This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
Tags
LW
$
Login
AI Misuse
Edit
History
Subscribe
Discussion
(0)
Help improve this page
Edit
History
Subscribe
Discussion
(0)
Help improve this page
AI Misuse
Random Tag
Contributors
2
Raemon
AI misuse.
Humans using AI in a way that harms humanity.
Posts tagged
AI Misuse
Most Relevant
2
61
Managing catastrophic misuse without robust AIs
Ω
ryan_greenblatt
,
Buck
11mo
Ω
17
2
30
Adversarial Robustness Could Help Prevent Catastrophic Misuse
Ω
aogara
1y
Ω
18
2
17
Distinguishing misuse is difficult and uncomfortable
lemonhope
2y
3
1
89
Covert Malicious Finetuning
Ω
Tony Wang
,
dannyhalawi
5mo
Ω
4
1
36
Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation
Ω
Soroush Pour
,
rusheb
,
Quentin FEUILLADE--MONTIXI
,
Arush
,
scasper
1y
Ω
2
1
23
On excluding dangerous information from training
ShayBenMoshe
1y
5
1
22
Proposal: we should start referring to the risk from unaligned AI as a type of *accident risk*
Christopher King
2y
6
1
18
Proposal: Align Systems Earlier In Training
OneManyNone
2y
0
1
6
How to solve the misuse problem assuming that in 10 years the default scenario is that AGI agents are capable of synthetizing pathogens
jeremtti
13d
0
1
2
Technical Risks of (Lethal) Autonomous Weapons Systems
Heramb
2mo
0