Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
48 posts
Community
Center for Human-Compatible AI (CHAI)
Moral Uncertainty
Regulation and AI Risk
Grants & Fundraising Opportunities
Future of Humanity Institute (FHI)
Population Ethics
Utilitarianism
The SF Bay Area
Future of Life Institute (FLI)
Disagreement
Events (Community)
11 posts
Agent Foundations
Machine Intelligence Research Institute (MIRI)
Cognitive Reduction
Dissolving the Question
190
2018 AI Alignment Literature Review and Charity Comparison
Larks
4y
26
130
2019 AI Alignment Literature Review and Charity Comparison
Larks
3y
18
116
Full-time AGI Safety!
Steven Byrnes
1y
3
105
Call for research on evaluating alignment (funding + advice available)
Beth Barnes
1y
11
95
Apply to the ML for Alignment Bootcamp (MLAB) in Berkeley [Jan 3 - Jan 22]
habryka
1y
4
74
AI Safety and Neighboring Communities: A Quick-Start Guide, as of Summer 2022
Sam Bowman
3mo
2
73
Introducing the ML Safety Scholars Program
Dan H
7mo
2
69
Announcing the Introduction to ML Safety course
Dan H
4mo
6
69
Announcing AI Alignment Awards: $100k research contests about goal misgeneralization & corrigibility
Akash
28d
20
68
Comparing Utilities
abramdemski
2y
31
67
AGI Safety Fundamentals curriculum and application
Richard_Ngo
1y
0
62
Encultured AI Pre-planning, Part 1: Enabling New Benchmarks
Andrew_Critch
4mo
2
62
ARC is hiring!
paulfchristiano
1y
2
61
Apply for research internships at ARC!
paulfchristiano
11mo
0
247
Why Agent Foundations? An Overly Abstract Explanation
johnswentworth
9mo
54
198
The Rocket Alignment Problem
Eliezer Yudkowsky
4y
42
110
What I’ll be doing at MIRI
evhub
3y
6
72
Challenges with Breaking into MIRI-Style Research
Chris_Leong
11mo
15
65
Prize and fast track to alignment research at ALTER
Vanessa Kosoy
3mo
4
59
Another take on agent foundations: formalizing zero-shot reasoning
zhukeepa
4y
20
53
Clarifying the Agent-Like Structure Problem
johnswentworth
2mo
14
41
Grokking the Intentional Stance
jbkjr
1y
20
27
On motivations for MIRI's highly reliable agent design research
jessicata
5y
1
23
Bridging Expected Utility Maximization and Optimization
Whispermute
4mo
5
21
My current take on the Paul-MIRI disagreement on alignability of messy AI
jessicata
5y
0