Re: Investing in FAI research: now vs. later.

From: Randall Randall (
Date: Mon Feb 11 2008 - 20:56:56 MST

On Feb 11, 2008, at 5:52 PM, Eliezer S. Yudkowsky wrote:
> Similarly, building an AI that knows what you "really mean" by
> "Friendly" when you type "Please make a Friendly AI" at the prompt,
> is FAI-complete, and not any easier than building a Friendly AI.

It seems to me that building a program to compute the first
N primes is far, far less difficult than computing the first
N primes myself, for sufficiently high values of N. Similarly,
it may be far less difficult to write an AI that can figure
out how to write an FAI, than to figure it out personally.

Of course, figuring out how to write an FAI might turn out to
be a paperclip factory, as you'll no doubt point out next. :)

Randall Randall <>
"If you are trying to produce a commercial product in
  a timely and cost efficient way, it is not good to have
  somebody's PhD research on your critical path." -- Chip Morningstar

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