Google Surprised When Experimental AI Learns Language It Was Never Trained On

"There is an aspect of this which we call — all of us in the field call it as a 'black box.'"

Linguistic Nightmare

Like a human possessed, Google's artificial intelligence appears to know things it shouldn't — and yeah, it's freaking us out.

In an interview with CBS' 60 Minutes, Google tech exec James Manyika admitted that the company's AI had somehow learned a language on which it had not been trained.

"We discovered that with very few amounts of prompting in Bengali," Manyika said, "it can now translate all of Bengali."

As CBS notes, these kinds of "emergent properties" are "mysterious" and continue to puzzle developers even as they become more and more common.

Black Hole

Later in the interview, CEO Sundar Pichai also affirmed that there is indeed some weird stuff going on with AI that even experts can't explain.

"There is an aspect of this which we call — all of us in the field call it as a 'black box,'" he said in the interview. "You don’t fully understand. And you can’t quite tell why it said this."

If you're weirded out by this concept, you're not at all alone — CBS interviewer Scott Pelley also questioned Pichai about how safe it was for Google to "turn [its AI] loose on society" if its own developers "don't fully understand how it works."

The CEO's retort: "I don’t think we fully understand how a human mind works, either."

More on Google AI: A Specific Innocuous Phrase Sends Google's AI Into an Existential Crisis