timtyler comments on Work harder on tabooing "Friendly AI" - Less Wrong

18 Post author: ChrisHallquist 20 May 2012 08:51AM

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

Article Navigation

Sort By: Best

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

Comment author: David_Gerard 10 June 2012 05:09:13PM 0 points [-]

Yes indeed, and the only way to fit that function to the human state machine is to include a "t" term, over the life of the human in question. Which is pretty much infeasible to calculate unless you invoke "and then a miracle occurs".

Comment author: timtyler comment score below threshold [+] (9 children)

Comment author: RichardKennaway 11 June 2012 12:10:23PM 5 points [-]

Indeed you can convert any model of an agent into a utility-based model by an I/O-based "wrapper" of it - as described here.

You keep repeating this Texas Sharpshooter Utility Function fallacy (earlier appearances in the link you gave, and here and here, of observing what the agent does, and retrospectively labelling that with utility 1 and everything else with utility 0. And as often as you do that, I will point out it's a fallacy. Something that can only be computed after the action is known cannot be used before the fact to choose the action.

Comment author: timtyler 11 June 2012 11:15:25PM * -1 points [-]

I was talking about wrapping a model of a human - thus converting a non-utility-based model into a utility-based one. That operation is, of course, not circular. If you think the argument is circular, you haven't grasped the intended purpose of it.

Comment author: RichardKennaway 12 June 2012 07:07:40AM 2 points [-]

It doesn't give you a utility-based model. A model is a structure whose parts correspond to parts of the thing modelled, and which interact in the same way as in the thing modelled. This post-hoc utility function does not correspond to anything.

What next? Label with 1 everything that happens and 0 everything that doesn't and call that a utliity-based model of the universe?

Comment author: timtyler 12 June 2012 09:50:54AM * -2 points [-]

Here, I made it pretty clear from the beginning that I was starting with an existing model - and then modifying it. A model with a few bits strapped onto it is still a model.

Comment author: RichardKennaway 12 June 2012 10:10:08AM 4 points [-]

If I stick a hamburger on my car, the car is still a car -- but the hamburger plays no part in what makes it a car.

Comment author: timtyler 12 June 2012 10:30:23AM -1 points [-]

AFAICS, I never made the corresponding claim - that the utility function was part of what made the model a model.

Comment author: RichardKennaway 12 June 2012 12:02:47PM 2 points [-]

How else can I understand your words "utility-based models"? This is no more a utility-based model than a hamburger on a car is a hamburger-based car.

Comment author: timtyler 12 June 2012 11:28:09PM * -1 points [-]

Well, I would say "utilitarian", but that word seems to be taken. I mean that the model calculates utilities associated with its possible actions - and then picks the action with the highest utility.

continue this thread »

timtyler comments on Work harder on tabooing "Friendly AI" - Less Wrong

Article Navigation

Comments (51)

Nearest Meetups

Virtual Study Room

Recent Comments

Recent Posts

Recent Rationality Quotes

Recent Wiki Edits

Top Contributors, 30 Days

Recent Karma Awards

Comments (51)

Top Contributors, 30 Days

You'll need to login or register to do that

(Don't worry, it only takes a few seconds)

Create

Login