Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
3 posts
Deceptive Alignment
6 posts
Deception
89
Trying to Make a Treacherous Mesa-Optimizer
MadHatter
1mo
13
40
Sticky goals: a concrete experiment for understanding deceptive alignment
evhub
3mo
13
29
Framings of Deceptive Alignment
peterbarnett
7mo
6
117
Monitoring for deceptive alignment
evhub
3mo
7
80
How likely is deceptive alignment?
evhub
3mo
21
39
Will transparency help catch deception? Perhaps not
Matthew Barnett
3y
5
27
The Speed + Simplicity Prior is probably anti-deceptive
7mo
29
19
Precursor checking for deceptive alignment
evhub
4mo
0
16
Training Trace Priors
Adam Jermyn
6mo
17