Re: CEV specifies who the AI cares about (was Re: Can't afford to rescue cows)

From: Matt Mahoney (
Date: Sat Apr 26 2008 - 21:21:41 MDT

--- Stefan Pernar <> wrote:

> I was following the discussion from the sideline but think it is time
> to point you to an alternative to Elizier's CEV.
> You can find my paper on friendliness called 'Practical Benevolence -
> a Rational Philosophy of Morality' at:
> In it I combine Kantian moral philosophy with Darwinian evolution to
> form a moral theory based in rational choice.

In section 1.7 you state that existence is preferable to non-existence,
and that existence is defined as the ability to be perceived. From
this you conclude that it is the agent's interest to ensure continuous

This is the crux of your argument. I believe it is flawed. Evolution
does not define existence as the ability to be perceived. It only
matters that your genes are propagated. It does not matter if other
animals are aware of your existence for you to exist. If they are
predators or prey, it is preferable that they do not perceive you.

Humans have a goal of being perceived by other humans. This is called
"ego". Tribes whose members desire attention have a competitive
advantage because ego leads to sharing of information, a common
language, reciprocal attention and friendship, and ability to organize
into companies and armies. For example, we would not post
noncommercial messages to the internet without ego.

But ego is not universal. Many animals are nonsocial. Some social
species like ants and bees act out of instinct rather than learn social
behavior out of a desire for attention.

-- Matt Mahoney,

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT