AI ALIGNMENT FORUM
Tags
AF

AI Misuse

Settings

•

Applied to Human study on AI spear phishing campaigns by Simon Lermen 14d ago

•

Applied to How to solve the misuse problem assuming that in 10 years the default scenario is that AGI agents are capable of synthetizing pathogens by jeremtti 2mo ago

•

Applied to Technical Risks of (Lethal) Autonomous Weapons Systems by Heramb 3mo ago

•

Applied to Covert Malicious Finetuning by Tony Wang 7mo ago

•

Applied to Managing catastrophic misuse without robust AIs by Ryan Greenblatt 1y ago

•

Applied to Adversarial Robustness Could Help Prevent Catastrophic Misuse by Aidan O'Gara 1y ago

•

Applied to On excluding dangerous information from training by Shay Ben Moshe 1y ago

•

Applied to Scalable And Transferable Black-Box Jailbreaks For Language Models Via Persona Modulation by Soroush Pour 1y ago

•

Applied to Proposal: we should start referring to the risk from unaligned AI as a type of *accident risk* by Christopher King 2y ago

•

Applied to Proposal: Align Systems Earlier In Training by OneManyNone 2y ago

•

Applied to Distinguishing misuse is difficult and uncomfortable by Raymond Arnold 2y ago

Raymond Arnold v1.0.0May 1st 2023 GMT (+56) LW2

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

•

Created by Raymond Arnold at 2y