New generative AI technologies can allow us to imagine new species that have been forced to adapt in order to survive. Hidden within a deep neural network, there are millions of these "ganimals" that no one has ever seen before. These ganimals occupy a digital landscape not unlike our own, where attention is short, and engagement is necessary to survive.
To withstand the harsh conditions of the attention economy, ganimals evolve very rapidly. As a result, they occupy a wide range of ecological niches and digital habitats. The data you provide about the ganimals is their "food." Using the feedback you provide, the GAN generates new ganimals by exploring both undiscovered ganimals, and the most highly rated previously discovered ganimals. Thus, by providing feedback on newly discovered species, you can help guide the evolution of future generations.
Meet the Ganimals is a collaborative social experiment to discover new species, breed your own, and feed the ones you love. By rating data about your preferences for ganimals, you can help them survive and guide their evolution. Unfed ganimals are quickly forgotten, so the cutest, scariest, most realistic, and most memorable ganimals have a genetic advantage, and breed more often.
In particular, the ganimals you encounter are generated by an algorithm that balances two factors. First, the algorithm explores undiscovered regions of the Ganimal Kingdom (the vast combinatorial space of all possible ganimals). Second, the algorithm surfaces already discovered ganimals that people love. Thus over time, the pool of ganimals slowly evolves to the crowd’s preferences.
There are several papers and blog posts about the project you can read to learn more:
The secret sauce for generating ganimals is the generative adversarial network (GAN) that creates them. In the next section, we learn how they work.