AI Misuse

TagLast edit: 1 May 2023 17:42 UTC by Raemon

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

Adversarial Robustness Could Help Prevent Catastrophic Misuse

aog11 Dec 2023 19:12 UTC

30 points

18 comments9 min readLW link

Managing catastrophic misuse without robust AIs

ryan_greenblatt and Buck

16 Jan 2024 17:27 UTC

63 points

17 comments11 min readLW link

Distinguishing misuse is difficult and uncomfortable

lemonhope1 May 2023 16:23 UTC

17 points

3 comments1 min readLW link

Proposal: Align Systems Earlier In Training

OneManyNone16 May 2023 16:24 UTC

18 points

0 comments11 min readLW link

Misalignment or misuse? The AGI alignment tradeoff

Max_He-Ho20 Jun 2025 10:43 UTC

3 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Human study on AI spear phishing campaigns

Simon Lermen, Fred Heiding and Andrew Kao

3 Jan 2025 15:11 UTC

81 points

8 comments5 min readLW link

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

Christopher King16 May 2023 15:18 UTC

22 points

6 comments2 min readLW link

On excluding dangerous information from training

ShayBenMoshe17 Nov 2023 11:14 UTC

23 points

5 comments3 min readLW link

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

Seon Gunness3 Jun 2025 20:10 UTC

4 points

0 comments12 min readLW link

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

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

7 Nov 2023 17:59 UTC

38 points

2 comments2 min readLW link

(arxiv.org)

Technical Risks of (Lethal) Autonomous Weapons Systems

Heramb23 Oct 2024 20:41 UTC

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

jeremtti27 Nov 2024 21:17 UTC

6 points

0 comments9 min readLW link

Covert Malicious Finetuning

Tony Wang and dannyhalawi

2 Jul 2024 2:41 UTC

94 points

4 comments3 min readLW link

No comments.