
Google DeepMind has announced Genie 3, the latest version of its AI world model that can generate 3D environments in real time from a simple text prompt. Genie 3, unlike earlier versions, supports continuous interaction for a few minutes, remembers where objects were placed, and allows dynamic changes like adding characters or altering weather conditions. Genie 3 is currently available as a limited research preview to select academics and creators, with plans to expand access gradually.
According to a blog post from Google that accompanied the release, agents may anticipate changes in the environment and the potential effects of their actions by using world models, which can comprehend and recreate settings.
World models like Genie are designed to generate digital environments based on a prompt, much like video game worlds, except here, everything is built by AI instead of manually created 3D assets. These environments can be used for purposes such as learning, entertainment, and training robots or AI systems.
With Genie 3, Google says interaction time has increased to a few minutes, a big jump from the 10–20 seconds possible in Genie 2. The system can now keep visual details in memory for about a minute. That means if you walk away from something like a chalkboard or a wall with paint and then look back, the details will remain as they were.
See What’s Next in Tech With the Fast Forward Newsletter
Tweets From @varindiamag
Nothing to see here - yet
When they Tweet, their Tweets will show up here.