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
32
Don't align agents to evaluations of plans
TurnTrout
24d
46
111
What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
johnswentworth
4mo
15
45
Humans aren't fitness maximizers
So8res
2mo
45
49
Mesa-Optimizers vs “Steered Optimizers”
Steven Byrnes
2y
7
69
Bottle Caps Aren't Optimisers
DanielFilan
4y
21
13
Mesa-Optimizers and Over-optimization Failure (Optimizing and Goodhart Effects, Clarifying Thoughts - Part 4)
Davidmanheim
3y
3
44
Aligning a toy model of optimization
paulfchristiano
3y
26
141
Selection vs Control
abramdemski
3y
25
35
Optimization Provenance
Adele Lopez
3y
5
35
Understanding Gradient Hacking
peterbarnett
1y
5
66
Optimization Concepts in the Game of Life
Vika
1y
15
33
Is the term mesa optimizer too narrow?
Matthew Barnett
3y
21
37
Two senses of “optimizer”
Joar Skalse
3y
41
22
Bits of Optimization Can Only Be Lost Over A Distance
johnswentworth
7mo
15
8
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
75
Comments on CAIS
Richard_Ngo
3y
14
18
Motivations, Natural Selection, and Curriculum Engineering
Oliver Sourbut
1y
0
10
A summary of aligning narrowly superhuman models
gugu
10mo
0
14
Quantifying General Intelligence
JasonBrown
6mo
6
41
Ngo and Yudkowsky on scientific reasoning and pivotal acts
Eliezer Yudkowsky
10mo
13
79
How special are human brains among animal brains?
zhukeepa
2y
38
53
Six AI Risk/Strategy Ideas
Wei_Dai
3y
18
140
Reframing Superintelligence: Comprehensive AI Services as General Intelligence
Rohin Shah
3y
75
31
AI Services as a Research Paradigm
VojtaKovarik
2y
12