In this episode Vivian and Noah purchase David Young's piece titled Winter Woods, a work produced using a GAN, leading to a larger discussion ... around art created using AI. Artist, researcher, and podcaster Mat Dryhurst helps explain how AI works, as well as how DALLE-2 , a new AI system from OpenAI is different from other GANs. We also hear from artist Super Metal Bosch, one of the artists behind the GAN art project Super Metal Mons. Vivian goes on to compare AI to photography and the art of being a clown, which goes over Noah's head. Artist Carlos Sanchez contributes thoughts about clowns.
The episode is interrupted by a last minute mint of Ezra Miller's project Silk Road.
A generative adversarial network ( GAN) is a class of machine learning frameworks designed by Ian Goodfellow and his colleagues in June 2014. Two neural networks contest with each other in a game (in the form of a zero-sum game, where one agent's gain is another agent's loss).
DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text-image pairs. We've found that it has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining unrelated concepts in plausible ways, rendering text, and applying transformations to existing images.