LESSWRONGTags
LW

Refine

EditHistorySubscribe
Discussion (0)
Help improve this page
EditHistorySubscribe
Discussion (0)
Help improve this page
Refine
Random Tag
Contributors
3NeuralBets
2Ruby

Refine is a conceptual research incubator hosted by Conjecture.

Posts tagged Refine
4
39confusion about alignment requirements
Ω
Tamsin Leake
1y
Ω
10
4
19Refine's Second Blog Post Day
Ω
adamShimi
1y
Ω
0
3
32What if we approach AI safety like a technical engineering safety problem
Ω
zeshen
1y
Ω
4
3
25Benchmarking Proposals on Risk Scenarios
Ω
Paul Bricman
1y
Ω
2
2
107What I Learned Running Refine
Ω
adamShimi
10mo
Ω
5
2
50PreDCA: vanessa kosoy's alignment protocol
Ω
Tamsin Leake
1y
Ω
8
2
39the Insulated Goal-Program idea
Ω
Tamsin Leake
1y
Ω
4
2
30Representational Tethers: Tying AI Latents To Human Ones
Ω
Paul Bricman
1y
Ω
0
2
30Epistemic Artefacts of (conceptual) AI alignment research
Ω
Nora_Ammann, particlemania
1y
Ω
1
2
27goal-program bricks
Ω
Tamsin Leake
1y
Ω
2
2
27ordering capability thresholds
Ω
Tamsin Leake
1y
Ω
0
2
23Refine Blogpost Day #3: The shortforms I did write
Ω
Alexander Gietelink Oldenziel
1y
Ω
0
2
18Refine's Third Blog Post Day/Week
Ω
adamShimi
1y
Ω
0
1
143Refine: An Incubator for Conceptual Alignment Research Bets
Ω
adamShimi
1y
Ω
13
1
87How to Diversify Conceptual Alignment: the Model Behind Refine
Ω
adamShimi
1y
Ω
11
Load More (15/33)
Add Posts