This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Tags
AF
Login
Refine
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Refine
Random Tag
Contributors
3
NeuralBets
2
Ruben Bloom
Refine
is a conceptual research incubator hosted by
Conjecture
.
Posts tagged
Refine
Most
Relevant
4
15
confusion about alignment requirements
Tamsin Leake
4mo
0
1
11
Refine's Second Blog Post Day
Adam Shimi
5mo
0
1
16
What if we approach AI safety like a technical engineering safety problem
Chin Ze Shen
5mo
0
1
17
Benchmarking Proposals on Risk Scenarios
Paul Bricman
5mo
0
2
48
What I Learned Running Refine
Adam Shimi
2mo
3
1
24
PreDCA: vanessa kosoy's alignment protocol
Tamsin Leake
5mo
1
1
21
the Insulated Goal-Program idea
Tamsin Leake
6mo
1
2
17
Representational Tethers: Tying AI Latents To Human Ones
Paul Bricman
4mo
0
0
21
Epistemic Artefacts of (conceptual) AI alignment research
Nora_Ammann
,
particlemania
5mo
0
2
16
ordering capability thresholds
Tamsin Leake
4mo
0
1
14
goal-program bricks
Tamsin Leake
6mo
0
1
13
Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
4mo
0
2
9
Refine's Third Blog Post Day/Week
Adam Shimi
4mo
0
0
44
Refine: An Incubator for Conceptual Alignment Research Bets
Adam Shimi
10mo
4
0
29
How to Diversify Conceptual Alignment: the Model Behind Refine
Adam Shimi
6mo
2