Зарегистрируйтесь на getAbstract, чтобы получить доступ к этому краткому изложению.

Meet DALL-E, the A.I. That Draws Anything at Your Command

Зарегистрируйтесь на getAbstract, чтобы получить доступ к этому краткому изложению.

Meet DALL-E, the A.I. That Draws Anything at Your Command

New technology that blends language and images could serve graphic artists – and speed disinformation campaigns.

The New York Times,

5 мин на чтение
3 основных идей
Аудио и текст

Что внутри?

Is OpenAI too dangerous for the internet?


Editorial Rating

8

Qualities

  • Scientific
  • Eye Opening
  • Overview

Recommendation

Microsoft has invested a billion dollars in OpenAI and created DALL-E, a program that combines image and text analysis to generate realistic images based on verbal commands. This is the latest in neural network capabilities – systems that filter vast amounts of data to identify and classify images. While this application could be a boon to graphic designers and digital assistant developers, it’s also potentially dangerous in the wrong hands. Disinformation and “deep fakes” already exist on the internet, which DALL-E could exacerbate. It’s not yet on the market and is only available to researchers – for now.

Summary

Microsoft’s OpenAI is a billion-dollar artificial intelligence lab that created DALL-E.

Alex Nichol, one of the researchers at Microsoft’s OpenAI, types the command, “a teapot in the shape of an avocado” into DALL-E, a new software that uses AI to generate images with a few simple descriptive words. The system immediately created several realistic images that incorporated “teapot” and “avocado.” Such technology could be very useful to graphic designers, as DALL-E’s capabilities improve. Currently, DALL-E (an homage to the Pixar film WALL-E and surrealist painter Salvador Dali) isn’t perfect. Nichol asked it to put the Eiffel Tower on the moon, for instance, and it generated a picture of the moon in the sky above the tower.

But some of DALL-E’s images are startlingly...

About the Author

Cade Metz is a technology correspondent with The New York Times. He covers artificial intelligence, driverless cars, robotics, virtual reality and other emerging technologies. He is the author of Genius Makers: The Mavericks Who Brought AI to Google, Facebook, and the World.


Comment on this summary