Pascal's mugging and AI safety - Revision history

Issa at 22:16, 17 November 2020

2020-11-17T22:16:48Z

Issa at 21:58, 17 November 2020

2020-11-17T21:58:02Z

Issa at 23:19, 12 November 2020

2020-11-12T23:19:09Z

Issa: Created page with "Existential risk reduction via work on AI safety has occasionally been compared to Pascal's mugging. The critic of AI safety argues that working on AI safety has a ver..."

2020-11-12T23:15:29Z

Created page with "Existential risk reduction via work on AI safety has occasionally been compared to Pascal's mugging. The critic of AI safety argues that working on AI safety has a ver..."

New page

Existential risk reduction via work on [[AI safety]] has occasionally been compared to [[Pascal's mugging]]. The critic of AI safety argues that working on AI safety has a very small probability of a very big payoff, which sounds suspicious.

The standard resolution seems to be:

* Point out that there are different levels of what "very small probability" means. Some people think 1% is very small, whereas in Pascal's mugging we are dealing with astronomically small probabilities such as 1/3^^^3.
* Argue that for probabilities like 1%, standard [[expected value]] calculations work fine.
* Argue that reducing x-risk from AI safety is more like a 1% chance than like an astronomically small chance.

[[Category:AI safety]]

@@ Line 9: / Line 9: @@
 Notably, [[Eliezer Yudkowsky]] has consistently argued against paying up in Pascal's mugging.
-e.g. <ref>https://forum.effectivealtruism.org/posts/zjbxdJbTTmTvrWAX9/tiny-probabilities-of-vast-utilities-concluding-arguments#The__claimed__probabilities_aren_t_that_small</ref>
+e.g. <ref>https://forum.effectivealtruism.org/posts/zjbxdJbTTmTvrWAX9/tiny-probabilities-of-vast-utilities-concluding-arguments#The__claimed__probabilities_aren_t_that_small</ref> <ref>https://slatestarcodex.com/2015/08/12/stop-adding-zeroes/</ref>
 ==References==

← Older revision		Revision as of 21:58, 17 November 2020
Line 8:		Line 8:

	Notably, [[Eliezer Yudkowsky]] has consistently argued against paying up in Pascal's mugging.		Notably, [[Eliezer Yudkowsky]] has consistently argued against paying up in Pascal's mugging.
		+
		+	e.g. <ref>https://forum.effectivealtruism.org/posts/zjbxdJbTTmTvrWAX9/tiny-probabilities-of-vast-utilities-concluding-arguments#The__claimed__probabilities_aren_t_that_small</ref>
		+
		+	==References==
		+
		+	<references/>

	[[Category:AI safety]]		[[Category:AI safety]]

@@ Line 6: / Line 6: @@
 * Argue that for probabilities like 1%, standard [[expected value]] calculations work fine.
 * Argue that reducing x-risk from AI safety is more like a 1% chance than like an astronomically small chance.
 [[Category:AI safety]]