Difference between revisions of "Minimal AGI vs task AGI"
(Created page with "* I'm not clear on what the difference is here * See MIRI's strategic plan from end of 2017 where they make this distinction * It seems like MIRI went from: ** a one-step view...") |
|||
(2 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
* I'm not clear on what the difference is here | * I'm not clear on what the difference is here | ||
− | * See MIRI's strategic plan from end of 2017 where they make this distinction | + | * See MIRI's strategic plan from end of 2017<ref>https://intelligence.org/2017/12/01/miris-2017-fundraiser/#3</ref> where they make this distinction |
* It seems like MIRI went from: | * It seems like MIRI went from: | ||
** a one-step view: just build a [[Sovereign]] | ** a one-step view: just build a [[Sovereign]] | ||
Line 6: | Line 6: | ||
** to a three-step view: build a [[minimal aligned AGI]], then task AGI, then Sovereign | ** to a three-step view: build a [[minimal aligned AGI]], then task AGI, then Sovereign | ||
* I'm not sure why "three" is the right number of phases (why not two or four?), and I don't think MIRI has explained this | * I'm not sure why "three" is the right number of phases (why not two or four?), and I don't think MIRI has explained this | ||
+ | |||
+ | see my question here: https://www.greaterwrong.com/posts/hL9ennoEfJXMj7r2D/two-clarifications-about-strategic-background#comment-yNGuxf4Gs27wW72Jp | ||
+ | |||
+ | ==References== | ||
+ | |||
+ | <references/> | ||
+ | |||
+ | [[Category:AI safety]] |
Latest revision as of 19:10, 27 February 2021
- I'm not clear on what the difference is here
- See MIRI's strategic plan from end of 2017[1] where they make this distinction
- It seems like MIRI went from:
- a one-step view: just build a Sovereign
- to a two-step view: build a task-directed AGI first, then go for Sovereign
- to a three-step view: build a minimal aligned AGI, then task AGI, then Sovereign
- I'm not sure why "three" is the right number of phases (why not two or four?), and I don't think MIRI has explained this
see my question here: https://www.greaterwrong.com/posts/hL9ennoEfJXMj7r2D/two-clarifications-about-strategic-background#comment-yNGuxf4Gs27wW72Jp