x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
LW
Login
Human-AI Safety — LessWrong
Human-AI Safety
This page is a stub.
Subscribe
Discussion
Subscribe
Discussion
Posts tagged
Human-AI Safety
Most Relevant
3
712
The Rise of Parasitic AI
Adele Lopez
3mo
178
2
243
Morality is Scary
Ω
Wei Dai
4y
Ω
116
2
155
The best simple argument for Pausing AI?
Gary Marcus
6mo
23
2
120
A broad basin of attraction around human values?
Ω
Wei Dai
4y
Ω
18
2
108
Two Neglected Problems in Human-AI Safety
Ω
Wei Dai
7y
Ω
25
2
82
How AI Manipulates—A Case Study
Adele Lopez
2mo
27
2
71
Three AI Safety Related Ideas
Ω
Wei Dai
7y
Ω
38
2
58
The Bleeding Mind
Ω
Adele Lopez
5d
Ω
8
2
17
SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research
Roman Leventov
2y
5
1
153
The Checklist: What Succeeding at AI Safety Will Involve
Ω
Sam Bowman
1y
Ω
51
Review
1
50
Apply to the Conceptual Boundaries Workshop for AI Safety
Chris Lakin
2y
0
1
48
Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Ω
Chris Lakin
2y
Ω
3
1
34
Should we align AI with maternal instinct?
Priyanka Bharadwaj
4mo
15
1
28
Research Without Permission
Priyanka Bharadwaj
6mo
1
1
27
Human-AI Complementarity: A Goal for Amplified Oversight
Ω
rishubjain
,
Sophie Bridgers
1y
Ω
4