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
131
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
101
Announcement: AI alignment prize round 3 winners and next round
cousin_it
4y
7
90
Announcement: AI alignment prize round 4 winners
cousin_it
3y
41
70
A Gym Gridworld Environment for the Treacherous Turn
Michaël Trazzi
4y
9
55
Corrigibility
paulfchristiano
4y
7
41
Can corrigibility be learned safely?
Wei_Dai
4y
115
40
[Linkpost] Treacherous turns in the wild
Mark Xu
1y
6
39
Solve Corrigibility Week
Logan Riggs
1y
21
38
Do what we mean vs. do what we say
Rohin Shah
4y
14
29
Addressing three problems with counterfactual corrigibility: bad bets, defending against backstops, and overconfidence.
RyanCarey
4y
1
28
Corrigibility doesn't always have a good action to take
Stuart_Armstrong
4y
0
27
Petrov corrigibility
Stuart_Armstrong
4y
10
27
[AN #165]: When large models are more likely to lie
Rohin Shah
1y
0
26
Formalizing Policy-Modification Corrigibility
TurnTrout
1y
6
183
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
123
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
82
Environmental Structure Can Cause Instrumental Convergence
TurnTrout
1y
44
80
Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
TurnTrout
1y
8
60
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
51
Clarifying Power-Seeking and Instrumental Convergence
TurnTrout
3y
7
40
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
38
Power as Easily Exploitable Opportunities
TurnTrout
2y
5
32
MDP models are determined by the agent architecture and the environmental dynamics
TurnTrout
1y
34