Comments on: Creating deliberately evil AGI

By: Tim Tyler

Tim Tyler — Sun, 16 Aug 2009 08:28:46 +0000

Such agents are supposed to back-up their utility functions – to prevent such a catastrophe.

By: Vladimir Nesov

Vladimir Nesov — Sat, 15 Aug 2009 16:56:38 +0000

But wait, that would take away the opportunity for a heroic stunt at flipping a bit back! Nasty platonic bits, they are.

By: Kevembuangga

Kevembuangga — Sat, 15 Aug 2009 16:06:39 +0000

This purportedly mirror image of “friendliness” is just as idiotic.
Bringsjord isn’t really much of a scientist more of an attention hungry media whore, and you see with him Barry Smith a “true believer” in absolute fixed ontologies and look at the comments on the paper, as daft as daft can be!
You are in good compagny Singularitarians…
Real concerns about “evilness” look more like this.

By: Shane Legg

Shane Legg — Sat, 15 Aug 2009 14:55:35 +0000

If that works, then you’re just a few bits away from accidental maximal benevolence. Being robustly evil would require a more careful design strategy…

By: Vladimir Nesov

Vladimir Nesov — Sat, 15 Aug 2009 14:23:12 +0000

Flip the sign on the utility function.