‘this is the GPT-3 moment for robotics 🤖’ announcement. We brought on @GeneralistAI CEO & Co-Founder @peteflorence on @GreylockVC Change Agents to dig into what’s going on at the frontier of robotics models. We covered the company’s latest Gen 1.5 model, few-shot learning, training robots on different embodiments, and the milestones towards a more generalized physical model. Timestamps: 00:51 The inception of Generalist 04:13 Long-term goal of the company 05:47 Parallels and differences between robotics and language models 12:05 Key differentiation in 1.5 Gen model 12:48 Robot vs banana 14:49 Emergent capabilities not explicitly trained for 17:13 Cross-embodiment and the importance of hands 22:26 Research vs working with customers 24:58 Beyond VLA vs world model 28:50 Future-looking milestones Some of the top takeaways: - One-shot and few-shot learning emerged without being trained for. Gen 1.5 can learn a new task from a single demonstration, and Pete compares it to the GPT-3 moment in language. In one example, a robot taught to sweep a cube into a bowl with a brush used a banana instead. Given a dustpan, it held the pan with one hand, swept with the other, then tipped the cube into the bowl. Neither behavior was explicitly trained, and Pete sees this as a signal of where the model's generalization is headed. -Generalizing to new hands remains a challenging problem for cross-embodiment. Physical hardware doesn’t stay static, and so cross-embodiment - the ability of a physical AI model to adapt to different hardware systems - is vital for success. -Customer deployments are a valuable source of research inputs. Generalist actively partners with their customers for feedback, which they use to inform their research and make real-world evaluations. -Generalist doesn't think in terms of "VLA vs. world model." Pete helped create early VLAs and has worked on world models, but he argues the goals matter more than the label, and the team is trained to think in a first-principled way when considering new research directions. Watch the full episode at the link in the comments. Thank you to @peteflorence for joining us!3h
    Greylock Partners@GreylockVCRT @CorinneMRiley: Feels like every week in robotics there’s a new ‘this is the GPT-3 moment for robotics 🤖’ announcement. We brought on…2h