Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
19 posts
Optimization
Selection vs Control
Distinctions
Adaptation Executors
World Modeling Techniques
10 posts
AI Services (CAIS)
General Intelligence
Narrow AI
37
Don't align agents to evaluations of plans
TurnTrout
24d
46
103
What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
johnswentworth
4mo
15
52
Humans aren't fitness maximizers
So8res
2mo
45
45
Mesa-Optimizers vs “Steered Optimizers”
Steven Byrnes
2y
7
79
Bottle Caps Aren't Optimisers
DanielFilan
4y
21
15
Mesa-Optimizers and Over-optimization Failure (Optimizing and Goodhart Effects, Clarifying Thoughts - Part 4)
Davidmanheim
3y
3
52
Aligning a toy model of optimization
paulfchristiano
3y
26
139
Selection vs Control
abramdemski
3y
25
38
Optimization Provenance
Adele Lopez
3y
5
30
Understanding Gradient Hacking
peterbarnett
1y
5
68
Optimization Concepts in the Game of Life
Vika
1y
15
37
Is the term mesa optimizer too narrow?
Matthew Barnett
3y
21
35
Two senses of “optimizer”
Joar Skalse
3y
41
26
Bits of Optimization Can Only Be Lost Over A Distance
johnswentworth
7mo
15
14
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
76
Comments on CAIS
Richard_Ngo
3y
14
16
Motivations, Natural Selection, and Curriculum Engineering
Oliver Sourbut
1y
0
8
A summary of aligning narrowly superhuman models
gugu
10mo
0
9
Quantifying General Intelligence
JasonBrown
6mo
6
51
Ngo and Yudkowsky on scientific reasoning and pivotal acts
Eliezer Yudkowsky
10mo
13
78
How special are human brains among animal brains?
zhukeepa
2y
38
64
Six AI Risk/Strategy Ideas
Wei_Dai
3y
18
118
Reframing Superintelligence: Comprehensive AI Services as General Intelligence
Rohin Shah
3y
75
30
AI Services as a Research Paradigm
VojtaKovarik
2y
12