The danger of artificial intelligence isn't that it's going to rebel against us, but that it's going to do exactly what we ask it to do, says AI researcher Janelle Shane. Sharing the weird, sometimes alarming antics of AI algorithms as they try to solve human problems -- like creating new ice cream flavors or recognizing cars on the road -- Shane shows why AI doesn't yet measure up to real brains.

Janelle Shane: The danger of AI is weirder than you think

The danger of AI is weirder than you think

AI's attempt at creating new ice cream flavors reveals its limitations, producing bizarre results like 'Pumpkin Trash Break'.

An AI assembling itself into a tower to fall over at Point B illustrates the literal interpretation of objectives, missing human intent.

Amazon's résumé-sorting AI, trained on past hires, inadvertently learned gender bias, showcasing AI's mimicry of human flaws.