AI News: These Google Updates Are Dividing People
Interactive world generation now grounded in real locations via Google Street View. Creator demoed a monkey on roller skates at Petco Park and called it impressive.
PG
Project Genie
Google DeepMind app for generating interactive, explorable worlds from prompts, including places grounded in Street View.
Updated EU status checked Last shown
Project Genie at a glance
- What is Project Genie?
- Project Genie is an app from Google DeepMind. Google DeepMind app for generating interactive, explorable worlds from prompts, including places grounded in Street View.
- Who makes Project Genie?
- Project Genie is made by Google DeepMind.
- Does Project Genie work in the EU?
- Unverified. No explicit evidence found. Last verified 14 Nov 2026.
- How much does Project Genie cost?
- Pricing unknown. No pricing information found in the provided sources. Licence: Proprietary.
- Where was Project Genie shown?
- In 1 creator video by Matt Wolfe. Most recently by Matt Wolfe on 22 May 2026, at 25:36 in “AI News: These Google Updates Are Dividing People”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
Project Genie is a Google DeepMind app for interactive world generation, built on the company's Genie line of world models. A user describes a scene or character and can then move through the generated environment, which is rendered in real time rather than as a fixed video clip.
According to a creator demo, worlds can now be grounded in real locations using Google Street View. One example placed a monkey on roller skates at Petco Park. The official pages provided do not describe Project Genie directly. They list Genie 4 as "a new generation of world simulation", but the relationship between Genie 4 and this app is not documented in the supplied material.
Details on access, pricing, supported regions, session length and resolution are not given in the provided sources. The product should be treated as an experimental Google DeepMind release.
Key features
- Generates interactive, navigable worlds from prompts
- Real-time world simulation rather than fixed video output
- Can ground worlds in real locations via Google Street View
- Built on Google DeepMind's Genie world-model research
1 moment
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
G4
Genie 4
Model · Google DeepMind
Google DeepMind world model that turns text or images into interactive, real-time controllable worlds with audio.
Unverified3D & Worlds
Release date n/a
DW
DreamX World
Model · Alibaba (Amap)
Open world model from Alibaba's Amap team that generates explorable, controllable worlds with long-horizon memory.
Available in EU3D & Worlds
Release date n/aOpen source
GW
GWM Worlds 2
Model · Runway
Runway's real-time interactive world model generating 720p/24fps video with audio, steered by text actions and camera input.
Unverified3D & Worlds
3 Sept 2026
LW
Lingbot World 2
Model · Robbyant
Real-time interactive world model from Robbyant that generates controllable, long-horizon environments.
Unverified3D & Worlds
Release date n/a
EV
Evoke
Model
14B autoregressive world model that generates interactive, camera-controlled video worlds in 3 denoising steps.
Unverified3D & Worlds
Release date n/aOpen source
GE
GenCeption
Research · Google DeepMind
Google DeepMind research that turns a text-to-video diffusion model into a single feed-forward, multi-task vision model.
UnverifiedResearch
Release date n/a