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

18 comments9 min readLW link

Managing catastrophic misuse without robust AIs

ryan_greenblatt and Buck

Jan 16, 2024, 5:27 PM

63 points

17 comments11 min readLW link

Distinguishing misuse is difficult and uncomfortable

lemonhopeMay 1, 2023, 4:23 PM

17 points

3 comments1 min readLW link

Proposal: Align Systems Earlier In Training

OneManyNoneMay 16, 2023, 4:24 PM

18 points

0 comments11 min readLW link

Human study on AI spear phishing campaigns

Simon Lermen, Fred Heiding and Andrew Kao

Jan 3, 2025, 3:11 PM

79 points

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

6 comments2 min readLW link

On excluding dangerous information from training

ShayBenMosheNov 17, 2023, 11:14 AM

23 points

5 comments3 min readLW link

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

Soroush Pour, rusheb, Quentin FEUILLADE--MONTIXI, Arush and scasper

Nov 7, 2023, 5:59 PM

38 points

2 comments2 min readLW link

(arxiv.org)

Technical Risks of (Lethal) Autonomous Weapons Systems

HerambOct 23, 2024, 8:41 PM

2 points

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

0 comments9 min readLW link

Covert Malicious Finetuning

Tony Wang and dannyhalawi

Jul 2, 2024, 2:41 AM

89 points

4 comments3 min readLW link

No comments.