LESSWRONG
is fundraising!
Tags
LW
$

Refine

EditHistorySubscribe

Help improve this page

EditHistorySubscribe

Help improve this page

Contributors

Refine is a conceptual research incubator hosted by Conjecture.

Posts tagged Refine

4

39confusion about alignment requirements

2y

10

4

19Refine's Second Blog Post Day

2y

0

3

36What if we approach AI safety like a technical engineering safety problem

2y

4

3

25Benchmarking Proposals on Risk Scenarios

2y

2

2

108What I Learned Running Refine

2y

5

2

50PreDCA: vanessa kosoy's alignment protocol

2y

8

2

46the Insulated Goal-Program idea

2y

4

2

31Epistemic Artefacts of (conceptual) AI alignment research

Nora_Ammann, particlemania

2y

1

2

31goal-program bricks

2y

2

2

30Representational Tethers: Tying AI Latents To Human Ones

2y

0

2

27ordering capability thresholds

2y

0

2

23Refine Blogpost Day #3: The shortforms I did write

Alexander Gietelink Oldenziel

2y

0

2

18Refine's Third Blog Post Day/Week

2y

0

1

144Refine: An Incubator for Conceptual Alignment Research Bets

3y

13

1

87How to Diversify Conceptual Alignment: the Model Behind Refine

2y

11