AI ALIGNMENT FORUM
Wikitags
AF

Refine

Written by Ruben Bloom last updated 1st Sep 2022

Refine is a conceptual research incubator hosted by Conjecture.

Posts tagged Refine

1

11Refine's Second Blog Post Day

3y

0

1

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

3y

0

1

17Benchmarking Proposals on Risk Scenarios

3y

0

2

51What I Learned Running Refine

2y

4

0

21Epistemic Artefacts of (conceptual) AI alignment research

Nora_Ammann, particlemania

3y

0

2

17Representational Tethers: Tying AI Latents To Human Ones

3y

0

1

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

Alexander Gietelink Oldenziel

3y

0

2

9Refine's Third Blog Post Day/Week

3y

0

0

45Refine: An Incubator for Conceptual Alignment Research Bets

3y

4

0

29How to Diversify Conceptual Alignment: the Model Behind Refine

3y

2

0

23Refine's First Blog Post Day

3y

0

0

21All the posts I will never write

Alexander Gietelink Oldenziel

3y

2

0

17I missed the crux of the alignment problem the whole time

3y

0

1

23My Thoughts on the ML Safety Course

2y

3

1

12A newcomer’s guide to the technical AI safety field

2y

1