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

    Perceptron Shares Isaac 0.5 Tic-Tac-Toe Adaptation Post

    Retweet from Perceptron AI co-founder highlights Isaac 0.5 tic-tac-toe demo.

    AA
    PA
    5 Sources, 29d ago, first seen 29d ago

    TLDR

    Armen Aghajanyan, co-founder and CEO of Perceptron AI, retweeted a post from @perceptroninc. The post states that Isaac 0.5 plays tic-tac-toe while adapting to small changes in board placement and new game states. The tweet presents this as a demonstration of the model's behavior in a physical or simulated environment. No further details on release status, technical specifications, or independent verification appear in the packet. The account describes Perceptron as focused on physical AI and multimodal models.

    Combined views

    17.3K

    5 Sources, first seen 29d ago

    Combined views

    17.3K

    5 Sources, first seen 29d ago

    159 likes
    159 likes
    11 comments
    75 saves
    48 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    11 comments
    75 saves
    48 reposts

    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

    5 Sources

    @ArmenAghaRT @perceptroninc: Isaac 0.5 plays tic tac toe, adapting to small perturbations in game environment (i.e., board placement) and new game st…
    @perceptronincIsaac 0.5 learns new embodiments efficiently. Trained on 1M hours of video and 100K hours of robotic interaction data, Isaac adapts to 35+ embodiments. YAM and SO-101 checkpoints coming soon. Read more: https://www.perceptron.inc/blog/introducing-isaac-0-5 Download weights: https://huggingface.co/PerceptronAI/Isaac-0.5

    5 Sources

    @ArmenAghaRT @perceptroninc: Isaac 0.5 plays tic tac toe, adapting to small perturbations in game environment (i.e., board placement) and new game st…
    @perceptronincIsaac 0.5 learns new embodiments efficiently. Trained on 1M hours of video and 100K hours of robotic interaction data, Isaac adapts to 35+ embodiments. YAM and SO-101 checkpoints coming soon. Read more: https://www.perceptron.inc/blog/introducing-isaac-0-5 Download weights: https://huggingface.co/PerceptronAI/Isaac-0.5