RE: of possible interest: interaction with autonomous agents

From: Lee Corbin (
Date: Tue Jun 28 2005 - 16:21:31 MDT

Eliezer wrote

> Lee Corbin wrote:
> > Everything else being equal, people in more powerful positions
> > are more intelligent than people in less powerful positions.
> That's an odd thing to say. Do you mean that all else being equal, you infer
> that people in more powerful positions are probably more intelligent?


> That is backed by the data. But do you mean that people in more
> powerful positions are by definition more intelligent?

:-) Far be it from me to venture such an amazing definition!

Justin writes

> On 6/28/05, Eliezer S. Yudkowsky <> wrote:
> > But do you mean that people in more powerful positions
> > are by definition more intelligent? That in virtue of
> > having more options, they are smarter? This would mean
> > that I could stand outside an experiment and control
> > someone's intelligence with a dial.
> This is disingenous.

I guess you mean disingenuous: lacking in candor; also : giving a
false appearance of simple frankness : CALCULATING (Websters)

> No matter what intelligence is based on, if it has a physical
> basis, you could experimentally control it with a dial.

I agree that if are speaking of intelligence as a characteristic
or attribute of a entity, then you can in principle experimentally
control it. But probably it was meant that by means of a dial one
could control the *options* available to a fixed entity, and so
affect its intelligence; which I find to be an unusual meaning of
the term.

> It's also important to note that intelligent behavior is affected by
> good feedback and emotional reinforcement, both of which powerful
> people get much more readily.

Now we are sliding into intelligence being merely a behavior
trait, which I think is subtly different, though, yes an entity
in circumstance A may behave with abnormally high intelligence
while in circumstance B behave with amazingly little. But I
originally meant to discuss intelligence as a general attribute
of an entity or system, and asserted that a strong indicator
of it is the degree to which the entity has the wherewithal to
control its environment.


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:51 MDT