Home Creators Posts Import Register Favorites Logout
haven't archived this post yet. have a subscription? use the importer!

Content

Newly made Artificial General Intelligences are basically like children, right? So we already know we can teach them how to behave... right?

A video in which I hurt my forehead a bit.

Files

Previews only

Why Not Just: Raise AI Like Kids?

Newly made Artificial General Intelligences are basically like children, right? So we already know we can teach them how to behave, right? Wrong. References to this Computerphile video: https://www.youtube.com/watch?v=tcdVC4e6EV4 and this paper: https://intelligence.org/files/ValueLearningProblem.pdf Thanks to my amazing Patreon Supporters: Sara Tjäder Jason Strack Chad Jones Ichiro Dohi Stefan Skiles Katie Byrne Ziyang Liu Jordan Medina James McCuen Joshua Richardson Fabian Consiglio Jonatan R Øystein Flygt Björn Mosten Michael Greve robertvanduursen The Guru Of Vision Fabrizio Pisani Alexander Hartvig Nielsen Volodymyr Peggy Youell Konstantin Shabashov Almighty Dodd DGJono Matthias Meger Scott Stevens Emilio Alvarez Benjamin Aaron Degenhart Michael Ore Robert Bridges Dmitri Afanasjev Brian Sandberg Einar Ueland Lo Rez C3POehne https://www.patreon.com/robertskmiles

Comments

Jimmy Gaussen

I'm throwing my hat in for another of your drawings! Great video, as always. You manage to strike the perfect balance between rythm and knowledge, with just the right amount of humor. Keep it up. :)

Anonymous

The almost default urge of some folks in anthropomorphizing superintelligence is the biggest error I've seen in AGI safety discussions. Robert, have you thought about Yudkowsky's 'Coherent Extrapolated Volition' as a guiding principle for the value loading problem? I wonder what you think about it.