Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
15 posts
Corrigibility
Petrov Day
2 posts
2017-2019 AI Alignment Prize
87
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
49
Corrigibility
paulfchristiano
4y
7
39
Solve Corrigibility Week
Logan Riggs
1y
21
30
Do what we mean vs. do what we say
Rohin Shah
4y
14
29
Can corrigibility be learned safely?
Wei_Dai
4y
115
20
Formalizing Policy-Modification Corrigibility
TurnTrout
1y
6
17
Addressing three problems with counterfactual corrigibility: bad bets, defending against backstops, and overconfidence.
RyanCarey
4y
1
15
On corrigibility and its basin
Donald Hobson
6mo
3
15
Corrigibility as Constrained Optimisation
Henrik Åslund
3y
3
13
Petrov corrigibility
Stuart_Armstrong
4y
10
10
Corrigibility doesn't always have a good action to take
Stuart_Armstrong
4y
0
9
Corrigibility Via Thought-Process Deference
Thane Ruthenis
26d
5
7
A first look at the hard problem of corrigibility
jessicata
7y
0
6
An Idea For Corrigible, Recursively Improving Math Oracles
jimrandomh
7y
0
85
Announcement: AI alignment prize round 3 winners and next round
cousin_it
4y
7
58
Announcement: AI alignment prize round 4 winners
cousin_it
3y
41