Different senses of claims about AGI - Revision history

Issa at 22:14, 28 April 2020

2020-04-28T22:14:35Z

Issa at 20:42, 28 April 2020

2020-04-28T20:42:33Z

Issa at 03:58, 26 April 2020

2020-04-26T03:58:53Z

Issa at 23:13, 23 February 2020

2020-02-23T23:13:23Z

Issa at 23:12, 23 February 2020

2020-02-23T23:12:56Z

Issa at 23:09, 18 February 2020

2020-02-18T23:09:09Z

Issa: Created page with "when making claims about AGI like "how much compute will AGI use?" or "will AGI be clean or messy?" there are several senses/scenarios of AGI we could be talking about: * cl..."

2020-02-18T02:44:26Z

Created page with "when making claims about AGI like "how much compute will AGI use?" or "will AGI be clean or messy?" there are several senses/scenarios of AGI we could be talking about: * cl..."

New page

when making claims about AGI like "how much compute will AGI use?" or "will AGI be clean or messy?" there are several senses/scenarios of AGI we could be talking about:

* claims about the first AGI that will probably appear
* claims about an ideal aligned AGI
* claims about a theoretically possible "optimal" AGI

@@ Line 4: / Line 4: @@
 * claims about the most likely AGI after it has existed for a while
 * claims about an ideal aligned AGI
 * claims about a theoretically possible "optimal" AGI
 * claims about an AGI that is likely to appear under some given assumptions

← Older revision		Revision as of 03:58, 26 April 2020
Line 8:		Line 8:

	another (possibly same) example is: will understanding the rationality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5]) one could believe this for aligned AI systems, but not believe it for unaligned/arbitrary AI systems.		another (possibly same) example is: will understanding the rationality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5]) one could believe this for aligned AI systems, but not believe it for unaligned/arbitrary AI systems.
		+
		+	[[Category:AI safety]]

← Older revision		Revision as of 23:13, 23 February 2020
Line 7:		Line 7:
	an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.		an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.

−	another example is: will understanding the rationality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5]) one could believe this for aligned AI systems, but not believe it for unaligned/arbitrary AI systems.	+	another (possibly same) example is: will understanding the rationality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5]) one could believe this for aligned AI systems, but not believe it for unaligned/arbitrary AI systems.

← Older revision		Revision as of 23:12, 23 February 2020
Line 6:		Line 6:

	an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.		an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.
		+
		+	another example is: will understanding the rationality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-Dk5LmWMEL55ufkTB5]) one could believe this for aligned AI systems, but not believe it for unaligned/arbitrary AI systems.

← Older revision		Revision as of 23:09, 18 February 2020
Line 4:		Line 4:
	* claims about an ideal aligned AGI		* claims about an ideal aligned AGI
	* claims about a theoretically possible "optimal" AGI		* claims about a theoretically possible "optimal" AGI
		+
		+	an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.

@@ Line 2: / Line 2: @@
 * claims about the first AGI that will probably appear
 * claims about an ideal aligned AGI
 * claims about a theoretically possible "optimal" AGI
 an example is [https://agentfoundations.org/item?id=1228 this comment] by [[Nate]]: "Indeed, if I thought one ''had'' to understand good consequentialist reasoning in order to design a highly capable AI system, I’d be less worried by a decent margin." the general MIRI view that you can get to the first AGI without really understanding anything, whereas to get an aligned AGI you do need to understand things.