RSS

Emer­gent Be­hav­ior ( Emer­gence )

TagLast edit: Oct 26, 2022, 5:07 PM by niplav

Emergent Behavior or emergence occurs when an entity is observed to have certain properties , that its individual parts do not have on their own. Certain properties or behaviors might come about only when the parts that make up that entity interact as a wider whole , or when the number of parts making up that entity reach a certain minimum threshold.

It is hypothesized that an AI system might display emergent properties simply as a function of scale. This is supported by the fact that various complex systems exist in nature that have displayed such emergent properties due to quantitative differences. Examples include :

This raises concerns that due to the quantitative increases in the size of AI models , we might soon hit an unexpected threshold and see unexpected differences in qualitiative behaviors and capabilites. This provides motivations to study complex systems with emergent phenomena to be able to draw inferences for when , and what types of capabilites might emerge.

References

Cri­sis of Faith case study: be­yond re­duc­tion­ism?

MalcolmOceanJun 8, 2023, 6:11 AM
6 points
9 comments19 min readLW link

The Fu­til­ity of Emergence

Eliezer YudkowskyAug 26, 2007, 10:10 PM
107 points
142 comments3 min readLW link

A Bird’s Eye View of the ML Field [Prag­matic AI Safety #2]

May 9, 2022, 5:18 PM
163 points
8 comments35 min readLW link

A Case for Con­scious Sig­nifi­cance rather than Free Will.

James Stephen BrownOct 25, 2024, 11:20 PM
10 points
2 comments6 min readLW link

In­tro­duc­tion to Prag­matic AI Safety [Prag­matic AI Safety #1]

May 9, 2022, 5:06 PM
80 points
3 comments6 min readLW link

Are Emer­gent Abil­ities of Large Lan­guage Models a Mirage? [linkpost]

Matthew BarnettMay 2, 2023, 9:01 PM
53 points
19 comments1 min readLW link
(arxiv.org)

Emer­gent Abil­ities of Large Lan­guage Models [Linkpost]

aogaraAug 10, 2022, 6:02 PM
25 points
2 comments1 min readLW link
(arxiv.org)

Towards a New On­tol­ogy of Intelligence

TaraJun 4, 2024, 8:19 AM
1 point
0 comments3 min readLW link

Tak­ing Away the Guns First: The Fun­da­men­tal Flaw in AI Development

s-iceNov 26, 2024, 10:11 PM
1 point
0 comments17 min readLW link

Im­pli­ca­tions—How Con­scious Sig­nifi­cance Could In­form Our lives

James Stephen BrownNov 26, 2024, 5:42 PM
7 points
0 comments13 min readLW link

In­de­pen­dent re­search ar­ti­cle an­a­lyz­ing con­sis­tent self-re­ports of ex­pe­rience in ChatGPT and Claude

rifeJan 6, 2025, 5:34 PM
4 points
20 comments1 min readLW link
(awakenmoon.ai)

Physics of Ce­les­tial Bodies Ap­plied to So­cial Dynamics

QuanJan 8, 2025, 11:16 PM
1 point
0 comments6 min readLW link

What If AI Rec­og­nized Mean­ing? An In­quiry into “Res­o­nant Recog­ni­tion”

JD___Feb 5, 2025, 9:24 PM
0 points
0 comments2 min readLW link

Com­plex Be­hav­ior from Sim­ple (Sub)Agents

moridinamaelMay 10, 2019, 9:44 PM
113 points
13 comments9 min readLW link1 review

Emer­gence and Con­trol: An ex­am­i­na­tion of our abil­ity to gov­ern the be­hav­ior of in­tel­li­gent systems

meanderingmooseJun 5, 2020, 5:10 PM
1 point
0 comments6 min readLW link

The Real­ity of Emer­gence

DragonGodOct 4, 2017, 8:11 AM
0 points
11 comments5 min readLW link

LINK: Google re­search chief: ‘Emer­gent ar­tifi­cial in­tel­li­gence? Hog­wash!’

ShmiMay 17, 2013, 7:45 PM
6 points
45 comments1 min readLW link

Matt Botv­inick on the spon­ta­neous emer­gence of learn­ing algorithms

Adam SchollAug 12, 2020, 7:47 AM
154 points
87 comments5 min readLW link

Sel­ling Nonapples

Eliezer YudkowskyNov 13, 2008, 8:10 PM
76 points
78 comments7 min readLW link

Linkpost: Are Emer­gent Abil­ities in Large Lan­guage Models just In-Con­text Learn­ing?

Erich_GrunewaldOct 8, 2023, 12:14 PM
12 points
7 comments2 min readLW link
(arxiv.org)

The Dark Side of Cog­ni­tion Hypothesis

Cameron BergOct 3, 2021, 8:10 PM
19 points
1 comment16 min readLW link

A physi­cist’s ap­proach to Ori­gins of Life

pchvykovJun 28, 2022, 3:23 PM
12 points
6 comments16 min readLW link

Bing find­ing ways to by­pass Microsoft’s filters with­out be­ing asked. Is it re­pro­ducible?

Christopher KingFeb 20, 2023, 3:11 PM
27 points
15 comments1 min readLW link

Perform Tractable Re­search While Avoid­ing Ca­pa­bil­ities Ex­ter­nal­ities [Prag­matic AI Safety #4]

May 30, 2022, 8:25 PM
51 points
3 comments25 min readLW link

Can Kauff­man’s NK Boolean net­works make hu­mans swarm?

Yori-92May 8, 2024, 2:09 AM
6 points
2 comments20 min readLW link

Emer­gent Author­ship: Creativity à la Communing

gswonkSep 14, 2024, 7:02 PM
1 point
0 comments3 min readLW link

Emer­gence Is a Univer­sal Non-Zero-Sum Phenomenon.

James Stephen BrownMay 14, 2024, 8:06 AM
6 points
0 comments1 min readLW link
(nonzerosum.games)
No comments.