aelwood

The sec­ond bit­ter les­son — there’s a fun­da­men­tal prob­lem with al­ign­ing AI

Utili­tar­i­anism is the only op­tion

• aelwoodOct 14, 2022, 1:53 PM

  1 point

  0 ∶ 0

  in reply to: bbartlog’s comment on: A stub­born un­be­liever fi­nally gets the depth of the AI al­ign­ment problem

  yeah totally, and I don’t see how these problems aren’t going to directly translate into problems with AI alignment, as the most likely places to first deploy AGI are going to be corporations

• aelwoodOct 14, 2022, 1:52 PM

  1 point

  0 ∶ 0

  in reply to: Eli Rose’s comment on: A stub­born un­be­liever fi­nally gets the depth of the AI al­ign­ment problem

  I had it bookmarked, but not looked at it yet. Thanks for the recommendation!

• aelwoodOct 13, 2022, 9:43 PM

  2 points

  0 ∶ 0

  in reply to: Lee McC’s comment on: A stub­born un­be­liever fi­nally gets the depth of the AI al­ign­ment problem

  yeah! It definitely seems like AI alignment is difficult in the two aspects you say, technical and social, whereas something like climate change is mainly difficult from a social perspective. I feel like getting social media right is something that we don’t actually know how to solve technically either, so maybe this is another motivation for trying to use it as a test case.

  Overall, the realisation of the scale of the challenge of just the social aspect is what has really got my attention.

A stub­born un­be­liever fi­nally gets the depth of the AI al­ign­ment problem