Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
29 posts
Corrigibility
Instrumental Convergence
Treacherous Turn
Programming
2017-2019 AI Alignment Prize
LessWrong Event Transcripts
Satisficer
Petrov Day
35 posts
AI Risk
56
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
32
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
87
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
9
Corrigibility Via Thought-Process Deference
Thane Ruthenis
26d
5
227
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
58
Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
TurnTrout
1y
8
183
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
60
Environmental Structure Can Cause Instrumental Convergence
TurnTrout
1y
44
39
Solve Corrigibility Week
Logan Riggs
1y
21
15
On corrigibility and its basin
Donald Hobson
6mo
3
20
Formalizing Policy-Modification Corrigibility
TurnTrout
1y
6
85
Announcement: AI alignment prize round 3 winners and next round
cousin_it
4y
7
19
[AN #165]: When large models are more likely to lie
Rohin Shah
1y
0
76
A Gym Gridworld Environment for the Treacherous Turn
Michaël Trazzi
4y
9
429
Counterarguments to the basic AI x-risk case
KatjaGrace
2mo
122
108
AI will change the world, but won’t take it over by playing “3-dimensional chess”.
boazbarak
28d
86
986
AGI Ruin: A List of Lethalities
Eliezer Yudkowsky
6mo
653
83
Niceness is unnatural
So8res
2mo
18
141
Worlds Where Iterative Design Fails
johnswentworth
3mo
26
161
AGI ruin scenarios are likely (and disjunctive)
So8res
4mo
37
61
What does it mean for an AGI to be 'safe'?
So8res
2mo
32
93
The alignment problem from a deep learning perspective
Richard_Ngo
4mo
13
91
Oversight Misses 100% of Thoughts The AI Does Not Think
johnswentworth
4mo
49
51
Eli's review of "Is power-seeking AI an existential risk?"
elifland
2mo
0
31
Instrumental convergence in single-agent systems
Edouard Harris
2mo
4
72
Complex Systems for AI Safety [Pragmatic AI Safety #3]
Dan H
7mo
2
19
Instrumental convergence: scale and physical interactions
Edouard Harris
2mo
0
60
Perform Tractable Research While Avoiding Capabilities Externalities [Pragmatic AI Safety #4]
Dan H
6mo
3