Skip to content
IFAI

Odyssey

Company7 stories

  1. ResearchReach 36

    Odyssey lets 20 humans and AI agents play together in a generated world

    Odyssey just released a playable research preview of Agora-2, a multi-agent world model that simulates real-time interactive worlds for up to 20 humans and AI agents. Trained on Diablo II data, it functions as a learned game engine that maintains a shared global state while streaming unique views to each participant. Why it matters: It shifts multi-agent AI training from hand-coded simulators to neural networks that learn physics and emergent behavior on the fly.

  2. RoboticsReach 39

    Odyssey-3 wants to be the foundation brain for every robot

    Odyssey just introduced Odyssey-3, a foundation world model that learns physics and causal dynamics directly from visual data. Instead of building narrow task-specific systems, a single frozen model can pilot robot arms, humanoids, drones, and self-driving cars with just tens of hours of control data. Why it matters: Generalist physical AI might finally be getting its GPT moment.

  3. AI modelsReach 50

    Odyssey turns AI world models into real-time multiplayer games

    Odyssey just dropped two frontier world models, Starchild-1 and Agora-1, pushing generative video into interactive simulation. Starchild-1 generates synchronized audio and video on the fly without fixed runtimes, while Agora-1 lets up to four players interact inside the same live-rendered game world with a shared state. It is a major shift from static clips to real-time playable realities.

  4. AI modelsReach 50

    Odyssey's new world model learns physics in real time

    Odyssey just introduced Odyssey-2 Max, a 3x-larger world model capable of continuous, real-time physical simulation. Unlike traditional video generators, it predicts open-ended futures autoregressively to internalize real-world mechanics, topping VBench 2 physics scores. It is currently available in private beta for robotics and gaming partners.

  5. Generative mediaReach 50

    Odyssey drops real-time interactive video powered by world models

    Odyssey just launched a public research preview of its real-time interactive video platform. Powered by world models running on NVIDIA H100s, it lets users directly influence streaming video via keystrokes or joystick moves with 40ms latency at 30 fps. The team admits it still feels like a glitchy dream, but envisions a future where all video is interactive.

  6. Generative mediaReach 36

    Odyssey straps 25-pound camera rigs to hikers to train world models

    Odyssey just raised $18 million in Series A funding to build generative AI world models using real-world data captured by human hikers. Equipped with custom 25-pound rigs carrying six cameras and two lidar sensors, the team captures 360-degree scenes to give creators fine control over geometry, lighting, and motion. Why it matters: Hollywood-grade world generation requires grounded physical depth that scraping web video can't replicate.

  7. Generative mediaReach 31

    Odyssey shows off directable Hollywood-grade visual AI

    Oliver Cameron just unveiled Odyssey, a new venture building Hollywood-grade visual AI aimed at films, TV, and video games. Rather than just generating scenes, the system lets creators actively direct scenery, characters, lighting, and motion. Why it matters: Adding genuine director-level control could transform generative video from an unpredictable gimmick into a serious production tool.