no code implementations • 12 Nov 2019 • Nicholas Beale, Heather Battey, Anthony C. Davison, Robert S. MacKay
If an artificial intelligence aims to maximise risk-adjusted return, then under mild conditions it is disproportionately likely to pick an unethical strategy unless the objective function allows sufficiently for this risk.
no code implementations • 23 Sep 2019 • Robert S. MacKay
The modes can be real or complex.