Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
45 posts
Instrumental Convergence
Orthogonality Thesis
12 posts
Deconfusion
Gradient Hacking
Gradient Descent
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
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
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
40
The Catastrophic Convergence Conjecture
TurnTrout
2y
15
39
A caveat to the Orthogonality Thesis
Wuschel Schulz
1mo
10
34
Empowerment is (almost) All We Need
jacob_cannell
1mo
43
34
Clarifying Power-Seeking and Instrumental Convergence
TurnTrout
3y
7
32
Instrumental convergence in single-agent systems
Edouard Harris
2mo
4
31
Review of 'Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More'
TurnTrout
1y
1
101
Gradient hacking
evhub
3y
39
69
Looking Deeper at Deconfusion
adamShimi
1y
13
51
Hypothesis: gradient descent prefers general circuits
Quintin Pope
10mo
26
40
Gradient descent is not just more efficient genetic algorithms
leogao
1y
14
27
Applications for Deconfusing Goal-Directedness
adamShimi
1y
3
23
Thoughts on gradient hacking
Richard_Ngo
1y
12
17
Approaches to gradient hacking
adamShimi
1y
8
14
Gradient hacking: definitions and examples
Richard_Ngo
5mo
1
14
Some real examples of gradient hacking
Oliver Sourbut
1y
8
12
Why Do AI researchers Rate the Probability of Doom So Low?
Aorou
2mo
6
9
Alex Turner's Research, Comprehensive Information Gathering
adamShimi
1y
3
6
(Extremely) Naive Gradient Hacking Doesn't Work
ojorgensen
9h
0