/AI23d ago

OdysseyML introduces Starchild-1 as the first real-time multimodal world model that generates interactive audio-video simulations evolving continuously from streaming text, speech, and action inputs

AI Judge changed title after evaluation, original title: "OdysseyML releases Starchild-1, a causal multimodal world model that generates interactive real-time audio-video simulations from continuous user inputs"

Oliver Cameron posted a demo of dynamic interactive scenes.

1531K181443223.9K
Original post
Oliver Cameron@olivercameron#1791inAI

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.

9:40 AM · May 18, 2026 · 211.9K Views
Sentiment

Positive users focus on the excitement and potential of OdysseyML's Starchild-1 as the first real-time multimodal world model, while negative users worry it is creepy or overestimates its capabilities.

Pos
82.5%
Neg
17.5%
43 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS3.6KRETWEETS4
Oliver Cameron@olivercameron

Starchild-1 is an early step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world.

Oliver Cameron@olivercameron

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.

23dViews 3.6KLikes 51Bookmarks 6
BOOKMARKS13
Oliver Cameron@olivercameron

We're also releasing an accompanying technical report of Starchild-1, to share our learnings and encourage further research in this direction!

Oliver Cameron@olivercameron

My dream is that models like Starchild-1 unlock entirely new forms of education, gaming, companionship, robotics, and brand new computing devices.

We're so early on this journey, but I'm so excited. The team did truly great work here.

https://odyssey.ml/introducing-starchild-1

23dViews 2.7KLikes 55Bookmarks 13
LIKES59
Oliver Cameron@olivercameron

My dream is that models like Starchild-1 unlock entirely new forms of education, gaming, companionship, robotics, and brand new computing devices.

We're so early on this journey, but I'm so excited. The team did truly great work here.

https://odyssey.ml/introducing-starchild-1

Oliver Cameron@olivercameron

Starchild-1 is an early step beyond world models that learn only from visual observation, toward systems that learn from richer multimodal interaction with the world.

23dViews 3.2KLikes 59Bookmarks 8
REPLIES19
Tiffany Fong@TiffanyFong

@olivercameron @odysseyml can it simulate my mom telling me she’s proud of me ???

23dViews 933Likes 48
Not Jerome Powell@alifarhat79

@olivercameron @odysseyml I need a first ever real-time multimodal world model of my printer

23dViews 2.1KLikes 6
Nathan Benaich@nathanbenaich

😍😍😍😍

Oliver Cameron@olivercameron

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.

23dViews 2.1KLikes 9Bookmarks 1
Rohan Paul@rohanpaul_ai

@olivercameron @odysseyml a serious technical step, as audio forces the model to learn hidden physical and social structure that silent video can often fake.

So many possibilities I can think of right away.

Oliver Cameron@olivercameron

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.

23dViews 372Likes 3Bookmarks 1
arc.@arceyul

@olivercameron @odysseyml really excited to see where this goes, the paper summarises it perfectly. congrats team!

23dViews 114Likes 2
Oliver Cameron@olivercameron

@maarcoofdezz @odysseyml Let's be honest we're all in a simulation anyway.

23dViews 34Likes 3
phed@PhedEU

@olivercameron @odysseyml this is pretty cool

23dViews 84Likes 2
Orangie@orangie

@olivercameron @odysseyml 🔥

22dViews 173Likes 1
Oliver Cameron@olivercameron

@roaldvanbuuren @odysseyml Devs was a total inspiration for Starchild-1.

22dViews 84Likes 1
Jeff Creedon@JeffCreedon

@TiffanyFong @olivercameron @odysseyml Impossible for any asian mother to say that

23dViews 23Likes 2
Aziz Builds@AzizBuilds

@olivercameron @odysseyml How long until they realise that they live in a simulation?

22dViews 160
Oliver Cameron@olivercameron

@AzizBuilds @odysseyml How long until we realize?

22dViews 151
Marco@maarcoofdezz

@olivercameron @odysseyml This is starting to feel like the future of simulation itself.

23dViews 40Likes 1
Kinjal Nandy@itsKinjalNandy

@olivercameron @odysseyml can it recreate what it’d feel like for my girlfriend and me to explore Mars?

23dViews 112
Roald Van Buuren@roaldvanbuuren

Devs has become real… or devs was always real and we are not? Or the simulation in devs is real but the non simulation in devs is not real and the viewer is the simulator? Or the viewer is a simulation and Devs is real and the simulation in Devs is not real? Error…

Anyways, very cool!

22dViews 98
Tapesee@Tapeseee

@TiffanyFong @olivercameron @odysseyml There are limitations to AI as well… 😕

23dViews 25Likes 5
Austin Nasso@austinnasso

@olivercameron @odysseyml So it’s like Higgsfield with voice mode plus a big eyeball?

22dViews 72
Load more posts