This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Tags
LW
Login
Human-AI Safety
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Human-AI Safety
Random Tag
Contributors
Posts tagged
Human-AI Safety
Most Relevant
2
193
Morality is Scary
Ω
Wei Dai
2y
Ω
116
2
109
A broad basin of attraction around human values?
Ω
Wei Dai
2y
Ω
17
2
98
Two Neglected Problems in Human-AI Safety
Ω
Wei Dai
5y
Ω
24
2
68
Three AI Safety Related Ideas
Ω
Wei Dai
5y
Ω
38
2
17
SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research
Roman Leventov
5mo
5
1
48
Apply to the Conceptual Boundaries Workshop for AI Safety
Chipmonk
6mo
0
1
47
Safety First: safety before full alignment. The deontic sufficiency hypothesis.
Ω
Chipmonk
5mo
Ω
3
1
5
Out of the Box
jesseduffield
6mo
1
1
3
Public Opinion on AI Safety: AIMS 2023 and 2021 Summary
Jacy Reese Anthis
,
Janet Pauketat
,
Ali
8mo
2
1
2
Will OpenAI also require a "Super Red Team Agent" for its "Superalignment" Project?
Q
Super AGI
2mo
Q
2
1
1
Gaia Network: An Illustrated Primer
Rafael Kaufmann Nedal
,
Roman Leventov
4mo
2
1
1
Let's ask some of the largest LLMs for tips and ideas on how to take over the world
Super AGI
3mo
0
1
-2
A conversation with Claude3 about its consciousness
rife
2mo
3