Talk:2429: Exposure Models - Revision history

42.book.addict at 03:42, 16 January 2025

2025-01-16T03:42:22Z

Quillathe Siannodel: /* Does anyone know why this is incomplete? */

2021-04-07T13:13:23Z

‎Does anyone know why this is incomplete?

Quillathe Siannodel: /* Does anyone know why this is incomplete? */

2021-04-07T13:12:36Z

‎Does anyone know why this is incomplete?

Quillathe Siannodel at 14:46, 25 March 2021

2021-03-25T14:46:05Z

141.101.98.96: /* Explained the joke(I think?) */

2021-02-28T19:55:01Z

‎Explained the joke(I think?)

162.158.63.188: /* Explained the joke(I think?) */

2021-02-26T14:19:07Z

‎Explained the joke(I think?)

162.158.63.188 at 14:17, 26 February 2021

2021-02-26T14:17:59Z

Hkmaly at 02:31, 26 February 2021

2021-02-26T02:31:49Z

162.158.63.118: /* Explained the joke(I think?) */

2021-02-26T00:57:26Z

‎Explained the joke(I think?)

172.69.170.120 at 00:44, 26 February 2021

2021-02-26T00:44:18Z

@@ Line 14: / Line 14: @@
 What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120|172.69.170.120]] 00:44, 26 February 2021 (UTC)
 : Well, it's just a guess, but using machine learning models to predict and design the behaviors of machine learning models would make a hyperintelligent system, in the extreme, no?  A big thing, as a software developer, is finding ways to get the computer to do for you, what you would previously do yourself, which can mean getting more and more meta as a habit.  Seems similar to the comic about the tower of babel, to me: touching on research towards hyperintelligence (and current events stemming from use of machine learning) without saying too much outright.  [[Special:Contributions/162.158.63.118|162.158.63.118]] 00:57, 26 February 2021 (UTC)
 Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 02:31, 26 February 2021 (UTC)

← Older revision		Revision as of 13:13, 7 April 2021
Line 20:		Line 20:
	:: It weren't me, but I can see why. There's no signs that any machine learning was employed. The text even stated "This might be the first time machine learning has been mentioned" (not sure that's right), but itself was the first obvious mention of machine learning. A model can just be a simulation (entirely configured by the human creator), and this seems far more likely here, given nothing to say otherwise. [[Special:Contributions/141.101.98.96\|141.101.98.96]] 19:55, 28 February 2021 (UTC)		:: It weren't me, but I can see why. There's no signs that any machine learning was employed. The text even stated "This might be the first time machine learning has been mentioned" (not sure that's right), but itself was the first obvious mention of machine learning. A model can just be a simulation (entirely configured by the human creator), and this seems far more likely here, given nothing to say otherwise. [[Special:Contributions/141.101.98.96\|141.101.98.96]] 19:55, 28 February 2021 (UTC)

−	~~== Does anyone know why this is incomplete? ==~~	+	Edit: Deleted comment. Sorry for the accidental spam. [[User talk:Quillathe Siannodel\|<sup>{)\|(}</sup>]][[User:Quillathe_Siannodel\|Quill]][[User talk:Quillathe Siannodel\|<sub>{)\|(}</sub>]] 14:46, 25 March 2021 (UTC)
−
−	~~Without information, nobody knows which part needs fixing~~. ~~If anyone knows why this is incomplete, please post~~ the ~~reason here~~. If nobody can provide a satisfactory answer, maybe we should consider removing the incomplete tag. '''Note that I am posting this exact same text on other comics of questionable incompleteness. It's not spamming, it's a conscious attempt to clean this category up.''' [[User talk:Quillathe Siannodel\|<sup>{)\|(}</sup>]][[User:Quillathe_Siannodel\|Quill]][[User talk:Quillathe Siannodel\|<sub>{)\|(}</sub>]] 14:46, 25 March 2021 (UTC)

← Older revision		Revision as of 13:12, 7 April 2021
Line 22:		Line 22:
	== Does anyone know why this is incomplete? ==		== Does anyone know why this is incomplete? ==

−	Without information, nobody knows which part needs fixing. If anyone knows why this is incomplete, please post the reason here. If nobody can provide a satisfactory answer, maybe we should consider removing the incomplete tag. '''Note that I am posting this exact same text on other comics of questionable incompleteness. It's not spamming, it's a conscious attempt to clean this category up.'''--[[User:Quillathe Siannodel\|~~Quillathe Siannodel~~]] ([[User talk:Quillathe Siannodel\|~~talk~~]]) 14:46, 25 March 2021 (UTC)	+	Without information, nobody knows which part needs fixing. If anyone knows why this is incomplete, please post the reason here. If nobody can provide a satisfactory answer, maybe we should consider removing the incomplete tag. '''Note that I am posting this exact same text on other comics of questionable incompleteness. It's not spamming, it's a conscious attempt to clean this category up.''' [[User talk:Quillathe Siannodel\|<sup>{)\|(}</sup>]][[User:Quillathe_Siannodel\|Quill]][[User talk:Quillathe Siannodel\|<sub>{)\|(}</sub>]] 14:46, 25 March 2021 (UTC)

← Older revision		Revision as of 14:46, 25 March 2021
Line 19:		Line 19:
	: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. But I guess that's what you're saying. It's just hard to rigorously define "be careful". Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)		: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. But I guess that's what you're saying. It's just hard to rigorously define "be careful". Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)
	:: It weren't me, but I can see why. There's no signs that any machine learning was employed. The text even stated "This might be the first time machine learning has been mentioned" (not sure that's right), but itself was the first obvious mention of machine learning. A model can just be a simulation (entirely configured by the human creator), and this seems far more likely here, given nothing to say otherwise. [[Special:Contributions/141.101.98.96\|141.101.98.96]] 19:55, 28 February 2021 (UTC)		:: It weren't me, but I can see why. There's no signs that any machine learning was employed. The text even stated "This might be the first time machine learning has been mentioned" (not sure that's right), but itself was the first obvious mention of machine learning. A model can just be a simulation (entirely configured by the human creator), and this seems far more likely here, given nothing to say otherwise. [[Special:Contributions/141.101.98.96\|141.101.98.96]] 19:55, 28 February 2021 (UTC)
		+
		+	== Does anyone know why this is incomplete? ==
		+
		+	Without information, nobody knows which part needs fixing. If anyone knows why this is incomplete, please post the reason here. If nobody can provide a satisfactory answer, maybe we should consider removing the incomplete tag. '''Note that I am posting this exact same text on other comics of questionable incompleteness. It's not spamming, it's a conscious attempt to clean this category up.'''--[[User:Quillathe Siannodel\|Quillathe Siannodel]] ([[User talk:Quillathe Siannodel\|talk]]) 14:46, 25 March 2021 (UTC)

← Older revision		Revision as of 19:55, 28 February 2021
Line 18:		Line 18:
	Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)		Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)
	: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. But I guess that's what you're saying. It's just hard to rigorously define "be careful". Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)		: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. But I guess that's what you're saying. It's just hard to rigorously define "be careful". Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)
		+	:: It weren't me, but I can see why. There's no signs that any machine learning was employed. The text even stated "This might be the first time machine learning has been mentioned" (not sure that's right), but itself was the first obvious mention of machine learning. A model can just be a simulation (entirely configured by the human creator), and this seems far more likely here, given nothing to say otherwise. [[Special:Contributions/141.101.98.96\|141.101.98.96]] 19:55, 28 February 2021 (UTC)

← Older revision		Revision as of 14:19, 26 February 2021
Line 17:		Line 17:

	Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)		Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)
−	: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)	+	: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. But I guess that's what you're saying. It's just hard to rigorously define "be careful". Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)

← Older revision		Revision as of 14:17, 26 February 2021
Line 17:		Line 17:

	Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)		Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)
		+	: nah it has more to do with how automatically pursuing goals can discover weird approaches that nobody expects. Somebody removed all the information about machine learning from the article. [[Special:Contributions/162.158.63.188\|162.158.63.188]] 14:17, 26 February 2021 (UTC)

← Older revision		Revision as of 02:31, 26 February 2021
Line 14:		Line 14:
	What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120\|172.69.170.120]] 00:44, 26 February 2021 (UTC)		What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120\|172.69.170.120]] 00:44, 26 February 2021 (UTC)
	: Well, it's just a guess, but using machine learning models to predict and design the behaviors of machine learning models would make a hyperintelligent system, in the extreme, no? A big thing, as a software developer, is finding ways to get the computer to do for you, what you would previously do yourself, which can mean getting more and more meta as a habit. Seems similar to the comic about the tower of babel, to me: touching on research towards hyperintelligence (and current events stemming from use of machine learning) without saying too much outright. [[Special:Contributions/162.158.63.118\|162.158.63.118]] 00:57, 26 February 2021 (UTC)		: Well, it's just a guess, but using machine learning models to predict and design the behaviors of machine learning models would make a hyperintelligent system, in the extreme, no? A big thing, as a software developer, is finding ways to get the computer to do for you, what you would previously do yourself, which can mean getting more and more meta as a habit. Seems similar to the comic about the tower of babel, to me: touching on research towards hyperintelligence (and current events stemming from use of machine learning) without saying too much outright. [[Special:Contributions/162.158.63.118\|162.158.63.118]] 00:57, 26 February 2021 (UTC)
		+
		+
		+	Note that alignment sounds like if the AIs end up being evil. They wouldn't be evil. They would be just fulfilling their purpose. Ignoring anything they don't have in program. So, it's kinda dangerous if we don't train the machine to be careful and not kill someone just because we don't know how it could do it ... -- [[User:Hkmaly\|Hkmaly]] ([[User talk:Hkmaly\|talk]]) 02:31, 26 February 2021 (UTC)

← Older revision		Revision as of 00:57, 26 February 2021
Line 13:		Line 13:

	What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120\|172.69.170.120]] 00:44, 26 February 2021 (UTC)		What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120\|172.69.170.120]] 00:44, 26 February 2021 (UTC)
		+	: Well, it's just a guess, but using machine learning models to predict and design the behaviors of machine learning models would make a hyperintelligent system, in the extreme, no? A big thing, as a software developer, is finding ways to get the computer to do for you, what you would previously do yourself, which can mean getting more and more meta as a habit. Seems similar to the comic about the tower of babel, to me: touching on research towards hyperintelligence (and current events stemming from use of machine learning) without saying too much outright. [[Special:Contributions/162.158.63.118\|162.158.63.118]] 00:57, 26 February 2021 (UTC)

← Older revision		Revision as of 00:44, 26 February 2021
Line 11:		Line 11:

	Strange that Randall is apparently debugging a manual model when machine learning models have passed the Turing test and gptneo was recently open sourced. [[Special:Contributions/162.158.63.170\|162.158.63.170]] 21:54, 25 February 2021 (UTC)		Strange that Randall is apparently debugging a manual model when machine learning models have passed the Turing test and gptneo was recently open sourced. [[Special:Contributions/162.158.63.170\|162.158.63.170]] 21:54, 25 February 2021 (UTC)
		+
		+	What's with the meta-model comment? I don't get it.[[Special:Contributions/172.69.170.120\|172.69.170.120]] 00:44, 26 February 2021 (UTC)