LESSWRONG
LW

2202
Wikitags

Human-AI Safety

This page is a stub.
Subscribe
Discussion
Subscribe
Discussion
Posts tagged Human-AI Safety
3
695The Rise of Parasitic AI
Adele Lopez
2mo
178
2
242Morality is Scary
Ω
Wei Dai
4y
Ω
116
2
155The best simple argument for Pausing AI?
Gary Marcus
5mo
23
2
120A broad basin of attraction around human values?
Ω
Wei Dai
4y
Ω
18
2
107Two Neglected Problems in Human-AI Safety
Ω
Wei Dai
7y
Ω
25
2
78How AI Manipulates—A Case Study
Adele Lopez
1mo
25
2
70Three AI Safety Related Ideas
Ω
Wei Dai
7y
Ω
38
2
17SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research
Roman Leventov
2y
5
1
151The Checklist: What Succeeding at AI Safety Will Involve
Ω
Sam Bowman
1y
Ω
50
1
50Apply to the Conceptual Boundaries Workshop for AI Safety
Chris Lakin
2y
0
1
48Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Ω
Chris Lakin
2y
Ω
3
1
34Should we align AI with maternal instinct?
Priyanka Bharadwaj
3mo
15
1
28Research Without Permission
Priyanka Bharadwaj
5mo
1
1
27Human-AI Complementarity: A Goal for Amplified Oversight
Ω
rishubjain, Sophie Bridgers
11mo
Ω
4
1
19Live Conversational Threads: Not an AI Notetaker
Ω
adiga
14d
Ω
0
Load More (15/32)
Add Posts