Get curated editors’ picks, peeks behind the scenes, film recommendations and more.
When viewing the work of the US artist and tool developer Joel Simon, you might find that his images are unlike anything you’ve ever seen before – which makes sense, as they weren’t quite born of nature or a human mind. Inspired by the biological properties of evolution and emergence, Simon uses simple programming rules, which, when applied over and over, give rise to uncanny images that augment the human imagination. His most recent work, explored in this video from Science Friday, applies a machine-learning framework known as a generative adversarial network (GAN) to two images. Guided by human users via Simon’s website Artbreeder, his programs ‘crossbreed’ pictures of everything from animals to artworks. Fascinating digital artefacts in their own right, the resulting, author-less images raise complex questions at the nexus of art, programming and design.
Video by Science Friday
Producer: Luke Groskin
Flicker through the eclectic beauty and biological diversity of 2,400 leaves
Bertrand Russell wanted to kill off causation. Can contemporary philosophy rescue it?
How many monkeys is it worth sacrificing to save a human life?
History of science
Bat-people on the Moon – what a famed 1835 hoax reveals about misinformation today
Human rights and justice
Thirty years after one teenager shot another, is it time to forgive?
What it’s like to wear a prosthetic that ‘feels’
A square inch in a Petri dish becomes a grand stage for chemical transformations
What is it like to be a paramedic, navigating human emergency?
The tangled tale of how physicists built a groundbreaking wormhole in a lab