Difference between revisions of "Simple core"
| Line 1: | Line 1: | ||
'''Simple core''' is a term that has been used to describe various things in AI safety. | '''Simple core''' is a term that has been used to describe various things in AI safety. | ||
| − | * Simple core to [[corrigibility]]<ref>https://ai-alignment.com/corrigibility-3039e668638</ref> | + | * Simple core to [[corrigibility]]<ref>https://ai-alignment.com/corrigibility-3039e668638</ref><ref>https://www.greaterwrong.com/posts/Djs38EWYZG8o7JMWY/paul-s-research-agenda-faq/comment/79jM2ecef73zupPR4</ref> |
* [[Simple core of consequentialist reasoning]] | * [[Simple core of consequentialist reasoning]] | ||
* Simple core to AI safety techniques<ref>https://intelligence.org/files/OpenPhil2016Supplement.pdf see page 13</ref> | * Simple core to AI safety techniques<ref>https://intelligence.org/files/OpenPhil2016Supplement.pdf see page 13</ref> | ||
Revision as of 04:37, 26 February 2020
Simple core is a term that has been used to describe various things in AI safety.
- Simple core to corrigibility[1][2]
- Simple core of consequentialist reasoning
- Simple core to AI safety techniques[3]
- Simple core for impact measures
