6 Sources
[1]
Odyssey's new AI model streams 3D interactive worlds | TechCrunch
Available on the web in an "early demo," the model generates and streams video frames every 40 milliseconds. Via basic controls, viewers can explore areas within a video, similar to a 3D-rendered video game. "Given the current state of the world, an incoming action, and a history of states and
[2]
You can now try interactive AI worlds backed by Pixar's cofounder
Jay Peters is a news editor covering technology, gaming, and more. He joined The Verge in 2019 after nearly two years at Techmeme. AI companies have recently been experimenting with interactive, AI-generated worlds. There's an AI-generated version of Quake. An AI-generated Minecraft. Google
[3]
This interactive AI video generator feels like walking into a video game - how to try it
You can try Odyssey's interactive video generator for free, GPUs permitting. With dozens of image generators on the market that can produce hyper-realistic pictures from text prompts, many developers have started tackling a new challenge: video generation. AI lab Odyssey has launched a video
[4]
This Dreamlike Video Generator Makes Interactive AI Feel Like a Lo-Fi Acid Trip
We talk a lot about AI hallucinations nowadaysâ€"and for good reason. "Hallucinations" is basically AI-speak for "making sh*t up," and most of the timeâ€"like in the case of web search, which relies on surfacing real, useful informationâ€"that's a Very Bad Thing. I don't think I'm alone when I say
[5]
I tried exploring a real-time generated AI world, and it was like walking through the uncanny valley
Google Maps Street View and similar tools allow you to virtually navigate real-world locations from the ground, even if you can't interact with what you see. A new tool from AI startup Odyssey offers an experience in AI-generated locations that you can interact with, and it's produced in almost
[6]
Odyssey's AI literally turns your screen into a playable explorable universe
Odyssey, a startup founded by Oliver Cameron and Jeff Hawke, has developed an AI model allowing users to interact with streaming video. Its early web demo generates and streams video frames every 40 milliseconds, letting viewers explore areas within these videos. According to the startup's blog
Share
Copy Link
Odyssey, an AI startup, has launched a research preview of its interactive video technology, allowing users to explore AI-generated 3D worlds in real-time. The technology, while still in early stages, promises to revolutionize entertainment and storytelling.
Odyssey, an AI startup backed by Pixar co-founder Edwin Catmull, has unveiled a groundbreaking technology that generates interactive 3D worlds in real-time. The company has launched a research preview of its "interactive video" platform, allowing users to explore AI-generated environments using basic controls
1
.
Source: Dataconomy
The technology utilizes a "world model" that generates and streams video frames every 40 milliseconds, creating a responsive environment that users can navigate using keyboard controls. Unlike traditional video games, Odyssey's system doesn't rely on pre-rendered assets but instead generates the entire world on the fly
2
.In its current state, the experience is described as "exploring a glitchy dream"
3
. Users can explore various environments such as forests, shopping malls, and parking lots. However, the visuals are blurry and unstable, with objects and layouts sometimes changing unexpectedly1
.
Source: The Verge
The system runs on clusters of Nvidia H100 GPUs, costing between $1-$2 per "user-hour" to operate. Despite its limitations, the technology has garnered significant interest, with 85,000 streams generated globally within 24 hours of its launch
3
.Odyssey is actively working on improving the technology, aiming for richer world representations, increased temporal stability, and expanded interaction capabilities
1
. The company envisions this technology evolving into new forms of entertainment, education, and advertising4
.Related Stories
The development of world models like Odyssey's is being pursued by several tech giants and startups, including DeepMind, Microsoft, and Decart. These models could potentially revolutionize interactive media creation and simulations for robot training
1
.However, the technology has raised concerns in the creative industry. A 2024 study commissioned by the Animation Guild estimated that over 100,000 U.S.-based film, television, and animation jobs could be disrupted by AI in the near future
1
.
Source: ZDNet
Early users have described the experience as surreal and reminiscent of early video games or low-budget avant-garde films
5
. While the current version is far from perfect, many see the potential for future applications in personalized storytelling, education, and even advertising5
.As Odyssey continues to refine its technology, the company aims to collaborate with creative professionals rather than replace them, potentially opening up new avenues for interactive storytelling and entertainment
1
.Summarized by
Navi
19 Dec 2024•Technology

03 Dec 2024•Technology

19 Jun 2025•Technology

1
Technology

2
Technology

3
Science and Research
