Difference between revisions of "Minimal AGI vs task AGI"
Line 12: | Line 12: | ||
<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