How AI image-generators work
Some are getting good enough to fool humans
THE FLURRY of images generated by artificial intelligence (AI) feels like the product of a thoroughly modern tool. In fact, computers have been at the easel for decades. In the early 1970s Harold Cohen, an artist, taught one to draw using an early AI system. “AARON” could instruct a robot to sketch black-and-white shapes on paper; within a decade Cohen had taught AARON to draw human figures.
Today “generative AI” models put brush to virtual paper: publicly available apps, such as Midjourney and OpenAI’s DALL-E, create images in seconds based on text prompts. The final products often dupe humans. In March AI-generated images of Donald Trump being handcuffed by police went viral online. And image generators are improving fast. How do they work—and how are they refining their craft?
Explore more
More from The Economist explains
Why Julian Assange’s extradition case is taking so long
The WikiLeaks co-founder is granted a new appeal against being sent to America
What are the Russian “turtle tanks” seen in Ukraine?
Wrapping vehicles in corrugated metal might protect them from drone attacks
The tawdry history of “catch-and-kill” journalism
Testimony from Donald Trump’s trial highlights a practice that is normally hidden