Google Expands Interactive World-Building with Genie 4 Launch
Google has released its latest world-generation model, Genie 4, to premium AI Ultra subscribers, introducing real-time environment modification and audio integration.
🤖AI ModelsPhoto: thenextweb.com
Key points
- Genie 4 allows users to modify interactive worlds in real-time using text prompts.
- The update introduces native audio, including background noise and dialogue.
- All generated content is protected by Google's SynthID invisible watermarking.
- Google DeepMind positions these models as potential training environments for future AI agents and robotics.
Google has officially launched Genie 4, its latest generative model designed to create interactive digital environments, for Google AI Ultra subscribers. The tool, accessible through the browser-based Project Genie platform, allows users to generate navigable worlds that can be modified mid-session through text prompts. This update marks a significant shift by introducing native audio capabilities, including ambient sound and character dialogue, to the immersive experience.
The release also includes a new creation agent capable of building worlds based on user conversation, alongside a community gallery for sharing and remixing projects. While Genie 4 offers enhanced interactivity, Google notes that the model remains a research prototype. Users may experience visual inconsistencies during extended sessions, and the system continues to face challenges with complex physics and legible text rendering.
To ensure transparency, all content generated within Project Genie is embedded with SynthID, Google’s proprietary invisible watermarking technology. Meanwhile, the previous iteration, Genie 3, remains available for users requiring longer generation windows, with its capacity extended to three minutes per session. Despite these advancements, industry adoption remains cautious, as major game developers continue to prioritize human-led design over generative alternatives.
What to watch next: As Google and competitors like Odyssey refine world models, the focus will shift toward whether these systems can reliably transition from creative prototypes to practical training environments for robotics and autonomous vehicles.
Source thenextweb.com — thenextweb.com/news/google-genie-4-project-genie-ai-ultra-world-model ↗
Read next
🧠AI AnalysisSalesforce Optimizes Global AI Model Inference with Amazon SageMaker
Salesforce has implemented cross-Region inference routing in Amazon SageMaker to manage AI model capacity across 30+ global regions more efficiently.
🏢Big TechMicrosoft Challenges Rivals on AI Pricing at Ignite Conference
Microsoft is positioning its Copilot AI as the more cost-effective choice for businesses compared to OpenAI and Anthropic, citing a commissioned study to support its clai…
🚀Startups & FundingOpenAI CEO Sam Altman Addresses Upcoming Biographical Film
OpenAI CEO Sam Altman commented on the upcoming film 'Artificial,' which portrays his life and the 2023 leadership crisis at the company.
🌐Work & SocietyDesign Studio Office Commun Launches Minimalist WebKit Browser for macOS
Paris-based design studio Office Commun has released Search, a lightweight, open-source web browser for macOS that prioritizes performance and minimalist design.
🔌Chips & HardwareSnapchat Integrates AI Coding Assistants into AR Lens Development
Snapchat has launched the Easy Lens CLI, enabling developers to build augmented reality experiences using AI coding tools like Claude Code and Cursor.
🚀Startups & FundingRadixArk Unveils DaisyRose-27B, Focused on Agentic Efficiency
Startup RadixArk has launched DaisyRose-27B, an AI model optimized for long-horizon agent tasks, claiming significant improvements in training efficiency and reasoning ca…