From: Alexander E. Richter (arichter@bubis.com)
Date: Tue Jul 02 2002 - 12:24:37 MDT
At 10:46 02.07.02 -0700, you wrote:
>Please see the posts on "Effective AI Jail":
>http://sysopmind.com/archive-sl4/0106/index.html#63
>
>It's not an exact overlap, but most of this has been discussed
>before. Basically, there *might* be ways to trap the AI in the short run,
>but once it's smarter than us there's not much hope.
I read the thread, but its more about talking to humans over vt100, but
not about setting up an escape-enviroment before the AI is created. ( Or
missed i something?)
This escape-enviroment should work without human interaction after it is
started or better no human should be able to stop or detect this
escape-enviroment.
cu Alex
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:40 MDT