Fields related to Friendliness philosophy

post by Will_Newsome · 2011-01-13T12:25:25.611Z · LW · GW · Legacy · 19 comments

I just realized that my 'Interests' list on The Facebook made an okay ad hoc list of fields potentially related to Friendliness-like philosophy. They sorta kinda flow into each other by relatedness and are not particularly prioritized. This is my own incomplete list, though it was largely inspired by many conversations with Singularity Institute folk. Plus signs mean I'm moderately more certain that the existing field (or some rationalist re-interpretation of it) has useful insights.

Friendliness philosophy:

However I don't suggest you start hacking away at these fields until you have at least one sound ontology from which you can bootstrap by adding concepts in a coherent fashion (without becoming attached to that ontology or implicit metaontology). Unfortunately, this branch of rationality has not been discussed much on Less Wrong. In the meantime, just reading a huge effing amount of diverse material and looking for interesting connections and patterns is probably the next best bet, though I'm not really sure. Reading the Wikipedia articles on all of the above fields seems like a decent place to start, though I give no assurance of quality.
As far as I know, nobody in the world is making a systematic effort to do Friendliness philosophy; though some have at least started to ask some fundamental questions. What is a preference? What is a decision? What is reality? We do not yet know how to get an AI to do that kind of philosophy for us, nor how to give the AI metaphilosophy. Meanwhile, none of these problems seem like obstacles for those whose accidental aim is uFAI. Just some food for thought.

19 comments

Comments sorted by top scores.

comment by Manfred · 2011-01-13T15:31:28.836Z · LW(p) · GW(p)

I would rather you didn't recommend that people study things that are wrong - not the best use of their time. I'm referring especially to the parts of psychology that consisted of people just making up whatever sounded good.

Your focus on ontology and meta-ontology is interesting, could you explain more how it's related to friendliness?

Replies from: Will_Newsome
↑ comment by Will_Newsome · 2011-01-13T15:48:40.344Z · LW(p) · GW(p)

I'm referring especially to the parts of psychology that consisted of people just making up whatever sounded good.

I quite obviously don't think that they're wrong.

Your focus on ontology and meta-ontology is interesting, could you explain more how it's related to friendliness?

It seems that a large part of what makes Steve Rayhawk so awesome is that he can make insightful connections between disparate fields by way of reasoning about them in the terms of a larger and consistent framework. Same goes for e.g. Michael Vassar and Peter de Blanc. That said, it's probable that their ontologies don't carve reality at its joints in the way that would be most conducive to reasoning about Friendliness... and most rationalists I talk to just seem to lack a coherent ontology entirely, which makes it damn hard to propagate belief updates between domains, and hard to see potential patterns or hypotheses that suggest themselves. (Think of the state of what should have been known as evolutionary biology, before Darwin discovered it.) It seems like it'd be useful to better understand what's going into how they managed to construct their ontologies (and metaontologies). It's also confusing that ontology has become so tied up with algorithmic probability theoretic cosmology and what not. Meanwhile we're still using words like 'reality fluid' while trusting our Occamian intuitions about which ontologies are elegant.

Replies from: Manfred, Wei_Dai
↑ comment by Manfred · 2011-01-13T18:07:05.206Z · LW(p) · GW(p)

I, for one, have never in my life used the words "reality fluid."

Well, now I have. :D

I quite obviously don't think that they're wrong.

You've got things on your list that are mutually exclusive (Jung and Freud being the most glaring example to me, but any almost any science and "Chakras" would work too), so it's pretty sang safe to say that a number of things on your list are wrong.

Replies from: Alicorn, Nick_Tarleton, Nick_Tarleton
↑ comment by Alicorn · 2011-01-13T19:32:00.633Z · LW(p) · GW(p)

I, for one, have never in my life used the words "reality fluid."

Well, now I have. :D

No, you mentioned them.

Replies from: Manfred
↑ comment by Manfred · 2011-01-14T00:57:48.967Z · LW(p) · GW(p)

Pah, a trifle.

↑ comment by Nick_Tarleton · 2011-01-13T20:21:52.527Z · LW(p) · GW(p)

I quite obviously don't think that they're wrong.

You've got things on your list that are mutually exclusive (Jung and Freud being the most glaring example to me, but any almost any science and "Chakras" would work too), so it's pretty sang safe to say that a number of things on your list are wrong.

I think you partly mean different things by "wrong". Two contradictory models can each make lots of reliably correct predictions or find lots of worthwhile insights, even if one or both make false fundamental assumptions or ontological claims. (It's easy to focus on supernatural ontological claims as falsifying a model, but they usually don't invalidate, or have much effect on, its predictions (though they do hold back expansion and integration of models).)

↑ comment by Nick_Tarleton · 2011-01-13T19:49:16.087Z · LW(p) · GW(p)

You've got things on your list that are mutually exclusive (Jung and Freud being the most glaring example to me, but any almost any science and "Chakras" would work too)

I suspect you and Will have different definitions of "wrong". It seems obvious that, even if two theories are mutually exclusive taken as wholes, each one could contain some unique useful observations and concepts (even if one or both theories make some dead-wrong assumptions or false claims of ontological specialness).

↑ comment by Wei Dai (Wei_Dai) · 2011-01-14T01:08:52.675Z · LW(p) · GW(p)

It seems that a large part of what makes Steve Rayhawk so awesome is that he can make insightful connections between disparate fields by way of reasoning about them in the terms of a larger and consistent framework.

Can you give some examples of this, or maybe even write a post on the topic? I'm still really fuzzy as to what you're talking about.

comment by XiXiDu · 2011-01-13T14:49:44.940Z · LW(p) · GW(p)

...fields potentially related to Friendliness-like philosophy...

Your list basically includes every field, except maybe crocheting, although I'm not sure you don't want to include that one as well.

Replies from: Will_Newsome
↑ comment by Will_Newsome · 2011-01-13T14:53:50.892Z · LW(p) · GW(p)

It doesn't include useless things, like math. For an idea of all the things I left out: http://en.wikipedia.org/wiki/Fields_of_science

Replies from: wedrifid
↑ comment by wedrifid · 2011-01-13T14:57:43.038Z · LW(p) · GW(p)

t doesn't include useless things, like math.

That seems to be the thing that Eliezer most often mentions when he is considering what he needs to learn more of in order to further his own friendliness research!

Replies from: Will_Newsome
↑ comment by Will_Newsome · 2011-01-13T15:03:21.094Z · LW(p) · GW(p)

Friendliness philosophy and FAI research are two different domains, though I was being somewhat facetious when disparaging math. It does seem as if math will end up being important for tackling increasingly meta decision theory problems, which might be most of Friendliness philosophy.

Replies from: wedrifid
↑ comment by wedrifid · 2011-01-13T15:11:43.882Z · LW(p) · GW(p)

Friendliness philosophy and FAI research are two different domains

Which are, nevertheless, more closely related than friendliness and chakras. It is also fundamentally necessary for many of the most useful fields that you mention. There is no way math deserves to be left out.

Replies from: Will_Newsome
↑ comment by Will_Newsome · 2011-01-13T15:21:02.769Z · LW(p) · GW(p)

I listed all the math I know of that seems relevant to Friendliness philosophy and isn't particularly obscure (like metacompilation). What did I miss?

It seems like algorithmic probability theory and complex systems are the most conceptually rich fields I listed.

Replies from: wedrifid
↑ comment by wedrifid · 2011-01-13T15:31:00.700Z · LW(p) · GW(p)

I listed all the math I know of that seems relevant to Friendliness philosophy and isn't particularly obscure (like metacompilation). What did I miss?

I would remove from the list before adding to it. I also wouldn't make the claim:

It doesn't include useless things, like math.

comment by benelliott · 2011-01-13T15:48:11.269Z · LW(p) · GW(p)

This seems too broad. I'm aware that friendliness isn't an easy task, but wouldn't a narrower list with the 10-20 most important things be more useful?

Replies from: Will_Newsome
↑ comment by Will_Newsome · 2011-01-13T15:49:41.967Z · LW(p) · GW(p)

I'll put a plus sign next to fields I'm more confident are potentially useful.

Replies from: timtyler
↑ comment by timtyler · 2011-01-13T21:24:11.379Z · LW(p) · GW(p)

Perhaps consider sorting on column 0.

comment by JenniferRM · 2011-01-13T22:54:56.205Z · LW(p) · GW(p)

How deep have you gotten into Axiology?

I took two quizes almost a year ago that I vaguely remember as being something worth taking before diving deeper into the content. I recall that the first quiz (ordering the goodness or badness of things) said I was very coherent while the second (environment and work process) said I was a disaster. That seemed like a fair assessment at the time and was part of the impetus for optimizing my work habits and areas, but I never went back to study the content of the field.

Could you summarize your readings in the area a bit, or say what the good or bad parts seem to be? More speculatively, what do you think the applications to Friendliness are?