Google is rolling out a new upgrade for its Gemini AI that lets the chatbot generate interactive 3D models and simulations based on user questions.
Instead of just giving text or static images, Gemini can now create visuals you can actually interact with in real time.
With this feature, users can rotate models, zoom in, and adjust different variables using sliders or input fields. For example, when asked to simulate the Moon orbiting the Earth, Gemini produces a 3D model that allows you to control the speed of the orbit, pause the motion, and even hide the path line. The model can also be viewed from different angles, making it easier to understand how the system works.
This update follows similar moves from other AI companies. Anthropic recently added support for charts, diagrams, and interactive visuals in Claude, while OpenAI introduced tools in ChatGPT for visualizing math and science concepts. Until now, Gemini was limited to generating interactive images rather than full simulations.
The feature is available to users through the Gemini app by selecting the Pro model in the prompt bar. Once enabled, you can ask Gemini to show things like a double pendulum or explain concepts such as the Doppler effect, then tap the option to view the visualization and interact with it directly.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
