How do you get an AI system that does better than a human would, without doing anything a human wouldn't?
A follow-up to "Maximizers and Satisficers": https://youtu.be/Ao4jwLwT36M
The Paper: https://intelligence.org/files/QuantilizersSaferAlternative.pdf
Forodriac Origamius
2020-12-06 20:17:17 +0000 UTC