Coherence and goal-directed agency discussion - Revision history

Issa at 19:09, 27 February 2021

2021-02-27T19:09:05Z

Issa at 08:39, 8 March 2020

2020-03-08T08:39:13Z

Issa at 08:14, 8 March 2020

2020-03-08T08:14:45Z

Issa at 08:12, 8 March 2020

2020-03-08T08:12:52Z

Issa at 22:36, 1 March 2020

2020-03-01T22:36:37Z

Issa at 03:47, 27 February 2020

2020-02-27T03:47:00Z

Issa at 03:40, 27 February 2020

2020-02-27T03:40:54Z

Issa: Created page with "https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw https://www.greaterwrong.com/posts/NxF5G6..."

2020-02-27T03:30:43Z

Created page with "https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw https://www.greaterwrong.com/posts/NxF5G6..."

New page

https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw

https://www.greaterwrong.com/posts/NxF5G6CJiof6cemTw/coherence-arguments-do-not-imply-goal-directed-behavior

https://www.greaterwrong.com/posts/9zpT9dikrrebdq3Jf/will-humans-build-goal-directed-agents

https://www.greaterwrong.com/posts/tHxXdAn8Yuiy9y2pZ/ai-safety-without-goal-directed-behavior

https://www.greaterwrong.com/posts/TE5nJ882s5dCMkBB8/conclusion-to-the-sequence-on-value-learning

← Older revision		Revision as of 19:09, 27 February 2021
Line 20:		Line 20:
	* [[Comparison of terms related to agency]]		* [[Comparison of terms related to agency]]
	* [[List of terms used to describe the intelligence of an agent]]		* [[List of terms used to describe the intelligence of an agent]]
		+
		+	[[Category:AI safety]]

← Older revision		Revision as of 08:39, 8 March 2020
Line 1:		Line 1:
−	One of the "big discussions" that has been taking place in AI safety in 2018–2020 is about [[coherence argument]]s and [[goal-directed]] agency. Some of the topics in this discussion are:	+	One of the "[[List of big discussions in AI alignment\|big discussions]]" that has been taking place in AI safety in 2018–2020 is about [[coherence argument]]s and [[goal-directed]] agency. Some of the topics in this discussion are:

	* What point was [[Eliezer]] trying to make when bringing up coherence arguments?		* What point was [[Eliezer]] trying to make when bringing up coherence arguments?

← Older revision		Revision as of 08:14, 8 March 2020
Line 1:		Line 1:
−	One of the "big discussions" that has been taking place in AI safety in 2018 ~~and 2019~~ is about [[coherence argument]]s and [[goal-directed]] agency. Some of the topics in this discussion are:	+	One of the "big discussions" that has been taking place in AI safety in 2018–2020 is about [[coherence argument]]s and [[goal-directed]] agency. Some of the topics in this discussion are:

	* What point was [[Eliezer]] trying to make when bringing up coherence arguments?		* What point was [[Eliezer]] trying to make when bringing up coherence arguments?

@@ Line 4: / Line 4: @@
 * Will the first AGI systems we build be goal-directed?
 * Are utility maximizers goal-directed?
-* What are the differences and implication structure among intelligence, goal-directedness, expected utility maximizer, coherent?
+* What are the differences and implication structure among intelligence, goal-directedness, expected utility maximizer, coherent, "EU maximizer + X" (for various values of X like "can convert extra resources into additional utility", "has a typical reward function", "has a simple reward function", "wasn't specifically optimized away from goal-directedness")?
 https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw

← Older revision		Revision as of 22:36, 1 March 2020
Line 15:		Line 15:

	https://www.greaterwrong.com/posts/TE5nJ882s5dCMkBB8/conclusion-to-the-sequence-on-value-learning		https://www.greaterwrong.com/posts/TE5nJ882s5dCMkBB8/conclusion-to-the-sequence-on-value-learning
		+
		+	==See also==
		+
		+	* [[Comparison of terms related to agency]]
		+	* [[List of terms used to describe the intelligence of an agent]]

← Older revision		Revision as of 03:40, 27 February 2020
Line 1:		Line 1:
		+	One of the "big discussions" that has been taking place in AI safety in 2018 and 2019 is about [[coherence argument]]s and [[goal-directed]] agency. Some of the topics in this discussion are:
		+
		+	* What point was [[Eliezer]] trying to make when bringing up coherence arguments?
		+	* Will the first AGI systems we build be goal-directed?
		+	* Are utility maximizers goal-directed?
		+
	https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw		https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw