AI ALIGNMENT FORUM
AF

Multiagent Models of Mind — AI Alignment Forum

Multiagent Models of Mind

Jan 16, 2019 by Kaj_Sotala

A sequence of posts which tries to break down the functioning of the brain into a number of subsystems, communicating in part through the global neuronal workspace of consciousness.

19Sequence introduction: non-agent and multiagent models of mind

Kaj_Sotala

27Book Summary: Consciousness and the Brain

Kaj_Sotala

31Building up to an Internal Family Systems model

Kaj_Sotala

16Subagents, introspective awareness, and blending

Kaj_Sotala

21Subagents, akrasia, and coherence in humans

Kaj_Sotala

21Integrating disagreeing subagents

Kaj_Sotala

12Subagents, neural Turing machines, thought selection, and blindspots

Kaj_Sotala

14Subagents, trauma and rationality

Kaj_Sotala

22System 2 as working-memory augmented System 1 reasoning

Kaj_Sotala

32Book summary: Unlocking the Emotional Brain

Kaj_Sotala

18A mechanistic model of meditation

Kaj_Sotala

23A non-mystical explanation of insight meditation and the three characteristics of existence: introduction and preamble

Kaj_Sotala

13A non-mystical explanation of "no-self" (three characteristics series)

Kaj_Sotala

19Craving, suffering, and predictive processing (three characteristics series)

Kaj_Sotala

13From self to craving (three characteristics series)

Kaj_Sotala

12On the construction of the self

Kaj_Sotala

9Three characteristics: impermanence

Kaj_Sotala

11Beliefs as emotional strategies

Kaj_Sotala

20My current take on Internal Family Systems “parts”

Kaj_Sotala

25Goodhart's Law inside the human mind

Kaj_Sotala

17Romance, misunderstanding, social stances, and the human LLM

Kaj_Sotala

17Quick thoughts on the implications of multi-agent views of mind on AI takeover

Kaj_Sotala