RSS

AI Misuse

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

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

Ad­ver­sar­ial Ro­bust­ness Could Help Prevent Catas­trophic Misuse

aogDec 11, 2023, 7:12 PM
30 points

9 votes

Overall karma indicates overall quality.

18 comments9 min readLW link

Manag­ing catas­trophic mi­suse with­out ro­bust AIs

Jan 16, 2024, 5:27 PM
63 points

23 votes

Overall karma indicates overall quality.

17 comments11 min readLW link

Dist­in­guish­ing mi­suse is difficult and uncomfortable

lemonhopeMay 1, 2023, 4:23 PM
17 points

10 votes

Overall karma indicates overall quality.

3 comments1 min readLW link

Pro­posal: Align Sys­tems Ear­lier In Training

OneManyNoneMay 16, 2023, 4:24 PM
18 points

8 votes

Overall karma indicates overall quality.

0 comments11 min readLW link

Misal­ign­ment or mi­suse? The AGI al­ign­ment tradeoff

Max_He-HoJun 20, 2025, 10:43 AM
3 points

2 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(forum.effectivealtruism.org)

Hu­man study on AI spear phish­ing campaigns

Jan 3, 2025, 3:11 PM
81 points

35 votes

Overall karma indicates overall quality.

8 comments5 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

15 votes

Overall karma indicates overall quality.

6 comments2 min readLW link

On ex­clud­ing dan­ger­ous in­for­ma­tion from training

ShayBenMosheNov 17, 2023, 11:14 AM
23 points

11 votes

Overall karma indicates overall quality.

5 comments3 min readLW link

Vi­sual Prompt In­jec­tions: Re­sults on test­ing AI spam-defense and AI vuln­er­a­bil­ity to de­cep­tive web ads.

Seon GunnessJun 3, 2025, 8:10 PM
4 points

4 votes

Overall karma indicates overall quality.

0 comments12 min readLW link

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

Nov 7, 2023, 5:59 PM
38 points

22 votes

Overall karma indicates overall quality.

2 comments2 min readLW link
(arxiv.org)

Tech­ni­cal Risks of (Lethal) Au­tonomous Weapons Systems

HerambOct 23, 2024, 8:41 PM
2 points

1 vote

Overall karma indicates overall quality.

0 comments1 min readLW link
(encodejustice.org)

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

4 votes

Overall karma indicates overall quality.

0 comments9 min readLW link

Covert Mal­i­cious Finetuning

Jul 2, 2024, 2:41 AM
94 points

41 votes

Overall karma indicates overall quality.

4 comments3 min readLW link
No comments.