Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
16 posts
Myopia
12 posts
Self Fulfilling/Refuting Prophecies
Luck
34
Steering Behaviour: Testing for (Non-)Myopia in Language Models
Evan R. Murphy
15d
16
48
Acceptability Verification: A Research Agenda
David Udell
5mo
0
15
Generative, Episodic Objectives for Safe AI
Michael Glass
2mo
3
53
LCDT, A Myopic Decision Theory
adamShimi
1y
51
60
Open Problems with Myopia
Mark Xu
1y
16
79
The Credit Assignment Problem
abramdemski
3y
40
56
AI safety via market making
evhub
2y
45
47
Why GPT wants to mesa-optimize & how we might change this
John_Maxwell
2y
32
47
Arguments against myopic training
Richard_Ngo
2y
39
56
Partial Agency
abramdemski
3y
18
21
Evan Hubinger on Homogeneity in Takeoff Speeds, Learned Optimization and Interpretability
Michaël Trazzi
1y
0
46
Towards a mechanistic understanding of corrigibility
evhub
3y
26
28
Bayesian Evolving-to-Extinction
abramdemski
2y
13
28
Defining Myopia
abramdemski
3y
18
13
Encouragement to Instill Confidence?
Zvi
10mo
5
32
Random Thoughts on Predict-O-Matic
abramdemski
3y
3
114
Self-fulfilling correlations
PhilGoetz
12y
50
23
Self-Supervised Learning and AGI Safety
Steven Byrnes
3y
9
9
Self-Fulfilling Prophecies Aren't Always About Self-Awareness
John_Maxwell
3y
7
21
Fifty Shades of Self-Fulfilling Prophecy
PhilGoetz
8y
87
21
An example of self-fulfilling spurious proofs in UDT
cousin_it
10y
43
21
Do the 'unlucky' systematically underestimate high-variance strategies?
MBlume
13y
5
6
Luck II: Expecting White Swans
fowlertm
9y
87
8
Omega and self-fulfilling prophecies
RichardKennaway
11y
19
0
Self-fulfilling values of time
KatjaGrace
5y
0
-2
Can chess be a game of luck?
Rune
13y
44