AI ALIGNMENT FORUM
Tags
AF

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

17confusion about alignment requirements

2y

0

1

11Refine's Second Blog Post Day

2y

0

1

18What if we approach AI safety like a technical engineering safety problem

2y

0

1

17Benchmarking Proposals on Risk Scenarios

2y

0

2

51What I Learned Running Refine

2y

4

1

25PreDCA: vanessa kosoy's alignment protocol

2y

1

1

23the Insulated Goal-Program idea

2y

3

0

21Epistemic Artefacts of (conceptual) AI alignment research

Nora_Ammann, particlemania

2y

0

1

16goal-program bricks

2y

0

2

17Representational Tethers: Tying AI Latents To Human Ones

2y

0

2

16ordering capability thresholds

2y

0

1

13Refine Blogpost Day #3: The shortforms I did write

Alexander Gietelink Oldenziel

2y

0

2

9Refine's Third Blog Post Day/Week

2y

0

0

45Refine: An Incubator for Conceptual Alignment Research Bets

3y

4

0

29How to Diversify Conceptual Alignment: the Model Behind Refine

2y

2