RSS

AI Misuse

TagLast edit: May 1, 2023, 5:42 PM by Raemon

AI misuse. Humans using AI in a way that harms humanity.

Dist­in­guish­ing mi­suse is difficult and uncomfortable

lemonhopeMay 1, 2023, 4:23 PM
17 points
3 comments1 min readLW link

Manag­ing catas­trophic mi­suse with­out ro­bust AIs

Jan 16, 2024, 5:27 PM
63 points
17 comments11 min readLW link

Ad­ver­sar­ial Ro­bust­ness Could Help Prevent Catas­trophic Misuse

aogDec 11, 2023, 7:12 PM
30 points
18 comments9 min readLW link

How to solve the mi­suse prob­lem as­sum­ing that in 10 years the de­fault sce­nario is that AGI agents are ca­pa­ble of syn­thetiz­ing pathogens

jeremttiNov 27, 2024, 9:17 PM
6 points
0 comments9 min readLW link

Hu­man study on AI spear phish­ing campaigns

Jan 3, 2025, 3:11 PM
79 points
8 comments5 min readLW link

Scal­able And Trans­fer­able Black-Box Jailbreaks For Lan­guage Models Via Per­sona Modulation

Nov 7, 2023, 5:59 PM
38 points
2 comments2 min readLW link
(arxiv.org)

On ex­clud­ing dan­ger­ous in­for­ma­tion from training

ShayBenMosheNov 17, 2023, 11:14 AM
23 points
5 comments3 min readLW link

Pro­posal: Align Sys­tems Ear­lier In Training

OneManyNoneMay 16, 2023, 4:24 PM
18 points
0 comments11 min readLW link

Pro­posal: we should start refer­ring to the risk from un­al­igned AI as a type of *ac­ci­dent risk*

Christopher KingMay 16, 2023, 3:18 PM
22 points
6 comments2 min readLW link

Covert Mal­i­cious Finetuning

Jul 2, 2024, 2:41 AM
89 points
4 comments3 min readLW link

Tech­ni­cal Risks of (Lethal) Au­tonomous Weapons Systems

HerambOct 23, 2024, 8:41 PM
2 points
0 comments1 min readLW link
(encodejustice.org)
No comments.