Tyrrell_McAllister comments on A Master-Slave Model of Human Preferences - Less Wrong

58 Post author: Wei_Dai 29 December 2009 01:02AM

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

Comments (80)

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

Comment author: pjeby 29 December 2009 01:42:57AM 7 points [-]

Your overall model isn't far off, but your terminal value list needs some serious work. Also, human behavior is generally a better match for models that include a time parameter (such as Ainslie's appetites model or PCT's model of time-averaged perceptions) than simple utility-maximization models.

But these are relative quibbles; people do behave sort-of-as-if they were built according to your model. The biggest drawbacks to your model are:

  1. The anthropomorphizing (neither the master nor the slave can truly be considered agents in their own right), and

  2. You've drawn the dividing lines in the wrong place: the entire mechanism of reinforcement is part of the master, not the slave. The slave is largely a passive observer, abstract reasoner, and spokesperson, not an enslaved agent. To be the sort of slave you envision, we'd have to be actually capable of running the show without the "master".

A better analogy would be to think of the "slave" as being a kind of specialized adjunct processor to the master, like a GPU chip on a computer, whose job is just to draw pretty pictures on the screen. (That's what a big chunk of the slave is for, in fact: drawing pretty pictures to distract others from whatever the master is really up to.)

The slave also has a nasty tendency to attribute the master's accomplishments, abilities, and choices to being its own doing... as can be seen in your depiction of the model, where you gave credit to the slave for huge chunks of what the master actually does. (The tendency to do this is -- of course -- another useful self/other-deception function, though!)

Comment author: Tyrrell_McAllister 29 December 2009 02:52:28AM 5 points [-]

. . . people do behave sort-of-as-if they were built according to your model. The biggest drawbacks to your model are . . .

Your "drawbacks" point out ways in which Wei Dai's model might differ from a human. But Wei Dai wasn't trying to model a human.