Caledonian2 comments on Abstracted Idealized Dynamics - Less Wrong

17 Post author: Eliezer_Yudkowsky 12 August 2008 01:00AM

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

Comments (25)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Caledonian2 12 August 2008 01:23:45AM 1 point [-]

No individual particle can be mistaken as to its own behavior. No collection of particles can be mistaken as to its own behavior.

Whether those behaviors properly represent the properties we want them to is another matter. That's why we can say the calculator struck by the cosmic ray is malfunctioning, although all of its parts work perfectly according to physics. 'Physics' is not the set of standards we're referring to, when we speak of the device not working properly.

Comment author: Will_Newsome 23 May 2011 04:00:35AM 1 point [-]

Of course, 'how we want the calculator to work' is just a stand-in that represents not a subgoal of our utility function, but a referent to something outside us we perceive as more objective than what we can see of ourselves. A broken calculator is not wrong because the number it spits out isn't the number we were hoping it would spit out when we started calculating our finances, nor because being misled about such a number would endanger our finances further. (That doesn't mean we should turn the universe into a big calculator, of course; unless it's a calculator that knows how to find and calculate the the most objective and elegant calculations, and not just arbitrary addition. Then maybe.)