55 citations · 149 across the 10 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2023★ 13 cited
Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?
Markus Anderljung, Julian Hazell
Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent a…
cs.AI2021★ 55 cited
Filling gaps in trustworthy development of AI
Shahar Avin, Haydn Belfield, Miles Brundage +9
The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address t…