Jiro comments on Debunking Fallacies in the Theory of AI Motivation - Less Wrong

8 Post author: Richard_Loosemore 05 May 2015 02:46AM

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

Comments (343)

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

Comment author: Plasmon 14 May 2015 07:31:38PM *  3 points [-]

me and a pretty large community of real AI builders who consider a utility-function-based goal stack to be so unworkable that it will never be used in any real AI.

Just because the programmer doesn't explicitly code a utility function does not mean that there is no utility function. It just means that they don't know what the utility function is.

Comment author: Jiro 14 May 2015 08:25:41PM *  5 points [-]

Although technically any AI has a utility function, the usual arguments about the failings of utility functions don't apply to unusual utility functions like the type that may be more easily described using other paradigms.

For instance, Google Maps can be thought of as having a utility function: it gains higher utility the shorter the distance is on the map. However, arguments such as "you can't exactly specify what you want it to do, so it might blackmail the president into building a road in order to reduce the map distance" aren't going to work, because you can program Google Maps in such a way that it never does that sort of thing.

Comment author: Plasmon 14 May 2015 08:46:36PM *  6 points [-]

However, arguments such as "you can't exactly specify what you want it to do, so it might blackmail the president into building a road in order to reduce the map distance"

The reason that such arguments do not work is that you can specify exactly what it is you want to do, and the programmers did specify exactly that.

In more complex cases, where the programmers are unable to specify exactly what they want, you do get unexpected results that can be thought of as "the program wasn't optimizing what the programmers thought it should be optimizing, but only a (crude) approximation thereof". (an even better example would be one where a genetic algorithm used in circuit design unexpectedly re-purposed some circuit elements to build an antenna, but I cannot find that reference right now)

Comment author: Jiro 14 May 2015 10:22:00PM 6 points [-]

The reason that such arguments do not work is that you can specify exactly what it is you want to do, and the programmers did specify exactly that.

Which is part of my point. Because you can specify exactly what you want--and because you can't for the kinds of utility functions that are usually discussed on LW--describing it as having a utility function is technically true, but is misleading because the things you say about those other utility functions won't carry over to it. Yeah, just because the programmer didn't explicitly code a utility function doesn't mean it doesn't have one--but it often does mean that it doesn't have one to which your other conclusions about utility functions apply.

Comment author: TheAncientGeek 15 May 2015 02:59:23PM *  2 points [-]

Thanks for pointing thus out, a lot of people seem confused on the issue, (What's worse, its largely a map/territory confusion)