This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Wikitags
AF
Login
Subscribe
Discussion
0
Refine
Subscribe
Discussion
0
Written by
Ruben Bloom
last updated
1st Sep 2022
Refine
is a conceptual research incubator hosted by
Conjecture
.
Posts tagged
Refine
Most Relevant
1
11
Refine's Second Blog Post Day
Adam Shimi
3y
0
1
18
What if we approach AI safety like a technical engineering safety problem
Chin Ze Shen
3y
0
1
17
Benchmarking Proposals on Risk Scenarios
Paul Bricman
3y
0
2
51
What I Learned Running Refine
Adam Shimi
2y
4
0
21
Epistemic Artefacts of (conceptual) AI alignment research
Nora_Ammann
,
particlemania
3y
0
2
17
Representational Tethers: Tying AI Latents To Human Ones
Paul Bricman
3y
0
1
13
Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
3y
0
2
9
Refine's Third Blog Post Day/Week
Adam Shimi
3y
0
0
45
Refine: An Incubator for Conceptual Alignment Research Bets
Adam Shimi
3y
4
0
29
How to Diversify Conceptual Alignment: the Model Behind Refine
Adam Shimi
3y
2
0
23
Refine's First Blog Post Day
Adam Shimi
3y
0
0
21
All the posts I will never write
Alexander Gietelink Oldenziel
3y
2
0
17
I missed the crux of the alignment problem the whole time
Chin Ze Shen
3y
0
1
23
My Thoughts on the ML Safety Course
Chin Ze Shen
2y
3
1
12
A newcomer’s guide to the technical AI safety field
Chin Ze Shen
2y
1