AI ALIGNMENT FORUM
AF

Wikitags

Refine

Edited by Ruby last updated 1st Sep 2022

Refine is a conceptual research incubator hosted by Conjecture.

Subscribe
Subscribe
Discussion0
Discussion0
Posts tagged Refine
11Refine's Second Blog Post Day
adamShimi
3y
0
18What if we approach AI safety like a technical engineering safety problem
zeshen
3y
0
17Benchmarking Proposals on Risk Scenarios
Paul Bricman
3y
0
51What I Learned Running Refine
adamShimi
3y
4
21Epistemic Artefacts of (conceptual) AI alignment research
Nora_Ammann, particlemania
3y
0
17Representational Tethers: Tying AI Latents To Human Ones
Paul Bricman
3y
0
13Refine Blogpost Day #3: The shortforms I did write
Alexander Gietelink Oldenziel
3y
0
9Refine's Third Blog Post Day/Week
adamShimi
3y
0
45Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
3y
4
29How to Diversify Conceptual Alignment: the Model Behind Refine
adamShimi
3y
2
23Refine's First Blog Post Day
adamShimi
3y
0
21All the posts I will never write
Alexander Gietelink Oldenziel
3y
2
17I missed the crux of the alignment problem the whole time
zeshen
3y
0
23My Thoughts on the ML Safety Course
zeshen
3y
3
12A newcomer’s guide to the technical AI safety field
zeshen
3y
1
Load More (15/24)
Add Posts