Dylan Hadfield-Menell, UC Berkeley/MIT: The value alignment problem in AI
Generally Intelligent
00:00
I Think There's a Lot of Intelligence in How We Manage the Optimization Component of Ourselves
I think there's a lot of intelligence in how we manage the optimization component of ourselves and making things worse. I think that is the ultimate dream as a researcher, is things that you didn't realize before, but then seem so obvious you can't imagine not thinking them. In this case, the big thing that we're applying that makes me think there might be useful insight here is the a i field has been working on, building prototypes for a very real sense.
Play episode from 30:36
Transcript
