Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
57 posts
Instrumental Convergence
Deconfusion
Orthogonality Thesis
Gradient Hacking
Gradient Descent
66 posts
Corrigibility
Treacherous Turn
Mild Optimization
Quantilization
Satisficer
Tripwire
205
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
170
Sorting Pebbles Into Correct Heaps
Eliezer Yudkowsky
14y
109
153
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
99
Gradient hacking
evhub
3y
39
93
Goal retention discussion with Eliezer
MaxTegmark
8y
26
88
Coherence arguments imply a force for goal-directed behavior
KatjaGrace
1y
27
72
Instrumental convergence is what makes general intelligence possible
tailcalled
1mo
11
61
Distinguishing claims about training vs deployment
Richard_Ngo
1y
30
58
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
57
Looking Deeper at Deconfusion
adamShimi
1y
13
54
Gradient descent is not just more efficient genetic algorithms
leogao
1y
14
44
The Catastrophic Convergence Conjecture
TurnTrout
2y
15
42
Clarifying Power-Seeking and Instrumental Convergence
TurnTrout
3y
7
40
Hypothesis: gradient descent prefers general circuits
Quintin Pope
10mo
26
118
Soares, Tallinn, and Yudkowsky discuss AGI cognition
So8res
1y
35
111
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
johnswentworth
4mo
8
109
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
105
A broad basin of attraction around human values?
Wei_Dai
8mo
16
73
A Gym Gridworld Environment for the Treacherous Turn
Michaël Trazzi
4y
9
69
Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
TurnTrout
1y
8
65
When to use quantilization
RyanCarey
3y
5
64
Corrigibility Can Be VNM-Incoherent
TurnTrout
1y
24
61
Steam
abramdemski
6mo
9
60
Boeing 737 MAX MCAS as an agent corrigibility failure
shminux
3y
3
52
Corrigibility
paulfchristiano
4y
7
52
Introducing Corrigibility (an FAI research subfield)
So8res
8y
28
46
Cake, or death!
Stuart_Armstrong
10y
13
39
Solve Corrigibility Week
Logan Riggs
1y
21