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
42
Don't align agents to evaluations of plans
TurnTrout
24d
46
59
Humans aren't fitness maximizers
So8res
2mo
45
95
What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
johnswentworth
4mo
15
206
The ground of optimization
Alex Flint
2y
74
70
Optimization Concepts in the Game of Life
Vika
1y
15
30
Bits of Optimization Can Only Be Lost Over A Distance
johnswentworth
7mo
15
80
Reflective Bayesianism
abramdemski
1y
27
49
Measurement, Optimization, and Take-off Speed
jsteinhardt
1y
4
137
Selection vs Control
abramdemski
3y
25
25
Understanding Gradient Hacking
peterbarnett
1y
5
102
Optimization Amplifies
Scott Garrabrant
4y
12
89
Bottle Caps Aren't Optimisers
DanielFilan
4y
21
41
Mesa-Optimizers vs “Steered Optimizers”
Steven Byrnes
2y
7
60
Aligning a toy model of optimization
paulfchristiano
3y
26
20
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
61
Ngo and Yudkowsky on scientific reasoning and pivotal acts
Eliezer Yudkowsky
10mo
13
77
How special are human brains among animal brains?
zhukeepa
2y
38
96
Reframing Superintelligence: Comprehensive AI Services as General Intelligence
Rohin Shah
3y
75
75
Six AI Risk/Strategy Ideas
Wei_Dai
3y
18
77
Comments on CAIS
Richard_Ngo
3y
14
14
Motivations, Natural Selection, and Curriculum Engineering
Oliver Sourbut
1y
0
29
AI Services as a Research Paradigm
VojtaKovarik
2y
12
4
Quantifying General Intelligence
JasonBrown
6mo
6
6
A summary of aligning narrowly superhuman models
gugu
10mo
0