This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
364
Wikitags
Human-AI Safety
This page is a stub.
Subscribe
Discussion
Subscribe
Discussion
Posts tagged
Human-AI Safety
Most Relevant
681
The Rise of Parasitic AI
Adele Lopez
2mo
178
238
Morality is Scary
Ω
Wei Dai
4y
Ω
116
155
The best simple argument for Pausing AI?
Gary Marcus
4mo
23
120
A broad basin of attraction around human values?
Ω
Wei Dai
4y
Ω
18
107
Two Neglected Problems in Human-AI Safety
Ω
Wei Dai
7y
Ω
25
78
How AI Manipulates—A Case Study
Adele Lopez
25d
25
70
Three AI Safety Related Ideas
Ω
Wei Dai
7y
Ω
38
17
SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research
Roman Leventov
2y
5
151
The Checklist: What Succeeding at AI Safety Will Involve
Ω
Sam Bowman
1y
Ω
50
50
Apply to the Conceptual Boundaries Workshop for AI Safety
Chris Lakin
2y
0
48
Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Ω
Chris Lakin
2y
Ω
3
34
Should we align AI with maternal instinct?
Priyanka Bharadwaj
2mo
15
28
Research Without Permission
Priyanka Bharadwaj
5mo
1
27
Human-AI Complementarity: A Goal for Amplified Oversight
Ω
rishubjain
,
Sophie Bridgers
10mo
Ω
4
19
Live Conversational Threads: Not an AI Notetaker
adiga
5d
0