Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
20 posts
Corrigibility
Treacherous Turn
Programming
2017-2019 AI Alignment Prize
Petrov Day
9 posts
Instrumental Convergence
Satisficer
LessWrong Event Transcripts
9
Corrigibility Via Thought-Process Deference
Thane Ruthenis
26d
5
15
On corrigibility and its basin
Donald Hobson
6mo
3
13
Petrov corrigibility
Stuart_Armstrong
4y
10
3
Corrigible omniscient AI capable of making clones
Kaj_Sotala
7y
0
6
An Idea For Corrigible, Recursively Improving Math Oracles
jimrandomh
7y
0
7
A first look at the hard problem of corrigibility
jessicata
7y
0
30
Do what we mean vs. do what we say
Rohin Shah
4y
14
87
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
39
Solve Corrigibility Week
Logan Riggs
1y
21
22
[Linkpost] Treacherous turns in the wild
Mark Xu
1y
6
19
[AN #165]: When large models are more likely to lie
Rohin Shah
1y
0
20
Formalizing Policy-Modification Corrigibility
TurnTrout
1y
6
15
Corrigibility as Constrained Optimisation
Henrik Åslund
3y
3
76
A Gym Gridworld Environment for the Treacherous Turn
Michaël Trazzi
4y
9
56
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
183
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
32
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
227
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
14
MDP models are determined by the agent architecture and the environmental dynamics
TurnTrout
1y
34
60
Environmental Structure Can Cause Instrumental Convergence
TurnTrout
1y
44
33
Clarifying Power-Seeking and Instrumental Convergence
TurnTrout
3y
7
22
Power as Easily Exploitable Opportunities
TurnTrout
2y
5
58
Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
TurnTrout
1y
8