Genie, Turning Images Into Playable Worlds
New Day, New Modality
Amid its current controversies, Google continues to innovate in other areas of Generative AI.
Now, it has created an entirely new type of model, named Genie, the first-ever model to create action-controllable environments, aka turning still images into playable games.
But it can be much more, as due to its innovative training approach, it has been framed as a potentially viable path to generalist agents, the milestone all AI labs in the world are desperately trying to achieve.
This insight and others have mostly been previously shared in my weekly newsletter, TheTechOasis.
If you want to be up-to-date with the frenetic world of AI while also feeling inspired to take action or, at the very least, to be well-prepared for the future ahead of us, this is for you.
🏝Subscribe below🏝
Genie in an AI Bottle
In succinct terms, Genie is a spatiotemporal transformer that takes in a single…
