Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
22 posts
Conjecture (org)
Project Announcement
Encultured AI (org)
11 posts
Refine
Analogy
213
Mysteries of mode collapse
janus
1mo
35
186
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
183
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
159
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
123
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13
123
Interpreting Neural Networks through the Polytope Lens
Sid Black
2mo
26
103
What I Learned Running Refine
adamShimi
26d
5
103
Announcing Encultured AI: Building a Video Game
Andrew_Critch
4mo
26
94
Circumventing interpretability: How to defeat mind-readers
Lee Sharkey
5mo
8
85
Conjecture Second Hiring Round
Connor Leahy
27d
0
82
Current themes in mechanistic interpretability research
Lee Sharkey
1mo
3
80
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
78
How to Diversify Conceptual Alignment: the Model Behind Refine
adamShimi
5mo
11
64
Searching for Search
NicholasKees
22d
6
53
I missed the crux of the alignment problem the whole time
zeshen
4mo
7
49
My Thoughts on the ML Safety Course
zeshen
2mo
3
39
the Insulated Goal-Program idea
carado
4mo
3
28
confusion about alignment requirements
carado
2mo
10
27
goal-program bricks
carado
4mo
2
25
Benchmarking Proposals on Risk Scenarios
Paul Bricman
4mo
2
25
(Structural) Stability of Coupled Optimizers
Paul Bricman
2mo
0
24
Steelmining via Analogy
Paul Bricman
4mo
0
24
Embedding safety in ML development
zeshen
1mo
1
23
Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
3mo
0
18
Refine's Third Blog Post Day/Week
adamShimi
3mo
0