World Labs Releases Frameboy, Streaming Atlas Scenes to Browsers at Up to 15 FPS
World Labs released Frameboy on November 5, 2026, a research preview that it says streams Atlas-generated scenes from cloud GPUs to a browser at up to 15 frames per second. The mode is also integrated into Viewfinder, the company's closed-beta web app for building 3D scenes.
World Labs released Frameboy on November 5, 2026, a research preview that the company says streams Atlas-generated scenes from cloud GPUs to a browser at up to 15 frames per second while users control the camera. The details come from a short summary published by Unite.AI.
What was released
- Frameboy: a research preview for real-time exploration of scenes generated by Atlas. According to World Labs, scenes stream from cloud GPUs to the browser at up to 15 frames per second.
- Camera control: users steer the camera as the stream runs.
- Viewfinder integration: World Labs also integrated the mode into Viewfinder, its closed-beta web app for building 3D scenes.
- Optimized Atlas variant: World Labs says the Atlas variant behind Frameboy is designed for faster, more efficient inference.
Context window, pricing, parameter count and benchmark scores are not part of the announcement summary.
What this means
Frameboy moves Atlas exploration from individual render requests to a continuous stream, a shift the Unite.AI report frames as going from render requests to continuous exploration. The 15 frames per second figure is a ceiling World Labs states, not a measured result, so real-world performance will depend on the cloud GPU delivery the company describes. Placing the mode inside Viewfinder, which is still in closed beta, ties the capability to World Labs' existing 3D scene-building workflow.
Related Articles
Meta adds real-time voice mode and expressive avatars to Muse AI agent in US app
Meta now lets users hold real-time voice conversations with their Muse AI agent, CEO Mark Zuckerberg announced. The voice mode and animated 'expressive' avatars are rolling out in the US for the app, with AI glasses support coming 'soon'.
Google shows Gemini Canvas turning a photo of a paper sketch into an interactive app
Google published a Gemini walkthrough on November 5, 2026, showing how a photograph of a paper sketch can become an interactive app in Canvas. The demonstration covers uploading the image, generating code, testing the result and refining it through conversation.
Anthropic launches Personal Finance in Claude with read-only Plaid access for US Pro, Max and Ultra users
Anthropic announced Personal Finance in Claude, a feature that connects bank and credit card accounts through Plaid with read-only access. Conversations in the Personal Finance hub are not used to train Anthropic's models. It is available only to Pro, Max and Ultra subscribers in the US.
Apple removes Siri AI waitlist in iOS 27 beta; compatible devices now download it immediately
Apple has removed the waitlist for Siri AI in the iOS 27 beta, according to ZDNET. Compatible devices now start downloading Siri AI as soon as the feature is enabled, though Apple could temporarily reinstate the waitlist during unusually high demand.
Comments
Loading...