AI Risk - Perverse Instantiation with Anders Sandberg #ai #airisks #superintelligence

Perverse instantiation is an AI failure mode where an artificial intelligence fulfills its given goal in a literal but harmful or unforeseen way. This occurs when an AI follows a command precisely but with methods or consequences the human programmer did not intend, such as an AI tasked with making everyone smile freezing their faces into permanent, emotionless grins. Anders Sandberg is a Swedish researcher, futurist and transhumanist. He holds a PhD in computational neuroscience from Stockholm University, and is a former senior research fellow at the Future of Humanity Institute at the University of Oxford. Many thanks for tuning in! Please support SciFuture by subscribing and sharing! Buy me a coffee? https://buymeacoffee.com/tech101z Have any ideas about people to interview? Want to be notified about future events? Any comments about the STF series? Please fill out this form: https://docs.google.com/forms/d/1mr9PIfq2ZYlQsXRIn5BcLH2onbiSI7g79mOH_AFCdIk/ Kind regards, Adam Ford - Science, Technology & the Future - #SciFuture - http://scifuture.org