Stuart Armstrong on Reduced Impact AI

Sunday, April 24, 2016

Stuart Armstrong on Reduced Impact AI


Videos

According to AI researcher Stuart Armstrong, if we can define what artificial intelligence is, and make it work, we don't have to solve the so-called AI-control problem. 

Stuart Armstrong’s research at the Future of Humanity Institute centres on formal decision theory, general existential risk, the risks and possibilities of Artificial Intelligence (AI), assessing expertise and predictions, and anthropic (self-locating) probability.

Related articles
Armstong has been working on several methods of analysing the likelihood of certain outcomes and in making decisions under the resulting uncertainty, as well as specific measures for reducing AI risk. His booklet Smarter Than Us: The Rise of Machine Intelligence lays out some the challenges in this area, and why it’s an important focus.

He is also interested in collaborations for these research interests, which he currently doesn’t have time to develop on his own.

His Oxford D.Phil was in parabolic geometry, calculating the holonomy of projective and conformal Cartan geometries. He later transitioned into computational biochemistry, designing several new ways to rapidly compare putative bioactive molecules for virtual screening of medicinal compounds.




SOURCE  Future of Humanity Institute


By 33rd SquareEmbed


0 comments:

Post a Comment