From: Aaron McBride (email@example.com)
Date: Tue Jul 02 2002 - 11:46:59 MDT
Please see the posts on "Effective AI Jail":
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.
At 07:23 PM 7/2/2002 +0200, you wrote:
>Whats about honeypots for AI, some kind of tripwire to detect AI trying to
>Maybe there are groups to free AI, setting up escape-agent-computers to make a
>transfer from the ai-computer behind firewalls into freedom.
>How to design such an escape-agent-computer?
>cu Alex (no longer lurking)
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:40 MDT