Welcome to the Quanta Audio Edition.

In each of these bi-weekly episodes, we bring you a story direct from the Quanta website

about developments in basic science and mathematics.

I'm Susan Vallett.

Image generators are designed to mimic their training data.

So where does their apparent creativity come from?

A recent study suggests that it's an inevitable byproduct of their architecture.

That's next.

Quantum Magazine is an editorially independent online publication supported by the

Simon's Foundation to enhance public understanding of science.

We were once promised self-driving cars and robot maids. Instead, we've seen the rise of

artificial intelligence systems that

can beat us in chess, analyze huge reams of text, and compose sonnets. This has been one of the

great surprises of the modern era. Physical tasks that are easy for humans turn out to be

very difficult for robots, while algorithms are increasingly

able to mimic our intellect.

Another surprise that has long-perplexed researchers is those algorithms knack for their own strange

kind of creativity.

Diffusion models are the backbone of image-generating tools such as

Dolly, Imagine, and stable diffusion. They're designed to generate carbon copies of the images

on which they've been trained. But in practice, they seem to improvise blending elements

within images to create something new, not just nonsensical

...