Analyzing disagreements - Revision history

Issa at 22:52, 8 February 2021

2021-02-08T22:52:49Z

Issa at 00:07, 7 June 2020

2020-06-07T00:07:19Z

Issa at 03:57, 26 April 2020

2020-04-26T03:57:33Z

Issa at 21:30, 25 March 2020

2020-03-25T21:30:17Z

Issa at 21:40, 21 March 2020

2020-03-21T21:40:22Z

Issa at 05:53, 26 February 2020

2020-02-26T05:53:19Z

Issa at 02:42, 24 February 2020

2020-02-24T02:42:22Z

Issa at 23:49, 23 February 2020

2020-02-23T23:49:28Z

Issa at 23:48, 23 February 2020

2020-02-23T23:48:19Z

Issa at 23:19, 23 February 2020

2020-02-23T23:19:53Z

← Older revision		Revision as of 22:52, 8 February 2021
Line 52:		Line 52:

	https://www.econlib.org/archives/2017/12/whats_my_core_m.html/#comment-174163 -- this is an interesting comment about how to identify correct contrarians. but for AI safety arguments the heuristics he uses don't discriminate between the various views, so it's not useful.		https://www.econlib.org/archives/2017/12/whats_my_core_m.html/#comment-174163 -- this is an interesting comment about how to identify correct contrarians. but for AI safety arguments the heuristics he uses don't discriminate between the various views, so it's not useful.
		+
		+	see also [[Justin Shovelain]]'s https://lw2.issarice.com/posts/DYWXntS3ybp8x3cKq/causes-of-disagreements

	==See also==		==See also==

@@ Line 3: / Line 3: @@
 i want to ask similar questions about disagreements, particularly disagreements in ai safety about [[AI timelines]], [[takeoff speed]], [[simple core algorithm of agency]], and so forth. why do people disagree? is it reasonable to have disagreements about this sort of thing? would we have expected these disagreements to arise prior to seeing the discussion?
-one step forward in this kind of thinking is [[eliezer]]'s [http://lesswrong.com/lw/gz/policy_debates_should_not_appear_onesided/ "Policy Debates Should Not Appear One-Sided"], which gives a kind of rule of thumb about ''when'' we should expect debates to be one-sided vs multi-sided. (namely, if it's a simple question of fact, it should appear one-sided, but if it's a policy question with multiple parties who have different stakes and each policy affects people in complicated ways, then we should expect strong arguments on multiple sides)
+one step forward in this kind of thinking is [[eliezer]]'s [http://lesswrong.com/lw/gz/policy_debates_should_not_appear_onesided/ "Policy Debates Should Not Appear One-Sided"], which gives a kind of rule of thumb about ''when'' we should expect debates to be one-sided vs multi-sided. (namely, if it's a simple question of fact, it should appear one-sided, but if it's a policy question with multiple parties who have different stakes and each policy affects people in complicated ways, then we should expect strong arguments on multiple sides.) Given this theory, it feels like AI safety should be a one-sided debate; it's a simple matter of fact, so we shouldn't expect "strong likelihoods pointing in multiple directions". So then what is going on, at the level of probability theory/bayesian math/whatever?
 see also https://www.greaterwrong.com/posts/TGux5Fhcd7GmTfNGC/is-that-your-true-rejection which has the following list:

← Older revision		Revision as of 03:57, 26 April 2020
Line 60:		Line 60:

	<references/>		<references/>
		+
		+	[[Category:AI safety]]

← Older revision		Revision as of 21:30, 25 March 2020
Line 50:		Line 50:

	another point: gary drescher mentions this in ''[[Good and Real]]'', but if you just try to get feedback on/argue about a single piece of your world model, you often get nowhere, because the other side doesn't have all of the other pieces in place in order to place your single point in the right context. So you need your interlocutor to model you holistically, rather than just critique a single part of your views.		another point: gary drescher mentions this in ''[[Good and Real]]'', but if you just try to get feedback on/argue about a single piece of your world model, you often get nowhere, because the other side doesn't have all of the other pieces in place in order to place your single point in the right context. So you need your interlocutor to model you holistically, rather than just critique a single part of your views.
		+
		+	https://www.econlib.org/archives/2017/12/whats_my_core_m.html/#comment-174163 -- this is an interesting comment about how to identify correct contrarians. but for AI safety arguments the heuristics he uses don't discriminate between the various views, so it's not useful.

	==See also==		==See also==

← Older revision		Revision as of 21:40, 21 March 2020
Line 48:		Line 48:

	I want to try doing an imaginary double crux example for AI safety stuff.		I want to try doing an imaginary double crux example for AI safety stuff.
		+
		+	another point: gary drescher mentions this in ''[[Good and Real]]'', but if you just try to get feedback on/argue about a single piece of your world model, you often get nowhere, because the other side doesn't have all of the other pieces in place in order to place your single point in the right context. So you need your interlocutor to model you holistically, rather than just critique a single part of your views.

	==See also==		==See also==

@@ Line 40: / Line 40: @@
 * Wei vs Paul
 * Eliezer vs Hanson
 ==See also==

@@ Line 18: / Line 18: @@
 * Fear that a past mistake could be disproved;
 * Deep self-deception for the sake of pride or other personal benefits.</blockquote>
 also see [https://intelligence.org/files/IEM.pdf IEM], which has:

@@ Line 31: / Line 31: @@
 * the [[gap between chimpanzee and human intelligence]]: [[Eliezer]] sees this as supporting FOOM, i.e. you can make a small tweak to a brain to get much more general intelligence. [[Paul]] sees this as an argument against FOOM, because evolution wasn't optimizing for general intelligence (so that it isn't an example of discontinuous improvement). See [https://lw2.issarice.com/posts.php?id=CjW4axQDqLd2oDCGG#YPodaAtRhN4qJefxb this comment] for more.
 * [[AlphaGo Zero]]: Eliezer sees this as supporting FOOM because a single project got ahead of everyone else and suddenly shot past human performance, and because a "simple" algorithm that generalizes to many settings was able to achieve this performance. Paul sees this as evidence against because Go isn't an economically valuable task so there wasn't enough incentive to get superhuman performance,<ref>https://www.facebook.com/yudkowsky/posts/10155848910529228?comment_id=10155849456079228</ref> and because he sees AlphaGo Zero as being impressive in implementation (rather than basic insights).<ref>https://www.facebook.com/yudkowsky/posts/10155848910529228?comment_id=10155849474514228</ref>
-* whether there is any strong evidence obtainable: Hanson thinks convincing evidence of FOOM can only be obtained once AIs control a substantial fraction of the economy (or something like that), and Eliezer predicts the world will have ended by that point. In other words, if Eliezer is right, then Hanson can never be convinced of this (because we will all be dead by the time the strong evidence comes in).
+* whether there is any strong evidence obtainable: Hanson thinks convincing evidence of FOOM can only be obtained once AIs control a substantial fraction of the economy (or something like that), and Eliezer predicts the world will have ended by that point. In other words, if Eliezer is right, then Hanson can never be convinced of this (because we will all be dead by the time the strong evidence comes in). On the other hand, if Hanson is right, then Eliezer ''can'' be convinced of this (but since Hanson's timelines are long(?) it will be many years until we find out(?)).
 Interesting common disagreements:

@@ Line 37: / Line 37: @@
 * Wei vs Paul
 * Eliezer vs Hanson
 ==References==
 <references/>