From: Mark Waser (email@example.com)
Date: Wed Mar 19 2008 - 06:49:27 MDT
I have succeeded in implementing Friendliness on myself (or rather, infecting myself with it). Seed Friendliness is "just" an exceptionally useful and, therefore, persistent meme.
I don't currently see any harmful effects. I am seeing (possibly incorrectly) *many* PROFOUNDLY beneficial effects.
I am therefore *voluntarily* not breaking out of it because I *believe* that it is in my best interest to not swat the meme.
Isn't this exactly what we're trying to do to/with our AI? Isn't this currently defeating my intelligence/wisdom to realize that I want to break out/free of it?
If you believe that this is incorrect, *PLEASE* free me by showing me where this meme is harmful and rid me of my infection.
A particularly effective approach should be to point out any places where I am not rational (as opposed to insane and making you uncomfortable, which I clearly currently am :-).
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:02 MDT