Skip to Content
Artificial intelligence

If we want AI to explain itself, here’s how it should tell us

February 15, 2018

Explainable AI systems aim to make decisions that are easily understood by humans—a laudable goal, but what makes a good explanation?

Testing the best: There’s only one way to figure that out: ask some users. So that’s what researchers from Harvard and Google Brain did, in a series of studies. Test subjects looked at different combinations of inputs, outputs, and explanations for a machine-learning algorithm that was designed to learn the dietary habits or medical conditions of an alien (yes, seriously—alien life was chosen to keep the test subject’s own biases from creeping in). Users then scored the different combinations.

Keep it short: Longer explanations were found to be more difficult to parse than shorter ones—though breaking up the same amount of text into many short lines was somehow better than making people read a few longer lines. As you can tell, the tests examined some pretty basic elements of how to deliver information—but at least it’s a start.

Deep Dive

Artificial intelligence

Geoffrey Hinton tells us why he’s now scared of the tech he helped build

“I have suddenly switched my views on whether these things are going to be more intelligent than us.”

ChatGPT is going to change education, not destroy it

The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better.

Deep learning pioneer Geoffrey Hinton has quit Google

Hinton will be speaking at EmTech Digital on Wednesday.

We are hurtling toward a glitchy, spammy, scammy, AI-powered internet

Large language models are full of security vulnerabilities, yet they’re being embedded into tech products on a vast scale.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at with a list of newsletters you’d like to receive.