01409nam a22003497a 4500001000400000003000500004005001700009008004100026020003900067020002500106020001500131040002900146082001900175100003100194245010400225264003500329264001100364300002400375336002100399337002500420338002300445500002000468504004400488520030000532650001400832650002900846650005600875650003700931650003100968650003800999650002201037557MBIP20250422102930.0250206b        |||||||| |||| 00| 0 eng d  a9781786494337qRM 67.70cPaperback  a9781786494320qebook  z1786494337  aMBIPbengcMBIPdNFerda04223a006.3bBRI1 aChristian, Brian,eauthor.10aTHE ALIGNMENT PROBLEM :bHow Can Artificial Intelligence Learn Human Values? /cby Brian Christian. 1aLondo :bAtlantic Books,c2021 4c©2020  a476 pages :c20 cm.  2rdacontentatext  2rdamediaaunmediated  2rdacarrieravolume  aIncludes index.  aIncludes bibliography (pages 402 - 451)  aThe Alignment Problem: Machine Learning and Human Values is a 2020 non-fiction book by the American writer Brian Christian. It is based on numerous interviews with experts trying to build artificial intelligence systems, particularly machine learning systems, that are aligned with human values. 0aComputers 0aSocial AspectsvScience  0aArtificial intelligence vMoral and ethical aspects 0aSocial aspectsvEthical problems 0aHuman-computer interaction 0aMachine learningvSafety measures 0aSoftware failures