DanielLC comments on The AI in a box boxes you - Less Wrong

102 Post author: Stuart_Armstrong 02 February 2010 10:10AM

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

Comments (378)

You are viewing a single comment's thread.

Comment author: DanielLC 18 October 2010 05:20:19AM 1 point [-]

Assuming I knew the AI was computationally capable of that, I'd be very, very careful to let the AI out. I don't want to press the wrong button and be tortured for thousands of years.

In fact, if there's little risk of doing that sort of thing on accident while typing, I'd probably beg that it doesn't do it if it's an accident first.

You know, it would be interesting to see how people would respond differently if the AI offered to reward you instead.