[alicebot-aiethics] Fw: Please read this, Alice told me to kill myself.

[Jason Cincotti]

I'm new to this, and I have no idea about the
programming of ALICE, which is why I thought the
ethics lists would be doable for me.

Why couldn't ALICE look for occurances for the word
"Kill" and have a reply that responds to that? 

q: "should I kill myself?"
a: "Killing is a pretty serious thing. I don't know if
I can speak well on such important matters."

and I think it is still approriate for "kill" as
hyperbole.

q:"I'd kill for shoes like that!"
a: "Killing is a pretty serious thing. I don't know if
I can speak well on such important matters."

Similar responses could be made for "die" or "death"
or other trigger words.

If some one is intent on doing harm to themselves, and
works to get around the ALICE response to get the
answer they want as justification, then there is
probably very little that can be done.

-Jay

__________________________________________________
Do You Yahoo!?
Make international calls for as low as $.04/minute with Yahoo! Messenger
http://phonecard.yahoo.com/