Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
10 posts
Refine
Analogy
1 posts
58
I missed the crux of the alignment problem the whole time
zeshen
4mo
7
56
My Thoughts on the ML Safety Course
zeshen
2mo
3
37
the Insulated Goal-Program idea
carado
4mo
3
36
Benchmarking Proposals on Risk Scenarios
Paul Bricman
4mo
2
33
Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
3mo
0
32
confusion about alignment requirements
carado
2mo
10
29
goal-program bricks
carado
4mo
2
25
Embedding safety in ML development
zeshen
1mo
1
25
(Structural) Stability of Coupled Optimizers
Paul Bricman
2mo
0
23
Refine's Third Blog Post Day/Week
adamShimi
3mo
0
33
Steelmining via Analogy
Paul Bricman
4mo
0