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

    Odyssey-3 reportedly builds interactive worlds from prompts in real time

    A post says users can walk, jump and move the camera, with the generated environment responding as they move.

    Robert ScobleRS
    Oliver CameronOC
    SantiagoSA
    6 Sources, ,

    TLDR

    A post describes Odyssey-3 as a world model that builds an environment from a prompt and generates it in real time as users move through it. It gives examples including ripples when someone steps into water, a car rolling through a crosswalk and a beaver wading out of a lake. The post says Odyssey is adapting the same model for robot arms, humanoids and driving, and that a research preview was open on October 8, 2026.

    Combined views

    15.4K

    6 Sources, first seen 1h ago

    Combined views

    15.4K

    6 Sources, first seen 1h ago

    133 likes
    1h ago
    first seen 1h ago
    133 likes
    14 comments
    24 saves
    13 reposts
    14 comments
    24 saves
    13 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

    #8

    Today's Rank

    #8

    6 Sources

    Robert Scoble@ScobleizerRT @odysseyml: Today we're launching Odyssey-3, the most powerful foundation world model yet. It sets a new state of the art on Physics-IQ…1h
    Oliver Cameron@olivercameronVery proud that Odyssey-3 is the most physics-accurate world model in...the world!1h
    Santiago@svpinoThe #1 video-to-video model in the Physics-IQ Verified benchmark is finally live! (Their research preview is) Odyssey 3 Pro is a world model, and nobody beats it for physical accuracy. You can use this model to control a robot, drive a car, play a video game, or pilot a drone. • It takes visual observations from the world • Uses these observations to learn how things work • Then maps that knowledge to the system's physical controls1h
    rachit@rachiitgrthis is not a video generator. it's a world model odyssey-3 builds an environment from a prompt and generates it in real time as you move through it walk, jump, move the camera → the world responds ripples when you step into water. a car rolling through a crosswalk. a beaver wading out of a lake the same model is what odyssey is adapting for robot arms, humanoids and driving research preview is open, try it yourself1h
    🚨 AI News | TestingCatalog@testingcatalogOdyssey has launched Odyssey-3, its most powerful foundation world model to date, and opened a research preview to the public. Odyssey-3 builds an environment from a prompt and predicts changes in real time as a person moves through it or triggers events. > Odyssey-3 Pro scored 66.1 on Physics-IQ Verified video-to-video with best-of-8 sampling. This is the highest reported result. > Users can walk through scenes in first or third person. The camera can also move independently. > Odyssey adapted the model to robot arms, humanoids, and a car on real roads in India. Each system uses its own trained policy.1h
    Dipti Sharma@Diptish09this is probably the first world model launch in a while that made me think beyond video generation Odyssey-3 can create interactive environments from a prompt, in real time. It can model physics, dynamics and cause-and-effect from visual experience. Then you have 66.1 on Physics-IQ Verified, plus the physical AI angle. There’s a lot packed into this launch.47m

    6 Sources

    Robert Scoble@ScobleizerRT @odysseyml: Today we're launching Odyssey-3, the most powerful foundation world model yet. It sets a new state of the art on Physics-IQ…1h
    Oliver Cameron@olivercameronVery proud that Odyssey-3 is the most physics-accurate world model in...the world!1h
    Santiago@svpinoThe #1 video-to-video model in the Physics-IQ Verified benchmark is finally live! (Their research preview is) Odyssey 3 Pro is a world model, and nobody beats it for physical accuracy. You can use this model to control a robot, drive a car, play a video game, or pilot a drone. • It takes visual observations from the world • Uses these observations to learn how things work • Then maps that knowledge to the system's physical controls1h
    rachit@rachiitgrthis is not a video generator. it's a world model odyssey-3 builds an environment from a prompt and generates it in real time as you move through it walk, jump, move the camera → the world responds ripples when you step into water. a car rolling through a crosswalk. a beaver wading out of a lake the same model is what odyssey is adapting for robot arms, humanoids and driving research preview is open, try it yourself1h
    🚨 AI News | TestingCatalog@testingcatalogOdyssey has launched Odyssey-3, its most powerful foundation world model to date, and opened a research preview to the public. Odyssey-3 builds an environment from a prompt and predicts changes in real time as a person moves through it or triggers events. > Odyssey-3 Pro scored 66.1 on Physics-IQ Verified video-to-video with best-of-8 sampling. This is the highest reported result. > Users can walk through scenes in first or third person. The camera can also move independently. > Odyssey adapted the model to robot arms, humanoids, and a car on real roads in India. Each system uses its own trained policy.1h
    Dipti Sharma@Diptish09this is probably the first world model launch in a while that made me think beyond video generation Odyssey-3 can create interactive environments from a prompt, in real time. It can model physics, dynamics and cause-and-effect from visual experience. Then you have 66.1 on Physics-IQ Verified, plus the physical AI angle. There’s a lot packed into this launch.47m