Google adds Street View integration to Project Genie, its interactive world builder, and expands Genie from the US to adult Google AI Ultra subscribers globally
Genie can simulate worlds based on real locations, and you can try it too!! Check out the blog for more infoJustine Moore /@venturetwins:I got to “play” a world model in real life. The @GoogleDeepMind folks set up a crazy demo for Genie. You select glowing orbs to represent your scene and character. It loads the world in the model, and you navigate with joysticks like a video game 🕹️ [video]Shlomi Fruchter /@shlomifruchter:Since we launched Project Genie, we hear from users that they want to exp
EngadgetJessica Conditt
Context & Ripple Effects
Project Genie follows DeepMind’s progression from Genie 2, which turned a prompt image into a playable 3D environment, to Genie 3, which added sustained interactive world generation. Google then packaged those capabilities into a consumer-facing builder for US AI Ultra subscribers.
The new update connects that builder to Street View and takes the subscription feature beyond the US. It also extends a pattern visible in related coverage: Genie 3 is already being applied to synthetic-world creation for Waymo training, while Project Genie exposes a version of the same underlying capability to users.
First-order effects
AI Ultra subscribers globally can access Project Genie rather than the prior US-only release, expanding the product’s immediate addressable user base.
Street View integration gives users a Google-supplied real-world reference layer for creating and navigating Genie worlds, making location-based creation more direct within the product.
Second-order effects
The update makes Google’s Maps/Street View assets more strategically useful alongside its generative-world models, rather than functioning solely as mapping products.
World-building tools that rely only on text or uploaded imagery face a clearer comparison point: Google can combine model-generated interaction with a large proprietary location-data interface for eligible users.
Third-order effects
If Google continues linking world models to mapping data and premium subscriptions, interactive simulation could evolve from a standalone AI demo into a vertically integrated Google platform spanning location data, creation tools, and AI services.
The pattern also raises a durable boundary question for the sector: as generated environments draw more heavily on real places and platform-held imagery, product differentiation and scrutiny will increasingly center on data rights, fidelity, and controls over real-world representation.
The trend: This is a data-integrated world-model trend, in which AI-generated interactive environments are being productized through proprietary context layers and subscription distribution.
Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at https://labs.google/... and read the blog for more info: https://blog.google/... [video]
Woot! You can now simulate real world places by grounding Genie 3 experiences with Street View imagery. Google sitting on the mother lode of real world data, and is starting to put it to work! Let's dive into some prompts & locations I tested... [video]
Last year on 60 minutes we talked about the potential to ground our world models with Street View data. Thanks to hard work from @poolio and others this is now possible—Genie can simulate worlds based on real locations, and you can try it too!! Check out the blog for more info
I got to “play” a world model in real life. The @GoogleDeepMind folks set up a crazy demo for Genie. You select glowing orbs to represent your scene and character. It loads the world in the model, and you navigate with joysticks like a video game 🕹️ [video]
Since we launched Project Genie, we hear from users that they want to explore worlds built around real locations. Genie now lets you ground your experience in real locations from Street View! [video]
By connecting Google's massive-scale Street View imagery to our most powerful world models, we unlock more realistic simulators for agents and new creative opportunities in your favorite locations. Here's a watercolor version of sweater frog on a bicycle at the top of Hawk Hill: …
Cool new launch for Project Genie ✨ World generation is now grounded with Google Maps. Pick a real-world location, restyle it, and draft a character to explore the scene. I turned @a16z SF into a desert and wandered around as a camel. [video]
For the past few months, I've had the opportunity to work on an incredible collaboration bridging the immersive world of #GoogleMaps #StreetView with the magic of Project Genie from #GoogleDeepMind. …
Thrilled to see Genie with Street View landed and going global! 🚀 — Have been working on improving the long-term consistency significantly in the past months. …
The results of the research happening in my team @GoogleDeepMind have convinced me that the next era of scientific discovery will be aided by AI agents acting as force multipliers for human ingenuity. That's why I'm proud to introduce Gemini for Science - a collection of
Out of all the announcements at @Google I/O today, this is the one closest to my heart - our foundational research on Co-Scientist was published in @Nature and we announced its broad availability via @GeminiApp for Science. When you are suffering from a disease, time is [video]
Got to play with a little of this before launch as well. My experience as a social scientist was that it was more bioscience focused right now, but I think Google has been the leading lab in releasing serious AI tools to accelerate science & expect to see them improve fast.
Gemini for Science! I've been saying this for some time: we have now entered a new phase in science, I call it Science 3.0, with research becoming completely AI-assisted! Google DeepMind is pushing this to the next frontier with very useful AI models and modules!
Congrats, team! 🥳 And this is my first @Nature paper and my first paper with my ex-boss @demishassabis as well! 🥳 (well, if we don't count for @GeminiApp papers lol)
A big day for multi-agent AI to accelerate biomedical discovery, hypothesis generation, designing experiments with proof points of new candidate drugs (cancer, fibrosis, macular degeneration, antimicrobial resistance, and more) 2 @Nature reports @GoogleDeepMind @FutureHouseSF
Industry-wide collaboration on content transparency tech is key to a trusted web. 🤝 We're accelerating the momentum started with @NVIDIA and partnering with @OpenAI, Kakao, and @ElevenLabs to bring SynthID to their generative content — helping give everyone more helpful context […
We're adding new ways for people to identify AI-generated images and understand where they came from. In addition to C2PA Content Credentials, images now also contain a SynthID watermark, and can be identified using a public verification tool to check whether an image was made
Really happy to see @OpenAI adopt @GoogleDeepMind's SynthID for watermarking AI generated images. We need more such cross industry partnerships for enabling responsible use of AI systems.