jacob_cannell comments on Anthropomorphic AI and Sandboxed Virtual Universes - Less Wrong

-3 Post author: jacob_cannell 03 September 2010 07:02PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (123)

You are viewing a single comment's thread. Show more comments above.

Comment author: jacob_cannell 03 September 2010 09:16:25PM 2 points [-]

Especially since when we are talking about "Friendly AI" humans are not even remotely friendly in the relevant sense

Point taken - Friendliness for an AI is a much higher standard than even idealized human morality. Fine. But to get to that Friendliness, you need to define CEV in the first place, so improving humans and evolving them forward is a route towards that.

But again I didn't mean to imply we need to create perfect human-sims. Not even close. This is an additional measure.

I more or less assume that the AI will find a way to convince the creators to release it into the 'real world'.

This is an unreasonable leap of faith if the AI doesn't even believe that there are 'creators' in the first place.

Do you believe there are creators?