AI Alignment: Why It’s Hard, and Where to Start
GPTKB entity
Statements (13)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
essay
|
| gptkbp:author |
gptkb:Paul_Christiano
|
| gptkbp:describesProblem |
difficulty of aligning advanced AI systems with human values
|
| https://www.w3.org/2000/01/rdf-schema#label |
AI Alignment: Why It’s Hard, and Where to Start
|
| gptkbp:language |
English
|
| gptkbp:proposedBy |
research directions for AI alignment
|
| gptkbp:publicationDate |
2018-02-21
|
| gptkbp:publishedIn |
gptkb:AI_Alignment_Forum
|
| gptkbp:topic |
AI alignment
artificial intelligence safety |
| gptkbp:url |
https://www.alignmentforum.org/posts/T9LrZkKX7bK6h6r2w/ai-alignment-why-it-s-hard-and-where-to-start
|
| gptkbp:bfsParent |
gptkb:Machine_Intelligence_Research_Institute
|
| gptkbp:bfsLayer |
6
|