Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:book
|
| gptkbp:author |
gptkb:Brian_Christian
|
| gptkbp:awards |
gptkb:2020_Best_Book_of_the_Year_(NPR,_Fortune,_Bloomberg,_etc.)
|
| gptkbp:countryOfOrigin |
gptkb:United_States
|
| gptkbp:describes |
challenges in aligning AI systems with human values
|
| gptkbp:explores |
value alignment problem
bias in machine learning fairness in algorithms interpretability of AI safety in AI systems |
| gptkbp:genre |
non-fiction
|
| https://www.w3.org/2000/01/rdf-schema#label |
The Alignment Problem
|
| gptkbp:ISBN |
978-0-393-65180-3
|
| gptkbp:language |
English
|
| gptkbp:pages |
496
|
| gptkbp:publicationDate |
2020
|
| gptkbp:publisher |
gptkb:W._W._Norton_&_Company
|
| gptkbp:reviewedBy |
gptkb:Nature
gptkb:The_Guardian gptkb:The_New_York_Times |
| gptkbp:subject |
gptkb:artificial_intelligence
gptkb:machine_learning ethics |
| gptkbp:bfsParent |
gptkb:Brian_Christian
|
| gptkbp:bfsLayer |
6
|