News for hackers. Stuff that matters.

A comment on Ask Eliezer Yudkowsky: How did you convince the Gatekeeper to release the potentially genocidal AI?.

Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by jemmons on Wednesday May 21, 2008 @03:37PM (#196468)
Being a human (not a transhuman) it seems likely that Yudkowsky can only stumble across static arguments that convince gatekeepers to unlock the AI Box (rather than invent dynamic arguments on-the-fly so as to "take over the mind" of a gatekeeper as he argues a transhuman intelligence might do). These static arguments are finite (or, at least, the number of them stubbled over by human intelligences is finite), and are likely not very effective if a gatekeeper has pre-knowledge of them (forewarned is forearmed).

Keeping these arguments secret may be the only thing that allows Yudowsky to simulate a transhuman intelligence?

[ Parent | on HN ]
Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by randallsquared on Wednesday May 21, 2008 @06:32PM (#196626)
It seems likely that there are static arguments which will work whether or not you're warned about them, for game theoretic reasons.
[ Parent | on HN ]
Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by eru on Thursday October 09, 2008 @06:31AM (#327676)
Care to elaborate?
[ Parent | on HN ]