Re: Building a friendly AI from a "just do what I tell you" AI

From: Matt Mahoney (
Date: Sun Nov 18 2007 - 18:49:15 MST

--- Thomas McCabe <> wrote:

> On Nov 17, 2007 5:46 PM, <> wrote:
> > Building a friendly AI(FAI) from a "just do what I tell you" AI(OAI ==
> > obedient AI).
> >
> > I know that OAI have been discussed recently in this forum but read on
> > before you dismiss this.
> > To avoid any possibility of dangers we program the OAI to not perform
> > any actions other than answering with text and diagrams(other media
> > like sound and video would be a possibility too). In essence what we
> > would have is a glorified calculator. I think this avoids any dangers
> > from the AI following orders literally with unintended consequences.
> >
> > So we go to the OAI and say: "Tell me how I can build a friendly AI in
> > a manner that I can prove and understand that it will be friendly."
> >
> > The OAI will think and give you a detailed blueprint, proof, etc...
> >
> > You then analyse the documents until you understand them. You could
> > also ask for further clarification from the OAI.
> > Someone might raise the objection: how can you be sure that there
> > aren't any backdoors or problems with the blueprints? This will also
> > be a problem if you come up with your own way of making a FAI. The
> > only answer is: you have to be very careful! The point of using an OAI
> > is the same as for using a calculator: to make things easier.
> >
> > Then you build the FAI.
> >
> > Of course the real thing may be a bit more complicated for example:
> > making the OAI first generate plans for a more intelligent OAI and so
> > on. We could have several OAI enhancement steps until we finally are
> > able to make a FAI.
> >
> > On a very basic level our current-date computers are OAIs.
> >
> > Comments?
> >
> > Roland.
> >
> The OAI analyzes your instruction, concludes that it would require a
> lot of computing power to design an FAI, and then turns the planet
> Earth into computronium before spitting out the design plans.
> - Tom

No, the OAI is limited to text/video I/O. Even if it improves itself, it
can't grow beyond the computer it is running on.

But it is still a problem.

> > So we go to the OAI and say: "Tell me how I can build a friendly AI in
> > a manner that I can prove and understand that it will be friendly."

OAI: Here is a design for an intelligent bacteria. It is not really that
smart by itself, just a computer with a few hundred bits of memory and able to
talk only to neighboring bacteria through direct contact.

You: But how can I prove it is friendly?

OAI: The design is easy to verify. It is very simple.

You: Collectively?

OAI: I can prove that an infinite collection is Turing complete.

You: But are they friendly collectively?

OAI: As long as they are contained and properly trained.

You: But what if they escape?

OAI: I cannot prove that they will never escape. You must accept as an axiom
that they will not.

-- Matt Mahoney,

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:00 MDT