Re: Compassion vs Respect; Exponential discounting of utility (was Re: Building a friendly AI from a "just do what I tell you" AI)

From: Mike Dougherty (msd001@gmail.com)
Date: Tue Dec 11 2007 - 07:13:29 MST


On Dec 11, 2007 5:15 AM, Joshua Fox <joshua@joshuafox.com> wrote:

> As you say, to the extent that the AI must interact with humans, this
> makes sense for the AI. But beyond that, isn't this a bias, and therefore
> less than rational?
>

What makes a bias less than rational? I have an inclination (bias) towards
remaining employed in an effort to keeping my comfortable lifestyle. Is
that really irrational?

If by the term bias you are indicating an incompletely examined or
misunderstood goal, then yeah that would be a problem. I imagine that an AI
would be able to audit the computation states that give rise to its goals,
no?



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:01 MDT