News for hackers. Stuff that matters.

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

Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by gojomo on Wednesday May 21, 2008 @05:45PM (#196592)
I didn't see a rule against it. Why wouldn't an AI (or Yudkowski) try bribery to assist its escape?
[ Parent | on HN ]
Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by swombat on Wednesday May 21, 2008 @06:02PM (#196605)
There's a rule about the discussion being between the AI and the Gatekeeper, not between the human behind the AI and the human behind the Gatekeeper.
[ Parent | on HN ]
Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by gojomo on Wednesday May 21, 2008 @06:52PM (#196645)
But in real life, any Gatekeepers will be corruptible humans, no?
[ Parent | on HN ]
Re:Ask Eliezer Yudkowsky: How did you convince the Gatekeepe... by xlnt on Wednesday May 21, 2008 @06:59PM (#196650)
the human playing the AI can't bribe the other human in real life. the AI can offer in-roleplay bribes.
[ Parent | on HN ]