Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
17 posts
Myopia
9 posts
Deceptive Alignment
Deception
107
The Credit Assignment Problem
abramdemski
3y
40
67
Arguments against myopic training
Richard_Ngo
2y
39
65
Why GPT wants to mesa-optimize & how we might change this
John_Maxwell
2y
32
63
Partial Agency
abramdemski
3y
18
57
Open Problems with Myopia
Mark Xu
1y
16
57
AI safety via market making
evhub
2y
45
50
LCDT, A Myopic Decision Theory
adamShimi
1y
51
49
Bayesian Evolving-to-Extinction
abramdemski
2y
13
44
Towards a mechanistic understanding of corrigibility
evhub
3y
26
41
Steering Behaviour: Testing for (Non-)Myopia in Language Models
Evan R. Murphy
15d
16
41
Acceptability Verification: A Research Agenda
David Udell
5mo
0
37
Defining Myopia
abramdemski
3y
18
36
Evan Hubinger on Homogeneity in Takeoff Speeds, Learned Optimization and Interpretability
Michaël Trazzi
1y
0
31
Random Thoughts on Predict-O-Matic
abramdemski
3y
3
119
Monitoring for deceptive alignment
evhub
3mo
7
85
Trying to Make a Treacherous Mesa-Optimizer
MadHatter
1mo
13
64
How likely is deceptive alignment?
evhub
3mo
21
47
Will transparency help catch deception? Perhaps not
Matthew Barnett
3y
5
33
The Speed + Simplicity Prior is probably anti-deceptive
7mo
29
30
Sticky goals: a concrete experiment for understanding deceptive alignment
evhub
3mo
13
17
Framings of Deceptive Alignment
peterbarnett
7mo
6
17
Precursor checking for deceptive alignment
evhub
4mo
0
8
Training Trace Priors
Adam Jermyn
6mo
17