Refine

TagLast edit: Sep 1, 2022, 2:27 PM by NeuralBets

Refine is a conceptual research incubator hosted by Conjecture.

Refine’s Second Blog Post Day

adamShimiAug 20, 2022, 1:01 PM

19 points

0 comments1 min readLW link

Benchmarking Proposals on Risk Scenarios

Paul BricmanAug 20, 2022, 10:01 AM

25 points

2 comments14 min readLW link

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

zeshenAug 20, 2022, 10:29 AM

36 points

4 comments7 min readLW link

What I Learned Running Refine

adamShimiNov 24, 2022, 2:49 PM

108 points

5 comments4 min readLW link

Refine Blogpost Day #3: The shortforms I did write

Alexander Gietelink OldenzielSep 16, 2022, 9:03 PM

23 points

0 comments1 min readLW link

Refine’s Third Blog Post Day/Week

adamShimiSep 17, 2022, 5:03 PM

18 points

0 comments1 min readLW link

Representational Tethers: Tying AI Latents To Human Ones

Paul BricmanSep 16, 2022, 2:45 PM

30 points

0 comments16 min readLW link

Epistemic Artefacts of (conceptual) AI alignment research

Nora_Ammann and particlemania

Aug 19, 2022, 5:18 PM

31 points

1 comment5 min readLW link

Oversight Leagues: The Training Game as a Feature

Paul BricmanSep 9, 2022, 10:08 AM

20 points

6 comments10 min readLW link

Ideological Inference Engines: Making Deontology Differentiable*

Paul BricmanSep 12, 2022, 12:00 PM

6 points

0 comments14 min readLW link

Levels of goals and alignment

zeshenSep 16, 2022, 4:44 PM

27 points

4 comments6 min readLW link

Cataloguing Priors in Theory and Practice

Paul BricmanOct 13, 2022, 12:36 PM

13 points

8 comments7 min readLW link

Refine: what helped me write more?

Alexander Gietelink OldenzielOct 25, 2022, 2:44 PM

12 points

0 comments2 min readLW link

Embedding safety in ML development

zeshenOct 31, 2022, 12:27 PM

24 points

1 comment18 min readLW link

A newcomer’s guide to the technical AI safety field

zeshenNov 4, 2022, 2:29 PM

42 points

3 comments10 min readLW link

Interlude: But Who Optimizes The Optimizer?

Paul BricmanSep 23, 2022, 3:30 PM

15 points

0 comments10 min readLW link

Summary of ML Safety Course

zeshenSep 27, 2022, 1:05 PM

7 points

0 comments6 min readLW link

My Thoughts on the ML Safety Course

zeshenSep 27, 2022, 1:15 PM

50 points

3 comments17 min readLW link

(Structural) Stability of Coupled Optimizers

Paul BricmanSep 30, 2022, 11:28 AM

25 points

0 comments10 min readLW link

Refine’s First Blog Post Day

adamShimiAug 13, 2022, 10:23 AM

55 points

3 comments1 min readLW link

How I think about alignment

Linda LinseforsAug 13, 2022, 10:01 AM

31 points

11 comments5 min readLW link

Steelmining via Analogy

Paul BricmanAug 13, 2022, 9:59 AM

24 points

0 comments2 min readLW link

(paulbricman.com)

I missed the crux of the alignment problem the whole time

zeshenAug 13, 2022, 10:11 AM

53 points

7 comments3 min readLW link

All the posts I will never write

Alexander Gietelink OldenzielAug 14, 2022, 6:29 PM

54 points

8 comments8 min readLW link

Refine: An Incubator for Conceptual Alignment Research Bets

adamShimiApr 15, 2022, 8:57 AM

144 points

13 comments4 min readLW link

How to Diversify Conceptual Alignment: the Model Behind Refine

adamShimiJul 20, 2022, 10:44 AM

87 points

11 comments8 min readLW link

No comments.