Effective Altruism ForumTopics
EA Forum

Login
Sign Up

AI alignment

EditHistory
Discussion (0)
EditHistory
Discussion (0)
Random Topic
Contributors
2Pablo
2BrownHairedEevee
2MichaelA
2Aaron Gertler
1Leo
Parent Topic: AI safety

AI alignment is research on how to align AI systems with human or moral goals.

Evaluation

80,000 Hours rates AI alignment a "highest priority area": a problem at the top of their ranking of global issues assessed by importance, tractability and neglectedness.[1]

...

(Read More)

Posts tagged AI alignment
Most Relevant
11
1472019 AI Alignment Literature Review and Charity Comparison
Larks
3y
28
10
120Ben Garfinkel: How sure are we about this AI stuff?
Ben Garfinkel, EA Global
4y
17
10
1182018 AI Alignment Literature Review and Charity Comparison
Larks
4y
28
9
123AGI Safety Fundamentals curriculum and application
richard_ngo
1y
20
9
29AI Research Considerations for Human Existential Safety (ARCHES)
Andrew Critch
3y
0
8
63Disentangling arguments for the importance of AI safety
richard_ngo
4y
14
7
127Why AI alignment could be hard with modern deep learning
Ajeya
1y
16
7
11Delegated agents in practice: How companies might end up selling AI services that act on behalf of consumers and coalitions, and what this implies for safety research
Remmelt
2y
0
6
102DeepMind is hiring for the Scalable Alignment and Alignment Teams
Rohin Shah, Geoffrey Irving
7mo
0
6
51My current thoughts on MIRI's "highly reliable agent design" work
Daniel_Dewey
5y
65
5
127Preventing an AI-related catastrophe - Problem profile
Benjamin Hilton, 80000_Hours
3mo
17
5
115The academic contribution to AI safety seems large
Gavin
2y
28
5
107Hiring engineers and researchers to help align GPT-3
Paul_Christiano
2y
19
5
101Why I prioritize moral circle expansion over reducing extinction risk through artificial intelligence alignment
Jacy
5y
72
5
572016 AI Risk Literature Review and Charity Comparison
Larks
6y
22