Pivotal act - Revision history

Issa at 15:15, 26 February 2022

2022-02-26T15:15:33Z

Issa: /* Non-examples */

2022-02-26T15:14:57Z

‎Non-examples

Issa: /* Examples */

2022-02-26T14:41:55Z

‎Examples

Issa: /* Examples */

2022-02-26T14:41:36Z

‎Examples

Issa at 14:32, 26 February 2022

2022-02-26T14:32:23Z

Issa at 14:29, 26 February 2022

2022-02-26T14:29:48Z

Issa: Created page with "A '''pivotal act''' is (putting down my guess here) something that allows a single entity (?) to take over the world? form a singleton? prevent others from taking over the..."

2022-02-26T14:29:00Z

Created page with "A '''pivotal act''' is (putting down my guess here) something that allows a single entity (?) to take over the world? form a singleton? prevent others from taking over the..."

New page

A '''pivotal act''' is (putting down my guess here) something that allows a single entity (?) to take over the world? form a [[singleton]]? prevent others from taking over the world or forming a singleton or achieving AGI?

according to some views of [[AI takeoff]], a pivotal act is an important part of the plan for preventing [[existential doom from AI]].

==External links==

==What links here==

{{Special:WhatLinksHere/{{FULLPAGENAME}}}}

[[Category:AI safety]]

← Older revision		Revision as of 15:15, 26 February 2022
Line 1:		Line 1:
	A '''pivotal act''' is (putting down my guess here) something that allows a single entity (?) to take over the world? form a [[singleton]]? prevent others from taking over the world or forming a singleton or achieving AGI?		A '''pivotal act''' is (putting down my guess here) something that allows a single entity (?) to take over the world? form a [[singleton]]? prevent others from taking over the world or forming a singleton or achieving AGI?
		+
		+	things to clarify: is pivotal act only for "good" actors, or does it also include destroying the world? also pivotal capability vs pivotal act

	according to some views of [[AI takeoff]], a pivotal act is an important part of the plan for preventing [[existential doom from AI]].		according to some views of [[AI takeoff]], a pivotal act is an important part of the plan for preventing [[existential doom from AI]].

← Older revision		Revision as of 15:14, 26 February 2022
Line 9:		Line 9:

	==Non-examples==		==Non-examples==
		+
		+	* make dramatic progress in proving mathematical theorems (without explaining the results to humans) -- not a pivotal capability because it's unclear how to perform a pivotal act<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>

	==External links==		==External links==

@@ Line 6: / Line 6: @@
 * "Build self-replicating open-air nanosystems and use them (only) to melt all GPUs."<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>
-* Make progress on the full (i.e. not restricted to a limited AI system or [[minimal AGI]]) alignment problem faster than humans can<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>
+* Make progress on the full (i.e. not restricted to a limited AI system like present-day systems or [[minimal AGI]]) alignment problem faster than humans can<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>
 ==Non-examples==

← Older revision		Revision as of 14:41, 26 February 2022
Line 6:		Line 6:

	* "Build self-replicating open-air nanosystems and use them (only) to melt all GPUs."<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>		* "Build self-replicating open-air nanosystems and use them (only) to melt all GPUs."<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>
		+	* Make progress on the full (i.e. not restricted to a limited AI system or [[minimal AGI]]) alignment problem faster than humans can<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>

	==Non-examples==		==Non-examples==

← Older revision		Revision as of 14:32, 26 February 2022
Line 6:		Line 6:

	* "Build self-replicating open-air nanosystems and use them (only) to melt all GPUs."<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>		* "Build self-replicating open-air nanosystems and use them (only) to melt all GPUs."<ref>https://www.lesswrong.com/posts/7im8at9PmhbT4JHsW/ngo-and-yudkowsky-on-alignment-difficulty#1_1__Deep_vs__shallow_problem_solving_patterns</ref>
		+
		+	==Non-examples==

	==External links==		==External links==

@@ Line 3: / Line 3: @@
 according to some views of [[AI takeoff]], a pivotal act is an important part of the plan for preventing [[existential doom from AI]].
 ==External links==
 ==What links here==