THE APEX TIMES
The company says its newest “world model” for interactive, browser-based scenes can now be edited in real time, with sound that shifts as events unfold.
Google is expanding access to Project Genie, an experimental system for generating and exploring interactive “worlds” in a web browser, with a new model it calls Genie 4. In a post on its official blog, Google said Genie 4 is now available to eligible users of its “Google AI Ultra” subscription tier, marking the latest step in the company’s push to make AI-generated environments feel more controllable and less static.
Project Genie was introduced earlier as a research prototype that combines what Google describes as its most advanced world models with Gemini models. The goal is to let users generate worlds, step into them, and shape what happens as they explore, directly from the browser rather than through a traditional app workflow.
Genie 4 is positioned as the most realistic and interactive world model yet. Google said users can prompt again while a session is underway to change the environment they created, essentially allowing mid-flight edits without restarting the experience. The examples provided include shifting the weather, dropping in a character, or redirecting the action through new instructions entered during navigation.
A key addition in the Genie 4 experience is audio. Google said Genie 4 pairs its visuals with real-time native audio that adapts as the scene unfolds, ranging from ambient soundscapes to character dialogue. The company did not provide technical specs or performance metrics in the post, but it framed audio as part of what makes the worlds feel more responsive.
Google also said Genie 3 remains available in Project Genie for users who want longer runs or worlds seeded from 360-degree panoramas. Today’s Genie 3 updates include a new “agent” that Google describes as moving beyond a single prompt. Instead, it is designed to help craft an interactive universe through a natural-language conversation where the agent coordinates multiple multimodal models to produce initial visuals and a custom background score tailored to the mood.
The post further described how Gemini models can be brought into a session as people explore. In Google’s description, Gemini can observe what is happening on screen, provide context-aware suggestion “chips” on where to go next, and trigger in-world events automatically as the journey unfolds. Those capabilities aim to turn exploration into something closer to co-piloted storytelling, rather than a purely user-driven walkthrough.
For users who want to start exploring right away, Google introduced a Project Genie gallery described as combining curated worlds with community creations. The gallery includes examples such as “Living Memory,” which Google says transforms personal photos into explorable spaces; “Dino Field Guide,” which it describes as prehistoric habitats grounded in 360-degree panoramas; and “Rock Paper Scissors,” where Gemini acts as a real-time referee for themed object battles.
Google also highlighted collaborations with outside creators that used early access to Project Genie. It cited work with creative technologist Will, known as BLVCKL!GHT, on “Villa Giallo,” described as a room-by-room mystery inside a gothic manor, and with filmmaker Anand Gandhi on “The Life of Ants,” which Google said invites users to navigate a complex colony from an ant’s perspective, drawing on Genie 4’s photorealism.
As with other frontier “world model” projects, Google emphasized safety and responsible deployment. It said all video and audio generated in Project Genie includes SynthID watermarking, and that model inputs and outputs undergo safety screenings. The company did not specify what categories of content are disallowed or the exact enforcement thresholds, but it pointed readers to a Genie 4 model research overview for deeper discussion of model limitations and progress.
Even with the new rollout, Google framed Genie 3 and Genie 4 as still in the frontier research space, and acknowledged ongoing technical challenges. It named areas such as camera latency, intricate physical interactions, real-time audio precision, and long-term scene permanence, suggesting that while users can interact more fluidly, the systems are still evolving. For users, the immediate question is how consistently mid-session prompts work across different scenarios, and how stable audio and physics remain during longer explorations.
Investors moved quickly after early outlines connected United Launch Alliance’s work to the BE-4 engine family, which Blue Origin’s New Glenn is expected to use for a planned 2027 flight carrying AST SpaceMobile’s BlueBird satellites.
A report tied to Anthropic’s debut highlights a cash position large enough to dwarf the combined figures of Amazon and NVIDIA, while also pointing to a new exchange-traded fund built around companies described as “ANT-linked.”
A Yahoo Finance report highlights how Berkshire Hathaway’s roughly $10 billion investment in Alphabet appears to be losing value, with Bill Ackman commenting that the timing and pricing were unexpected even as he noted the stake was bought at a perceived discount.
The company said it has reshaped leadership around national security and export-control oversight after Huang’s exit, emphasizing governance changes ahead of its next quarter and the continuing geopolitical scrutiny on advanced chips.
Anthropic priced its IPO at $83 per share ahead of its debut, while Nvidia heads toward a seventh straight weekly decline amid fresh US pressure on AI chip exports.
A report citing Cathie Wood’s ARK funds says they sold about $84.8 million of Nvidia shares before the company’s earnings period and used the cash to buy holdings tied to crypto markets.
Reports tied to Nvidia’s former chief executive, including allegations of multiple affairs involving a suspected Chinese intelligence-linked figure, are now being read alongside a broader, politically sensitive backdrop for advanced chip sales across the United States and China.
A celebrity investor publicly criticized NVIDIA’s former CEO Jensen Huang, then appeared to reverse course several days later, echoing a message that Nvidia employees “know better than the board,” according to a Yahoo Finance report.
A reporting update says the major banks and asset managers that earlier this year promised as much as $500 billion in financing support for Nvidia customers have not yet moved capital into that program.
The sale, disclosed in a regulatory filing, trims Lisa Su’s direct stake in Advanced Micro Devices while the company’s shares have climbed sharply this year.
Comments
Community guidelines. Comments may be removed for violations.
Loading comments...