Re:The Problem with Intelligence
by Xcelerate on Thursday September 15, 2022 @05:29PM
(#32858714)
> Intelligence needs to be defined with respect to a range of tasks and a range of priors.
Yep, you’re right. I forgot to mention that in my “loosely put” sentence, although the work by Hutter and Legg does mention that and discusses algorithmic information theory heavily.
Yep, you’re right. I forgot to mention that in my “loosely put” sentence, although the work by Hutter and Legg does mention that and discusses algorithmic information theory heavily.