LESSWRONGTags
LW

Refine

EditHistory
Discussion (0)
Help improve this page
EditHistory
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
33confusion about alignment requirementsΩ
Tamsin Leake
8mo
Ω
10
4
19Refine's Second Blog Post DayΩ
adamShimi
10mo
Ω
0
3
32What if we approach AI safety like a technical engineering safety problemΩ
zeshen
10mo
Ω
4
3
25Benchmarking Proposals on Risk ScenariosΩ
Paul Bricman
10mo
Ω
2
2
104What I Learned Running RefineΩ
adamShimi
7mo
Ω
5
2
48PreDCA: vanessa kosoy's alignment protocolΩ
Tamsin Leake
10mo
Ω
8
2
39the Insulated Goal-Program ideaΩ
Tamsin Leake
10mo
Ω
4
2
30Epistemic Artefacts of (conceptual) AI alignment researchΩ
Nora_Ammann, particlemania
10mo
Ω
1
2
30Representational Tethers: Tying AI Latents To Human OnesΩ
Paul Bricman
9mo
Ω
0
2
27ordering capability thresholdsΩ
Tamsin Leake
9mo
Ω
0
2
27goal-program bricksΩ
Tamsin Leake
10mo
Ω
2
2
23Refine Blogpost Day #3: The shortforms I did writeΩ
Alexander Gietelink Oldenziel
9mo
Ω
0
2
18Refine's Third Blog Post Day/WeekΩ
adamShimi
9mo
Ω
0
1
137Refine: An Incubator for Conceptual Alignment Research BetsΩ
adamShimi
1y
Ω
13
1
87How to Diversify Conceptual Alignment: the Model Behind RefineΩ
adamShimi
1y
Ω
11
Load More (15/33)
Add Posts