crispweed

• crispweed 30 Oct 2024 21:17 UTC

  1 point

  0

  in reply to: Dave Lindbergh’s comment on: The Align­ment Trap: AI Safety as Path to Power

  There is the point about offensive/​defensive asymmetry..

• crispweed 30 Oct 2024 21:16 UTC

  1 point

  0

  in reply to: crispweed’s comment on: The Align­ment Trap: AI Safety as Path to Power

  how much earlier

  Yeah, good question. I don’t know really.

  and does it matter?

  I think so, because even if pure AI control follows on from human-AI entity control (which would actually be my prediction), I expect the dynamics of human-AI control to very much lead to and accelerate that eventual pure AI control.

  I’m thinking, also, that there is a thing where pure AI entities need to be careful not to ‘tip their hat’. What I mean by this is that pure AI entities will need to be careful not to reveal the extent of their capabilities up until a point where they are actually capable of taking control, whereas human-AI entities can kind of go ahead and play the power game and start to build up control without so much concern about this. (To the average voter, this could just look like more of the same.)

• crispweed 30 Oct 2024 17:03 UTC

  1 point

  0

  in reply to: Steven Byrnes’s comment on: The Align­ment Trap: AI Safety as Path to Power

  Is the sentence “in reality we should expect combined human-AI entities to reach dangerous capabilities before pure artificial intelligence” really true, and if so how much earlier and does it matter? (I lean towards “not necessarily true in the first place, and if true, probably not by much, and it’s not all that important”)

  I guess in my model this is not something that suddenly becomes true at a certain level of capabilities. Instead, I think that the capabilities of human-AI entities become more dangerous in something of a continuous fashion as AI (and the technology for controlling AI) improves.

The Align­ment Trap: AI Safety as Path to Power

• crispweed 14 May 2024 8:41 UTC

  1 point

  0

  on: We might be miss­ing some key fea­ture of AI take­off; it’ll prob­a­bly seem like “we could’ve seen this com­ing”

  In this blog post, I argue that a key feature we might be missing is that dangerous AI could potentially be a lot less capable than current state of the art LLMs, in some ways (specifically, less like a polymath): https://​​upcoder.com/​​21/​​is-there-a-power-play-overhang

  (link post here: https://​​www.lesswrong.com/​​posts/​​7pdCh4MBFT6YXLL2a/​​is-there-a-power-play-overhang )

Is There a Power Play Over­hang?