Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
22 posts
Conjecture (org)
12 posts
Refine
164
Mysteries of mode collapse
janus
1mo
35
132
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
118
Connor Leahy on Dying with Dignity, EleutherAI and Conjecture
Michaël Trazzi
5mo
29
105
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
103
What I Learned Running Refine
adamShimi
26d
5
101
Understanding Conjecture: Notes from Connor Leahy interview
Akash
3mo
24
66
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13
63
How to Diversify Conceptual Alignment: the Model Behind Refine
adamShimi
5mo
11
59
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
45
Conjecture Second Hiring Round
Connor Leahy
27d
0
43
Refine's First Blog Post Day
adamShimi
4mo
3
42
The First Filter
adamShimi
24d
5
36
Abstracting The Hardness of Alignment: Unbounded Atomic Optimization
adamShimi
4mo
3
35
Epistemological Vigilance for Alignment
adamShimi
6mo
11
45
I missed the crux of the alignment problem the whole time
zeshen
4mo
7
39
the Insulated Goal-Program idea
carado
4mo
3
32
All the posts I will never write
Alexander Gietelink Oldenziel
4mo
8
24
(Structural) Stability of Coupled Optimizers
Paul Bricman
2mo
0
23
Representational Tethers: Tying AI Latents To Human Ones
Paul Bricman
3mo
0
23
goal-program bricks
carado
4mo
2
22
confusion about alignment requirements
carado
2mo
10
22
Embedding safety in ML development
zeshen
1mo
1
12
Benchmarking Proposals on Risk Scenarios
Paul Bricman
4mo
2
12
Refine's Third Blog Post Day/Week
adamShimi
3mo
0
11
Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
3mo
0
9
Boolean Primitives for Coupled Optimizers
Paul Bricman
2mo
0