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

    Skild AI Shows S1 Model Learning 10-Minute Tasks From One Video

    The foundation model performs unseen long-horizon tasks through in-context learning.

    DP
    RS
    SM
    36 Sources, 36d ago, first seen 36d ago

    TLDR

    Skild AI posted that its S1 model learns tasks over 10 minutes long from one video prompt. The tasks were never seen during pre-training and require no fine-tuning. Founder Deepak Pathak described the approach as building intelligence from the foundations up. Sequoia Capital investors called the work impressive and a potential game changer. Company researcher Roozbeh Mottaghi noted the absence of test-task leakage and the focus on extended sequences. Other observers labeled the release the GPT moment for robotics.

    Combined views

    633.2K

    36 Sources, first seen 36d ago

    Combined views

    633.2K

    36 Sources, first seen 36d ago

    3.7K likes
    3.7K likes
    117 comments
    1.1K saves
    411 reposts

    Sentiment

    Positive84.1%15.9%Negative

    Based on 69 sentiment-bearing replies from 63 accounts across 7 conversations.

    Featured Source
    117 comments
    1.1K saves
    411 reposts

    Sentiment

    Positive84.1%15.9%Negative

    Based on 69 sentiment-bearing replies from 63 accounts across 7 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    36 Sources

    @deepakpathakIn-context learning for robotics is here. - Long-horizon tasks over 10 minutes long - Never seen during pre-training - Prompted with one video, no fine-tuning We are building intelligence from the foundations up, not from the top down.
    @gradypbincredible moment for robotics
    @JulienBekChatGPT moment for robotics
    @Alfred_LinWhile robot olympics may get more media headlines, these types of advancements are really what change the game for robotics. Very impressive work on turning single prompts into long-horizon tasks that robots can then execute independently.
    @sequoiaRT @SkildAI: Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has neve…
    @brianzhan1This is the first genuine ChatGPT moment in robotics. I head they are already in production?!
    @ScobleizerThey wanted to pay me to write this post, and I turned them down. Why? Because I wanted to be able to say, without any prejudice: this is a step forward for robotics. Hopefully, I can get them to sponsor something else in the future.
    @chris_j_paxtonThis is the mark of a general purpose robot foundation model -- that it can be taught tasks from examples without training. We saw an early version of this from rhoda and a solid one last week from generalist, and now a really impressive, ten minute long one from skild. This to me does feel like the true gpt moment for robotics -- because if it truly generalizes, that means that you can really start deploying robots for anything, as developing robot skills becomes like prompting
    @gschw1ndSo amazing to see such impressive signs of robotic in-context learning. For the first time it really feels like a truly intelligent policy! Getting to see the wide span of diverse tasks S1 is able to complete is truly gobsmacking. I hope everyone, even if you’re not in the field, gets a chance to read through the blogpost to get a sense of truly how difficult of a feat this is!!
    @jesskahWho knew the ChatGPT moment of robotics would involve pancakes. @SkildAI @gupta_abhinav_ @deepakpathak we should host a US robot olympics where the robots cook brunch and do household tasks.

    36 Sources

    @deepakpathakIn-context learning for robotics is here. - Long-horizon tasks over 10 minutes long - Never seen during pre-training - Prompted with one video, no fine-tuning We are building intelligence from the foundations up, not from the top down.
    @gradypbincredible moment for robotics
    @JulienBekChatGPT moment for robotics
    @Alfred_LinWhile robot olympics may get more media headlines, these types of advancements are really what change the game for robotics. Very impressive work on turning single prompts into long-horizon tasks that robots can then execute independently.
    @sequoiaRT @SkildAI: Introducing S1, our new foundation model that learns from one example. It can be taught 10-minute long tasks that it has neve…
    @brianzhan1This is the first genuine ChatGPT moment in robotics. I head they are already in production?!
    @ScobleizerThey wanted to pay me to write this post, and I turned them down. Why? Because I wanted to be able to say, without any prejudice: this is a step forward for robotics. Hopefully, I can get them to sponsor something else in the future.
    @chris_j_paxtonThis is the mark of a general purpose robot foundation model -- that it can be taught tasks from examples without training. We saw an early version of this from rhoda and a solid one last week from generalist, and now a really impressive, ten minute long one from skild. This to me does feel like the true gpt moment for robotics -- because if it truly generalizes, that means that you can really start deploying robots for anything, as developing robot skills becomes like prompting
    @gschw1ndSo amazing to see such impressive signs of robotic in-context learning. For the first time it really feels like a truly intelligent policy! Getting to see the wide span of diverse tasks S1 is able to complete is truly gobsmacking. I hope everyone, even if you’re not in the field, gets a chance to read through the blogpost to get a sense of truly how difficult of a feat this is!!
    @jesskahWho knew the ChatGPT moment of robotics would involve pancakes. @SkildAI @gupta_abhinav_ @deepakpathak we should host a US robot olympics where the robots cook brunch and do household tasks.