AspiringKnitter comments on The Human's Hidden Utility Function (Maybe) - Less Wrong

44 Post author: lukeprog 23 January 2012 07:39PM

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

Comments (87)

You are viewing a single comment's thread.

Comment author: AspiringKnitter 24 January 2012 08:33:31PM 1 point [-]

If I understand this correctly, then the model-based system and the model-free system sound like inside and outside views.

Comment author: Manfred 25 January 2012 03:40:52PM 1 point [-]

Although in this case the "outside view" can't learn from anybody else's mistakes, it always has to make them itself.

Comment author: lessdazed 25 January 2012 04:03:32AM 1 point [-]

I agree.

Whoever downvoted this should have said why they disagreed if they did.

Comment author: JoachimSchipper 25 January 2012 12:40:56PM 0 points [-]

My inside view already feels pretty probabilistic, actually. (I suspect LW-reading mathematicians are not a very good model of the average human, though.)