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
462
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
243
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
183
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
147
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
135
AGI ruin scenarios are likely (and disjunctive)
So8res
4mo
37
131
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
124
AI Safety "Success Stories"
Wei_Dai
3y
27
123
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
113
Niceness is unnatural
So8res
2mo
18
108
The Main Sources of AI Risk?
Daniel Kokotajlo
3y
25
107
What can the principal-agent literature tell us about AI risk?
Alexis Carlier
2y
31
101
Announcement: AI alignment prize round 3 winners and next round
cousin_it
4y
7
98
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
93
The alignment problem from a deep learning perspective
Richard_Ngo
4mo
13
156
Goodhart Taxonomy
Scott Garrabrant
4y
33
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
55
Does Bayes Beat Goodhart?
abramdemski
3y
26
53
Using expected utility for Good(hart)
Stuart_Armstrong
4y
5
51
Specification gaming examples in AI
Vika
4y
9
51
Defeating Goodhart and the "closest unblocked strategy" problem
Stuart_Armstrong
3y
15
51
Bounding Goodhart's Law
eric_langlois
4y
2
49
Introduction to Reducing Goodhart
Charlie Steiner
1y
10
38
Re-introducing Selection vs Control for Optimization (Optimizing and Goodhart Effects - Clarifying Thoughts, Part 1)
Davidmanheim
3y
5
33
What does Optimization Mean, Again? (Optimizing and Goodhart Effects - Clarifying Thoughts, Part 2)
Davidmanheim
3y
7
33
All I know is Goodhart
Stuart_Armstrong
3y
23
32
Competent Preferences
Charlie Steiner
1y
2
29
Non-Adversarial Goodhart and AI Risks
Davidmanheim
4y
11