LESSWRONG
Wikitags
LW

1

AI Misuse

1

Written by Raemon last updated 1st May 2023

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

Posts tagged AI Misuse

2

63Managing catastrophic misuse without robust AIs

ryan_greenblatt, Buck

1y

17

2

30Adversarial Robustness Could Help Prevent Catastrophic Misuse

1y

18

2

17Distinguishing misuse is difficult and uncomfortable

2y

3

1

89Covert Malicious Finetuning

Tony Wang, dannyhalawi

11mo

4

1

79Human study on AI spear phishing campaigns

Simon Lermen, Fred Heiding, Andrew Kao

5mo

8

1

38Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation

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

2y

2

1

23On excluding dangerous information from training

2y

5

1

22Proposal: we should start referring to the risk from unaligned AI as a type of *accident risk*

Christopher King

2y

6

1

18Proposal: Align Systems Earlier In Training

2y

0

1

6How to solve the misuse problem assuming that in 10 years the default scenario is that AGI agents are capable of synthetizing pathogens

6mo

0

1

2Technical Risks of (Lethal) Autonomous Weapons Systems

7mo

0