Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
4 posts
Research Taste
Intellectual Progress (Individual-Level)
Humility
Social & Cultural Dynamics
524 posts
Selection Effects
Epistemic Review
55
Methodological Therapy: An Agenda For Tackling Research Bottlenecks
adamShimi
2mo
6
73
How to do theoretical research, a personal perspective
Mark Xu
4mo
4
65
How I Formed My Own Views About AI Safety
Neel Nanda
9mo
6
305
Alignment Research Field Guide
abramdemski
3y
9
29
Attempts at Forwarding Speed Priors
james.lucassen
2mo
2
23
Epistemic Strategies of Selection Theorems
adamShimi
1y
1
38
Torture and Dust Specks and Joy--Oh my! or: Non-Archimedean Utility Functions as Pseudograded Vector Spaces
Louis_Brown
3y
29
32
AI Alignment Open Thread August 2019
habryka
3y
96
24
Where's the Turing Machine? A step towards Ontology Identification
adamShimi
2y
0
22
Openness Norms in AGI Development
Sublation
2y
4
23
On the falsifiability of hypercomputation, part 2: finite input streams
jessicata
2y
7
25
What are concrete examples of potential "lock-in" in AI research?
Grue_Slinky
3y
6
21
AI Alignment Open Thread October 2019
habryka
3y
58
18
On the falsifiability of hypercomputation
jessicata
2y
4
21
Uncertainty versus fuzziness versus extrapolation desiderata
Stuart_Armstrong
3y
8
19
Theory of Ideal Agents, or of Existing Agents?
johnswentworth
3y
1
19
Best utility normalisation method to date?
Stuart_Armstrong
3y
7
19
False assumptions and leaky abstractions in machine learning and AI safety
David Scott Krueger (formerly: capybaralet)
3y
3