Difference between revisions of "Future planning"

From Issawiki
Jump to: navigation, search
 
(40 intermediate revisions by the same user not shown)
Line 1: Line 1:
things to talk about:
+
* the most decision-relevant questions for me right now (everything else should feed into one of these questions):
 +
** AI safety vs something else? right now AI safety seems like the best candidate for the biggest/soonest change, but i want to investigate some other things.
 +
** if AI safety, then what technical agenda seems best? this matters for (1) deciding what to do technical research on, if at all; (2) what technical research to pay attention to/support.
 +
** if AI safety, then what will the end of the world look like (basically this is takeoff speeds + what the most likely failure mode looks like)? (this matters for [[AI prepping|prepping]])
 +
** how likely is the end of the world?
 +
** when will AGI come?
  
* how doomed ML safety approaches are e.g. see discussion [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-32dCL2u6p8L8td9BA here]
+
Example scenarios:
* can MIRI-type research be done in time to help with AGI? see [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5 this comment]
+
 
* prior on difficulty of alignment, and ideas like "if ML-based safety were to have any shot at working, wouldn't we just go all the way and expect the default (no EA intervention) approach to AGI to just produce basically ok outcomes?"
+
{| class="wikitable"
 +
! Name of scenario !! Next big thing? !! AI safety technical agenda !! What will end of the world look like? !! How likely is the world to end? !! When will the world end/reach a singularity/cure aging? || What I should do
 +
|-
 +
| Eliezerian end of world || AGI || MIRI? || FOOM/AI takeover || Highly likely? || 10-20 years? || Don't have kids. Probably don't even bother with wife search. Focus on AI safety research, either field building or figuring out how to contribute to MIRI-like technical work.
 +
|-
 +
| Eliezerian end of world, but longer timelines || AGI || MIRI? || FOOM/AI takeover || Highly likely? || 40 years ||
 +
|-
 +
| Eliezerian end of world, but even longer timelines || AGI || MIRI? || FOOM/AI takeover || Highly likely? || 60 years ||
 +
|-
 +
| Age of em || WBE ||
 +
|-
 +
| Paul's end of world || AGI || ? || || || 20 years? || [[AI prepping]]???
 +
|-
 +
| CAIS
 +
|-
 +
| GPT-3-like limited AI causes big changes in the world
 +
|-
 +
| Great Stagnation (world stays basically the same for the next 100 years) ||
 +
|-
 +
| Super long AI timelines (AI won't come for 100 years) ||
 +
|}

Latest revision as of 18:53, 7 September 2020

  • the most decision-relevant questions for me right now (everything else should feed into one of these questions):
    • AI safety vs something else? right now AI safety seems like the best candidate for the biggest/soonest change, but i want to investigate some other things.
    • if AI safety, then what technical agenda seems best? this matters for (1) deciding what to do technical research on, if at all; (2) what technical research to pay attention to/support.
    • if AI safety, then what will the end of the world look like (basically this is takeoff speeds + what the most likely failure mode looks like)? (this matters for prepping)
    • how likely is the end of the world?
    • when will AGI come?

Example scenarios:

Name of scenario Next big thing? AI safety technical agenda What will end of the world look like? How likely is the world to end? When will the world end/reach a singularity/cure aging? What I should do
Eliezerian end of world AGI MIRI? FOOM/AI takeover Highly likely? 10-20 years? Don't have kids. Probably don't even bother with wife search. Focus on AI safety research, either field building or figuring out how to contribute to MIRI-like technical work.
Eliezerian end of world, but longer timelines AGI MIRI? FOOM/AI takeover Highly likely? 40 years
Eliezerian end of world, but even longer timelines AGI MIRI? FOOM/AI takeover Highly likely? 60 years
Age of em WBE
Paul's end of world AGI ? 20 years? AI prepping???
CAIS
GPT-3-like limited AI causes big changes in the world
Great Stagnation (world stays basically the same for the next 100 years)
Super long AI timelines (AI won't come for 100 years)