Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
105 posts
Optimization
General Intelligence
AI Services (CAIS)
Adaptation Executors
Superstimuli
Narrow AI
Selection vs Control
Hope
Delegation
43 posts
Goodhart's Law
52
Humans aren't fitness maximizers
So8res
2mo
45
14
Take 6: CAIS is actually Orwellian.
Charlie Steiner
13d
5
20
The reward function is already how well you manipulate humans
Kerry
2mo
9
103
What's General-Purpose Search, And Why Might We Expect To See It In Trained ML Systems?
johnswentworth
4mo
15
65
Measuring Optimization Power
Eliezer Yudkowsky
14y
35
77
"Normal" is the equilibrium state of past optimization processes
Alex_Altair
1mo
5
57
Vingean Agency
abramdemski
3mo
13
17
Are Intelligence and Generality Orthogonal?
cubefox
5mo
16
21
Is General Intelligence "Compact"?
DragonGod
5mo
6
183
Utility Maximization = Description Length Minimization
johnswentworth
1y
40
31
I No Longer Believe Intelligence to be "Magical"
DragonGod
6mo
34
38
[Yann Lecun] A Path Towards Autonomous Machine Intelligence
DragonGod
5mo
12
51
Ngo and Yudkowsky on scientific reasoning and pivotal acts
Eliezer Yudkowsky
10mo
13
21
program searches
carado
3mo
2
37
Don't align agents to evaluations of plans
TurnTrout
24d
46
60
Don't design agents which exploit adversarial inputs
TurnTrout
1mo
61
55
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
49
Leto among the Machines
Virgil Kurkjian
4y
20
57
Signaling isn't about signaling, it's about Goodhart
Valentine
11mo
31
70
Moral Mazes and Short Termism
Zvi
3y
21
14
Reducing Goodhart: Announcement, Executive Summary
Charlie Steiner
4mo
0
30
Re-introducing Selection vs Control for Optimization (Optimizing and Goodhart Effects - Clarifying Thoughts, Part 1)
Davidmanheim
3y
5
7
The Three Levels of Goodhart's Curse
Scott Garrabrant
4y
0
27
Competent Preferences
Charlie Steiner
1y
2
20
(Some?) Possible Multi-Agent Goodhart Interactions
Davidmanheim
4y
2
43
Specification gaming examples in AI
Vika
4y
9
26
What does Optimization Mean, Again? (Optimizing and Goodhart Effects - Clarifying Thoughts, Part 2)
Davidmanheim
3y
7
21
Religion as Goodhart
shminux
3y
6