Rutherford and Fry on Living with AI: A Future for Humans
Curious Cases
00:00
The Alignment Problem in Artificial Intelligence
Stuart russell gave an example of an alignment problem. And he was thinking specifically about dinner robots and cats. Unfortunately, the robot lacks the understanding that the cat's sentimental value is far more important than its nutritional value. But isn't that just solved by introducing a variable which says, feed the children, rule one? Rule two, don't kill cats. Doesn't that just make the alignment problem go away? Adrian: There's almost no end to how many rules you would need to add.
Transcript
Play full episode
