A short, typed description of a scene is enough to get this software making footage.
How it works: Science reports that the AI uses two neural networks—one to create video, another to assess if it’s realistic in order to improve the first's output. We named these kinds of AIs one of our 10 Breakthrough Technologies of 2018.
What it does: First, the system is trained on footage of activities labelled with descriptions like "playing golf on grass." It can then recreate similar scenes given a snippet of text. Plus, it can make clips combining disparate concepts from training data, such as "sailing on snow."
Why it matters: Automatic generation of video from text could be incredibly useful—for creating huge sets of synthetic training data for autonomous cars, say. It could also lead to some worrying fake content too.
But: The clips are just 32 frames long and 64x64 pixels in size. They're still not wholly convincing, and if they're made larger, accuracy plummets. All that needs fixing to build a useful text-to-video converter.
Why Meta’s latest large language model survived only three days online
Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense.
DeepMind’s game-playing AI has beaten a 50-year-old record in computer science
The new version of AlphaZero discovered a faster way to do matrix multiplication, a core problem in computing that affects thousands of everyday computer tasks.
A bot that watched 70,000 hours of Minecraft could unlock AI’s next big thing
Online videos are a vast and untapped source of training data—and OpenAI says it has a new way to use it.
The White House just unveiled a new AI Bill of Rights
It's the first big step to hold AI to account.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.