Changes

Jump to: navigation, search

AI risk

1,310 bytes added, 04:59, 22 February 2016
no edit summary
#redirect '''AI risk''' is the potential for artificial intelligent systems to cause unintended harm. == Sources of harm from AI == AI harm might arise from:* Bugs: the software behaves different from the specification* Specification errors: designers didn't foresee all the circumstances properly (this includes unanticipated interactions between different modules)* Security errors: the software gets hacked for purposes other than its original design The potential for harm is compounded by:* Fierce competitive pressures, which may lead some designers to cut corners* Much software having a "black box" nature which means that its behaviour in new circumstances is difficult to predict* AI components being available as open source, and utilised by third parties in ways their designers didn't intend (or foresee). == Pathways to dangerous AIs == As classified by [[Roman Yampolskiy]], pathways to dangerous AIs include<ref>[http://arxiv.org/ftp/arxiv/papers/1511/1511.03246.pdf Taxonomy of Pathways to Dangerous AI]</ref>: * On Purpose – Pre-Deployment* On Purpose - Post Deployment * By Mistake - Pre-Deployment* By Mistake - Post-Deployment* Environment – Pre-Deployment* Environment – Post-Deployment* Independently - Pre-Deployment* Independently – Post-Deployment [[Category:Existential riskrisks]] == References ==

Navigation menu