@omarsar0: The interfaces you see in the clip are generated directly by the model. Generated in real time without code or HTML. Th…
Summary
Runway introduces Solaris, an Interface World Model that generates interactive interfaces frame by frame in real time without code, outperforming frontier LLMs.
View Cached Full Text
Cached at: 09/01/26, 11:50 PM
The interfaces you see in the clip are generated directly by the model.
Generated in real time without code or HTML.
That’s nuts!
Just thinking to myself all the things you could build with an interface world model like this. Simulators, games, etc.
Runway (@runwayml): Today, we’re sharing new research on Solaris, our first Interface World Model.
Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new
Similar Articles
Introducing Solaris (17 minute read)
Runway introduces Solaris, the first AI model in their Interface World Models family, which generates real-time interactive interfaces by synthesizing frames directly, eliminating the need for code and enabling dynamic design and agent training.
Introducing Solaris our first Interface World Model | Runway
Runway has released Solaris, its first Interface World Model, which can generate dynamic software interfaces in real-time based on user interactions, without the need for pre-set code, marking a fundamental shift in software operation.
Open Source vs frontier models on a single-file HTML canvas driving animation - results
A user compares open-source and frontier AI models on a single-file HTML canvas car driving animation task, presenting results and a gallery.
@omarsar0: The frontier open model takeoff is spectacular to witness! Looks like the gap between closed and open models is a thing…
This tweet discusses the closing gap between open and closed AI models, with bolt.new reporting popular usage of models like GLM 5.3 Flash and DeepSeek V4 Pro among builders.
@omarsar0: Exciting to see that world models are learning how to act. Odyssey-3 previews a single world model powering robot arms,…
Odyssey-3 is a new foundation world model that can control robots, cars, drones, and virtual worlds by reusing world knowledge across machines with minimal experience.