Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
64 posts
AI Risk
Corrigibility
Instrumental Convergence
Treacherous Turn
Programming
2017-2019 AI Alignment Prize
LessWrong Event Transcripts
Satisficer
Petrov Day
19 posts
Goodhart's Law
Modeling People
60
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
98
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
243
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
462
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
113
Niceness is unnatural
So8res
2mo
18
147
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
83
What does it mean for an AGI to be 'safe'?
So8res
2mo
32
135
AGI ruin scenarios are likely (and disjunctive)
So8res
4mo
37
65
Eli's review of "Is power-seeking AI an existential risk?"
elifland
2mo
0
17
Corrigibility Via Thought-Process Deference
Thane Ruthenis
26d
5
40
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
93
The alignment problem from a deep learning perspective
Richard_Ngo
4mo
13
131
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
79
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
4mo
49
18
Reducing Goodhart: Announcement, Executive Summary
Charlie Steiner
4mo
0
49
Introduction to Reducing Goodhart
Charlie Steiner
1y
10
14
Proxy misspecification and the capabilities vs. value learning race
Sam Marks
7mo
1
156
Goodhart Taxonomy
Scott Garrabrant
4y
33
32
Competent Preferences
Charlie Steiner
1y
2
79
Classifying specification problems as variants of Goodhart's Law
Vika
3y
5
72
How does Gradient Descent Interact with Goodhart?
Scott Garrabrant
3y
19
17
Models Modeling Models
Charlie Steiner
1y
5
55
Does Bayes Beat Goodhart?
abramdemski
3y
26
51
Defeating Goodhart and the "closest unblocked strategy" problem
Stuart_Armstrong
3y
15
53
Using expected utility for Good(hart)
Stuart_Armstrong
4y
5
51
Bounding Goodhart's Law
eric_langlois
4y
2
38
Re-introducing Selection vs Control for Optimization (Optimizing and Goodhart Effects - Clarifying Thoughts, Part 1)
Davidmanheim
3y
5
33
All I know is Goodhart
Stuart_Armstrong
3y
23