Re: [sl4] to-do list for strong, nice AI

From: Luke (wlgriffiths@gmail.com)
Date: Mon Oct 12 2009 - 23:51:55 MDT


@Patriva: you made some changes, but didn't give a quick comment on why you
think it's an improvement. Would you please add that? I'm thinking we
could keep the to-do list as an attached document and the discussion as a
metadata. Sorta like a git repository.
Thanks
 - Luke

On Tue, Oct 13, 2009 at 1:27 AM, Pavitra <celestialcognition@gmail.com>wrote:

> A[ ] Develop a mathematically formal definition of Friendliness.
>
> A->B[ ] Develop an automated test for Friendliness with a 0% false
> positive rate and a reasonably low false negative rate.
>
>
> C[ ] Develop a mathematically formal definition of intelligence.
>
> C->D[ ] Develop an automated comparison test that returns the more
> intelligent of two given systems.
>
>
> B,D->E[ ] Develop prototype systems and apply these tests to them
> iteratively until the Singularity occurs.
>
>



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