The compressed map a generative model builds of its training data, in which each point corresponds to a possible output and nearby points produce similar ones. Artists explore it by moving between points, finding and blending forms.
I was mainly interested in not any one output, but the space of outputs. And that's what I was trying to communicate artistically, is look at these faces that are all in the local manifold of possibilities.
Tom White, Tom White & Gene Kogan on the Birth of GAN Art
But when you actually dig into the tools, use open source and try and do strange and different things with them, you can explore them as these kind of vast wildernesses that can open up new aesthetic frontiers.
Kevin Esherick, AI Psychosis Summit: Macy Gettles, quasimatt