London-based AI lab Odyssey has launched a analysis preview of a mannequin remodeling video into interactive worlds. Initially specializing in world fashions for movie and recreation manufacturing, the Odyssey workforce has stumbled onto probably a totally new leisure medium.
The interactive video generated by Odyssey’s AI mannequin responds to inputs in real-time. You may work together with it utilizing your keyboard, telephone, controller, or ultimately even voice instructions. The parents at Odyssey are billing it as an “early model of the Holodeck.”
The underlying AI can generate realistic-looking video frames each 40 milliseconds. Which means whenever you press a button or make a gesture, the video responds virtually immediately—creating the phantasm that you simply’re truly influencing this digital world.
“The expertise as we speak seems like exploring a glitchy dream—uncooked, unstable, however undeniably new,” in accordance with Odyssey. We’re not speaking about polished, AAA-game high quality visuals right here, at the very least not but.
Not your commonplace video tech
Let’s get a bit technical for a second. What makes this AI-generated interactive video tech totally different from, say, an ordinary online game or CGI? All of it comes all the way down to one thing Odyssey calls a “world mannequin.”
In contrast to conventional video fashions that generate whole clips in a single go, world fashions work frame-by-frame to foretell what ought to come subsequent primarily based on the present state and any person inputs. It’s just like how giant language fashions predict the subsequent phrase in a sequence, however infinitely extra advanced as a result of we’re speaking about high-resolution video frames moderately than phrases.
“A world mannequin is, at its core, an action-conditioned dynamics mannequin,” as Odyssey places it. Every time you work together, the mannequin takes the present state, your motion, and the historical past of what’s occurred, then generates the subsequent video body accordingly.
The result’s one thing that feels extra natural and unpredictable than a conventional recreation. There’s no pre-programmed logic saying “if a participant does X, then Y occurs”—as a substitute, the AI is making its finest guess at what ought to occur subsequent primarily based on what it’s discovered from watching numerous movies.
Odyssey tackles historic challenges with AI-generated video
Constructing one thing like this isn’t precisely a stroll within the park. One of many largest hurdles with AI-generated interactive video is preserving it steady over time. Once you’re producing every body primarily based on earlier ones, small errors can compound rapidly (a phenomenon AI researchers name “drift.”)
To deal with this, Odyssey has used what they time period a “slim distribution mannequin”—primarily pre-training their AI on common video footage, then fine-tuning it on a smaller set of environments. This trade-off means much less selection however higher stability so every thing doesn’t change into a weird mess.
The corporate says they’re already making “quick progress” on their next-gen mannequin, which apparently reveals “a richer vary of pixels, dynamics, and actions.”
Operating all this fancy AI tech in real-time isn’t low cost. Presently, the infrastructure powering this expertise prices between £0.80-£1.60 (1-2) per user-hour, counting on clusters of H100 GPUs scattered throughout the US and EU.
Which may sound costly for streaming video, however it’s remarkably low cost in comparison with producing conventional recreation or movie content material. And Odyssey expects these prices to tumble additional as fashions change into extra environment friendly.
Interactive video: The subsequent storytelling medium?
All through historical past, new applied sciences have given delivery to new types of storytelling—from cave work to books, images, radio, movie, and video video games. Odyssey believes AI-generated interactive video is the subsequent step on this evolution.
In the event that they’re proper, we could be trying on the prototype of one thing that can remodel leisure, training, promoting, and extra. Think about coaching movies the place you’ll be able to observe the abilities being taught, or journey experiences the place you’ll be able to discover locations out of your couch.
The analysis preview out there now could be clearly only a small step in direction of this imaginative and prescient and extra of a proof of idea than a completed product. Nonetheless, it’s an intriguing glimpse at what could be doable when AI-generated worlds change into interactive playgrounds moderately than simply passive experiences.
You can provide the analysis preview a strive here.
See additionally: Telegram and xAI forge Grok AI deal
Wish to study extra about AI and massive knowledge from business leaders? Take a look at AI & Big Data Expo going down in Amsterdam, California, and London. The great occasion is co-located with different main occasions together with Intelligent Automation Conference, BlockX, Digital Transformation Week, and Cyber Security & Cloud Expo.
Discover different upcoming enterprise know-how occasions and webinars powered by TechForge here.
