Introducing Agora-1, a multi-agent world model.
Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time.
Try our playable research preview today, with Agora-1 simulating a multiplayer GoldenEye deathmatch!
FIRST real-time multimodal world model. Video + Audio.
I couldn't be more proud of the team at @odysseyml - this is just the start.
I hope Starchild-1 invokes the awe and wonder it did with me.
Onwards!
Introducing Starchild-1 from @odysseyml, the first ever real-time multimodal world model.
This a model that can generate interactive simulations of the world that you can—for the first time ever—hear.
Starchild-1 represents a big step towards a general-purpose world simulator.
Introducing PROWL!
We’ve built RL agents that explore game environments, tasked with discovering failures in world models across physics, visuals, and actions.
Those failures then become training data in an automated loop that advances world model performance.
Incredible interview from @olivercameron at @StartupGrind 🎙️🎙️
Skip to 14:56 to see his prediction of when the "GPT-2 Moment" will happen with world models and which industry/applications it will happen in 👀👀
P.S. watch the whole thing, it's worth your time!
https://t.co/csH1Y2Bm4D
@Scobleizer@odysseyml I like where you're headed here!!
We're super excited about all the learning potential world models can enable.
The LLM tutors are single dimensional.
World model EDU experiences will be transformative.
The @odysseyml team is absolutely cooking!!
We're beating benchmarks and bringing new multi-modal intelligence.
It's happening.
Want to try it out or learn more? Let's talk.
It’s time to go beyond language models.
Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy.
This is a big step toward models that simulate and interact with the world in real time.
A new intelligence entirely!