Empowerment: Concrete Problems in AI Safety part 2

Maybe AI systems would be safer if they avoid gaining too much control over their environment? How might that work? This is a follow-up to this earlier video: The paper ’Concrete Problems in AI Safety’: A book chapter about Empowerment: Prof Brailsford’s Information Theory Videos: 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