142857

• 142857 9 May 2023 6:35 UTC

  1 point

  0

  on: All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [May 2023]

  Given an aligned AGI, to what extent are people ok with letting the AGI modify us? Examples of such modifications include (feel free to add to the list):

  • Curing aging/​illnesses

  • Significantly altering our biological form

  • Converting us to digital life forms

  • Reducing/​Removing the capacity to suffer

  • Giving everyone instant jhanas/​stream entry/​etc.

  • Altering our desires to make them easier to satisfy

  • Increasing our intelligence (although this might be an alignment risk?)

  • Decreasing our intelligence

  • Refactoring our brains entirely

  What exact parts of being “human” do we want to preserve?

• 142857 26 Apr 2023 0:15 UTC

  19 points

  4

  on: My Assess­ment of the Chi­nese AI Safety Community

  A “moonshot idea” I saw brought up is getting Yudkowsky’s Harry Potter fanfiction translated into Chinese (please never ever do this).

  This has already been done, and has pretty good reviews and some discussions.

  I’ve looked through the EA/​Rationalist/​AI Safety forums in China

  If these are public, could you post the links to them?

  there is only one group doing technical alignment work in China

  Do you know the name of the group, and what kinds of approaches they are taking toward technical alignment?

• 142857 16 Mar 2023 2:37 UTC

  1 point

  0

  in reply to: 142857’s comment on: All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [~monthly thread]

  I’ll use this comment to collect things I find.

  LOVE (Learning Other’s Values or Empowerment).

• 142857 14 Mar 2023 6:32 UTC

  1 point

  0

  on: All AGI Safety ques­tions wel­come (es­pe­cially ba­sic ones) [~monthly thread]

  Are there any alignment approaches that try to replicate how children end up loving their parents (or vice versa), except with AI and humans? Alternatively, approaches that look like getting an AI to do Buddhist lovingkindness?

• 142857 12 Sep 2022 22:47 UTC

  4 points

  0

  on: Is there an Ul­ti­mate text ed­i­tor?

  For derendering latex in Emacs, see https://​​github.com/​​io12/​​org-fragtog.

  For drawing images in line, you could try https://​​github.com/​​misohena/​​el-easydraw.

• 142857 12 Sep 2022 5:10 UTC

  2 points

  0

  in reply to: David Rein’s comment on: phone.spin­ning’s Shortform

  I like this idea and think it is worth exploring. It is not even just with training new models; AGI have to worry about misalignment with every self-modification and every interaction with the environment that changes itself.

  Perhaps there are even ways to deter an AGI from self-improvement, by making misalignment more likely.

  Some caveats are:

  • AGI may not take alignment seriously. We already have plenty of examples of general intelligences who don’t.

  • AGI can still increase its capabilities without training new models, e.g. by getting more compute

  • If an AGI decides to solve alignment before significant self-improvement, it will very likely be overtaken by other humans or AGI who don’t care as much about alignment.

Suffi­ciently many Godzillas as an al­ign­ment strategy

• 142857 24 Aug 2022 21:22 UTC

  3 points

  0

  on: In­ter­species diplo­macy as a po­ten­tially pro­duc­tive lens on AGI alignment

  Escape. Invest in space travel and escape the solar system before they arrive.
  If your AI timelines are long, this may be a viable strategy for preserving the human species in the event of unaligned AGI.
  In your AI timelines are short, a budget solution is to just send human brains into space and hope they will be found and revived by other powerful species (hopefully at least one of them is “benevolent”).

[Question] What if we solve AI Safety but no one cares