How Can Machines Learn Human Values? – with Brian Christian

Brian explores everything that goes wrong when we build AI systems and introduces the people that fix them.
Brian’s book ‘The Alignment Problem’ is available now: ❤️情人节美甲💅教程#20nails://geni.us/24uce
看Q&A here: ❤️情人节美甲💅教程#20nails://youtu.be/Gfd0HraqyHI

Recent years have seen an eruption of concern about machine learning. When the systems we attempt to teach don’t do what we want or what we expect, ethical and potentially existential risks emerge.

Brian Christian is the author of ‘The Most Human Human’, which was named a Wall Street Journal bestseller, a New York Times Editors’ Choice, and a New Yorker favourite book of the year.

This talk was recorded on the 21st January 2021.

—
A very special thank you to our Patreon supporters who help make these videos happen, especially:
Paulina Barren, Elisa, Metzger, Kevin Winoto, Jonathan Killin, János Fekete, Mehdi Razavi, Mark Barden, Taylor Hornby, Rasiel Suarez, Stephan Giersche, William ‘Billy’ Robillard, Scott Edwardsen, Jeffrey Schweitzer, Gou Ranon, Christina Baum, Frances Dunne, jonas.app, Tim Karr, Adam Leos, Michelle J. Zamarron, Andrew Downing, Fairleigh McGill, Alan Latteri, David Crowner, Matt Townsend, Anonymous, Andrew McGhee, Roger Shaw, Robert Reinecke, Paul Brown, Lasse T. Stendan, David Schick, Joe Godenzi, Dave Ostler, Osian Gwyn Williams, David Lindo, Roger Baker, Greg Nagel, and Rebecca Pan.
—

Subscribe for regular science videos: 在家DIY的最佳美甲://bit.ly/RiSubscRibe

The Ri is on Patreon: ❤️情人节美甲💅教程#20nails://www.patreon.com/TheRoyalInstitution
and Twitter: 在家DIY的最佳美甲://twitter.com/ri_science
和脸书: 在家DIY的最佳美甲://www.facebook.com/royalinstitution
和 Tumblr: 在家DIY的最佳美甲://ri-science.tumblr.com/
我们的编辑政策: 在家DIY的最佳美甲://www.rigb.org/home/editor-policy
订阅最新的科学视频: 在家DIY的最佳美甲://bit.ly/RiNewsletter

此页面上的产品链接可能是附属链接，这意味着它不会花费您任何额外费用，但如果您决定通过链接购买，我们可能会赚取少量佣金.