AI Use Case: Genie3 and the Power of Imagination

More amazing than the world of image and video creation (and the explosion of deepfakes, historical tik toks and more) is the world of virtually rendered environments as seen in Google's release of Genie 3 last week.

From Google

Using the data gathered from YouTube, images, and maps, Google has created an AI image that renders an interactive virtual environment in real time:

Given a text prompt, Genie 3 can generate dynamic worlds that you can navigate in real time at 24 frames per second, retaining consistency for a few minutes at a resolution of 720p.

Although it is not yet publicly available, Genie 3 and what I'm sure will be a host of copycats in the near future - seems like a natural extension of the MinecraftEDU phase of the previous decade.

We've discussed previously using AI generated images and video as a creative assessment to track student understanding. Students use generative AI and prompting to produce particular images or video of a character from a novel (or scene), historical event, et al. much as we might have students draw a picture.

From the Genie 3 announcement page.

Genie 3 offers the promise of having students create a virtual world for these same figures. What gaps in student learning could be demonstrated by the recreation of a scene from Macbeth in the virtual space? Or placing their created historical figure or character in a new context? This is all before the possibly? coming explosion of virtual reality glasses.

I highly recommend heading over to the Genie 3 announcement page and just checking out some of the environments rendered. Or watch the announcement video: