Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
22 posts
Outer Alignment
Mesa-Optimization
20 posts
Neuroscience
Neuromorphic AI
Predictive Processing
Neocortex
Computing Overhang
Planning & Decision-Making
Hansonian Pre-Rationality
Intentionality
Emergent Behavior ( Emergence )
148
Risks from Learned Optimization: Introduction
evhub
3y
42
85
Risks from Learned Optimization: Conclusion and Related Work
evhub
3y
4
78
"Inner Alignment Failures" Which Are Actually Outer Alignment Failures
johnswentworth
2y
38
75
Conditions for Mesa-Optimization
evhub
3y
48
74
Mesa-Search vs Mesa-Control
abramdemski
2y
45
73
An Increasingly Manipulative Newsfeed
Michaël Trazzi
3y
16
71
Human Mimicry Mainly Works When We’re Already Close
johnswentworth
4mo
16
64
Paper: Constitutional AI: Harmlessness from AI Feedback (Anthropic)
LawrenceC
4d
10
58
Agency As a Natural Abstraction
Thane Ruthenis
7mo
9
56
Meta learning to gradient hack
Quintin Pope
1y
11
50
[AN #58] Mesa optimization: what it is, and why we should care
Rohin Shah
3y
9
46
The Steering Problem
paulfchristiano
4y
12
44
Thoughts on gradient hacking
Richard_Ngo
1y
12
38
Formal Solution to the Inner Alignment Problem
michaelcohen
1y
123
151
Matt Botvinick on the spontaneous emergence of learning algorithms
Adam Scholl
2y
87
141
Inner Alignment in Salt-Starved Rats
Steven Byrnes
2y
39
123
Book review: "A Thousand Brains" by Jeff Hawkins
Steven Byrnes
1y
18
114
My computational framework for the brain
Steven Byrnes
2y
26
78
How uniform is the neocortex?
zhukeepa
2y
23
77
Brain-inspired AGI and the "lifetime anchor"
Steven Byrnes
1y
16
75
My take on Jacob Cannell’s take on AGI safety
Steven Byrnes
22d
13
73
Inner alignment in the brain
Steven Byrnes
2y
16
63
What Decision Theory is Implied By Predictive Processing?
johnswentworth
2y
17
61
Multi-agent predictive minds and AI alignment
Jan_Kulveit
4y
18
55
Human instincts, symbol grounding, and the blank-slate neocortex
Steven Byrnes
3y
23
53
Building brain-inspired AGI is infinitely easier than understanding the brain
Steven Byrnes
2y
14
50
Relevant pre-AGI possibilities
Daniel Kokotajlo
2y
7
46
Predictive coding = RL + SL + Bayes + MPC
Steven Byrnes
3y
8