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
239
Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
60
208
Sorting Pebbles Into Correct Heaps
Eliezer Yudkowsky
14y
109
194
Seeking Power is Often Convergently Instrumental in MDPs
TurnTrout
3y
38
101
Gradient hacking
evhub
3y
39
85
Instrumental convergence is what makes general intelligence possible
tailcalled
1mo
11
78
Coherence arguments imply a force for goal-directed behavior
KatjaGrace
1y
27
69
Looking Deeper at Deconfusion
adamShimi
1y
13
61
Goal retention discussion with Eliezer
MaxTegmark
8y
26
59
You can still fetch the coffee today if you're dead tomorrow
davidad
11d
15
58
Distinguishing claims about training vs deployment
Richard_Ngo
1y
30
51
Hypothesis: gradient descent prefers general circuits
Quintin Pope
10mo
26
40
Gradient descent is not just more efficient genetic algorithms
leogao
1y
14
40
The Catastrophic Convergence Conjecture
TurnTrout
2y
15
39
A caveat to the Orthogonality Thesis
Wuschel Schulz
1mo
10
114
Interpretability/Tool-ness/Alignment/Corrigibility are not Composable
johnswentworth
4mo
8
102
Soares, Tallinn, and Yudkowsky discuss AGI cognition
So8res
1y
35
97
A broad basin of attraction around human values?
Wei_Dai
8mo
16
91
Let's See You Write That Corrigibility Tag
Eliezer Yudkowsky
6mo
67
80
A Gym Gridworld Environment for the Treacherous Turn
Michaël Trazzi
4y
9
62
Steam
abramdemski
6mo
9
61
When to use quantilization
RyanCarey
3y
5
61
Satisficers Tend To Seek Power: Instrumental Convergence Via Retargetability
TurnTrout
1y
8
55
Corrigibility Can Be VNM-Incoherent
TurnTrout
1y
24
52
Corrigibility
paulfchristiano
4y
7
48
Boeing 737 MAX MCAS as an agent corrigibility failure
shminux
3y
3
41
Solve Corrigibility Week
Logan Riggs
1y
21
33
Exploring Mild Behaviour in Embedded Agents
Megan Kinniment
5mo
3
33
A toy model of the treacherous turn
Stuart_Armstrong
6y
13