Difference between revisions of "Christiano's operationalization of slow takeoff"
| Line 1: | Line 1: | ||
In a 2018 blog post, [[Paul Christiano]] provided the following operationalization of [[slow takeoff]]: "There will be a complete 4 year interval in which world output doubles, before the first 1 year interval in which world output doubles. (Similarly, we’ll see an 8 year doubling before a 2 year doubling, etc.)"<ref>https://sideways-view.com/2018/02/24/takeoff-speeds/</ref> Subsequently, this operationalization has been cited by many others in discussions of [[AI takeoff]]. | In a 2018 blog post, [[Paul Christiano]] provided the following operationalization of [[slow takeoff]]: "There will be a complete 4 year interval in which world output doubles, before the first 1 year interval in which world output doubles. (Similarly, we’ll see an 8 year doubling before a 2 year doubling, etc.)"<ref>https://sideways-view.com/2018/02/24/takeoff-speeds/</ref> Subsequently, this operationalization has been cited by many others in discussions of [[AI takeoff]]. | ||
| + | |||
| + | ==External links== | ||
| + | |||
| + | * https://www.greaterwrong.com/posts/AfGmsjGPXN97kNp57/arguments-about-fast-takeoff/comment/ZyJwKwDrX5jWujXxo | ||
==References== | ==References== | ||
Revision as of 23:06, 25 February 2021
In a 2018 blog post, Paul Christiano provided the following operationalization of slow takeoff: "There will be a complete 4 year interval in which world output doubles, before the first 1 year interval in which world output doubles. (Similarly, we’ll see an 8 year doubling before a 2 year doubling, etc.)"[1] Subsequently, this operationalization has been cited by many others in discussions of AI takeoff.
