FAI Research Constraints and AGI Side Effects

2015-06-03T19:25:14.508Z · score: 18 (22 votes)

Minneapolis Meetup: Saturday May 28, 3:00PM

2011-05-23T23:55:22.132Z · score: 2 (3 votes)

Minneapolis Meetup: Saturday May 14, 3:00PM

2011-05-13T21:14:45.113Z · score: 5 (6 votes)
Comment by justinshovelain on Metaphilosophical Mysteries · 2010-07-28T19:57:39.325Z · score: 0 (0 votes) · LW · GW

By new "term" I meant to make the clear that this statement points to an operation that cannot be done with the original machine. Instead it calls this new module (say a halting oracle) that didn't exist originally.

Comment by justinshovelain on Metaphilosophical Mysteries · 2010-07-28T09:06:39.977Z · score: 0 (0 votes) · LW · GW

Are you trying to express the idea of adding new fundamental "terms" to your language describing things like halting oracles and such? And then discounting their weight by the shortest statement of said term's properties expressed in the language that existed previously to including this additional "term?" If so, I agree that this is the natural way to extend priors out to handle arbitrary describable objects such as halting oracles.

Stated another way. You start with a language L. Let the definition of an esoteric mathematical object (say a halting oracle) E be D in the original language L. Then the prior probability of a program using that object is discounted by the description length of D. This gives us a prior over all "programs" containing arbitrary (describable) esoteric mathematical objects in their description.

I'm not yet sure how universal this approach is at allowing arbitrary esoteric mathematical objects (appealing to the Church-Turing thesis here would be assuming the conclusion) and am uncertain whether we can ignore the ones it cannot incorporate.

Comment by justinshovelain on Think Before You Speak (And Signal It) · 2010-03-19T23:39:58.954Z · score: 6 (6 votes) · LW · GW

Interesting idea.

I agree that trusting newly formed ideas is risky, but there are several reasons to convey them anyway (non-comprehensive listing):

  • To recruit assistance in developing and verifying them

  • To convey an idea that is obvious in retrospect, an idea you can be confident in immediately

  • To signal cleverness and ability to think on one's feet

  • To socially play with the ideas

What we are really after though is to asses how much weight to assign to an idea off the bat so we can calculate the opportunity costs of thinking about the idea in greater detail and asking for the idea to be fleshed out and conveyed fully. This overlaps somewhat with the confidence (context sensitive rules in determining) with which the speaker is conveying the idea. Also, how do you gauge how old an idea really is? Especially if it condenses gradually or is a simple combination out of very old parts? Still... some metric is better than no metric.

Sequential Organization of Thinking: "Six Thinking Hats"

2010-03-18T05:22:48.488Z · score: 25 (30 votes)
Comment by justinshovelain on Open Thread: March 2010, part 2 · 2010-03-14T08:24:46.590Z · score: -33 (33 votes) · LW · GW

Vote this down for karma balance.

Comment by justinshovelain on Open Thread: March 2010, part 2 · 2010-03-14T08:24:25.521Z · score: 35 (35 votes) · LW · GW

Vote this up if you are the oldest child with siblings.

Comment by justinshovelain on Open Thread: March 2010, part 2 · 2010-03-14T08:23:46.614Z · score: 12 (12 votes) · LW · GW

Vote this up if you are an only child.

Comment by justinshovelain on Open Thread: March 2010, part 2 · 2010-03-14T08:23:32.478Z · score: 14 (14 votes) · LW · GW

Vote this up if you have older siblings.

Comment by justinshovelain on Open Thread: March 2010, part 2 · 2010-03-14T08:23:08.088Z · score: 5 (5 votes) · LW · GW

Poll: Do you have older siblings or are an only child?

karma balance

Coffee: When it helps, when it hurts

2010-03-10T06:14:56.186Z · score: 44 (47 votes)
Comment by justinshovelain on Open Thread: March 2010 · 2010-03-10T00:48:39.422Z · score: 7 (7 votes) · LW · GW

I'm thinking of writing up a post clearly explaining update-less decision theory. I have a somewhat different way of looking at things than Wei Dia and will give my interpretation of his idea if there is demand. I might also need to do this anyway in preparation for some additional decision theory I plan to post to lesswrong. Is there demand?

Comment by justinshovelain on Individual vs. Group Epistemic Rationality · 2010-03-02T22:25:27.110Z · score: 2 (2 votes) · LW · GW

Closely related to your point is the paper, "The Epistemic Benefit of Transient Diversity"

It describes and models the costs and benefits of independent invention and transient disagreement.

Meetup: Bay Area: Sunday, March 7th, 7pm

2010-03-02T21:18:28.332Z · score: 6 (7 votes)
Comment by justinshovelain on The Preference Utilitarian’s Time Inconsistency Problem · 2010-01-15T17:35:15.481Z · score: 2 (2 votes) · LW · GW

Why are you more concerned about something with unlimited ability to self reflect making a calculation error than about the above being a calculation error? The AI could implement the above if the calculation implicit in it is correct.

Comment by justinshovelain on The Preference Utilitarian’s Time Inconsistency Problem · 2010-01-15T17:23:27.833Z · score: 3 (3 votes) · LW · GW

What keeps the AI from immediately changing itself to only care about the people's current utility function? That's a change with very high expected utility defined in terms of their current utility function and one with little tendency to change their current utility function.

Will you believe that a simple hack will work with lower confidence next time?

Comment by justinshovelain on Positive-affect-day-Schelling-point-mas Meetup · 2009-12-23T21:24:08.995Z · score: 1 (1 votes) · LW · GW

I'll be there.

Comment by justinshovelain on Intuitive supergoal uncertainty · 2009-12-05T02:46:26.327Z · score: 0 (2 votes) · LW · GW

Hmm, darn. When I write I do have a tendency to see what ideas I meant to describe instead of seeing my actual exposition; I don't like grammar checking my writing until I've had some time to forget details, I read right over my errors unless I pay special attention.

I did have a three LWers look over the article before I sent it and got the general criticism that it was a bit obscure and dense but understandable and interesting. I was probably too ambitious in trying to include everything within one post though, length vs clarity tradeoff.

To address your points:

Have you not felt or encountered people who have the opinion that our life goals may be uncertain, something to have opinions about, and are valid targets for argument? Also, is not uncertainty of our most fundamental goals something we must consider and evaluate (explicitly or implicitly) in order to verify that an artificial intelligence is provably Friendly?

Elaborating on the second statement, when I used "naturalistically" I wished to invoke the idea that the exploration I was doing was similar to classifying animals before we had taxonomies, we look around with our senses (or imagination and inference in this case) and see what we observe and lay no claim to systematic search or analysis. In this context I did a kind of imagination limited shallow search process without trying to systematically relate the concepts (combinatorial explosion and I'm not yet sure how to condense and analyze supergoal uncertainty).

As to the third point, what I did in this article is allocate a name "supergoal uncertainty", roughly described it in the first paragraph and hopefully brought up the intuition, and then subsequently considered various definitions of "supergoal uncertainty" following from this intuition.

In retrospect, I probably errored on the clarity versus writing time trade-off and was perhaps biased in trying to get this uncomfortable writing task (I'm not a natural writer) off my plate so I can do other things.

Comment by justinshovelain on Intuitive supergoal uncertainty · 2009-12-05T02:09:29.165Z · score: 0 (0 votes) · LW · GW

I think he meant that even if we are not religious, society tends to pull us into moral realism even though of course moral realism is an illusion.

You are correct, though I don't go as far as calling moral realism an illusion because of unknown unknowns (though I would be very surprised to find it isn't illusionary).

Comment by justinshovelain on Intuitive supergoal uncertainty · 2009-12-05T02:04:18.007Z · score: 0 (0 votes) · LW · GW

Addressing your reification point:

By means of reification something that was previously implicit, unexpressed and possibly unexpressible is explicitly formulated and made available to conceptual (logical or computational) manipulation." - Reification(computer science) from wikipedia.

I don't think I did abuse vocabulary outside of possibly generalizing meanings in straightforward ways and taking words and meanings common in one topic and using them in a context where they are rather uncommon (e.g. computer science to philosophy). I rely on context to refine and imbue words with meaning instead of focusing on dictionary definitions (to me all sentences take the form of puzzles and words are the pieces; I've written more words in proofs than in all other contexts combined). I will try to pay more attention to context invariant meanings in the future. Thanks for the criticism.

Intuitive supergoal uncertainty

2009-12-04T05:21:03.942Z · score: 7 (13 votes)
Comment by justinshovelain on How to test your mental performance at the moment? · 2009-11-24T05:16:59.056Z · score: 7 (7 votes) · LW · GW

Some things I use to test mental ability as well as train it are: BrainWorkshop (A free dualNback program), Cognitivefun.net (A site with assorted tests and profiles including everything from reaction time, to subitizing, to visual backward digit span), Posit Science's jewel diver demo (a multi-object tracking test), and Lumosity.com (brainshift, memory matrix, speed match, top chimp. All of these tests can be found for free on the internet).

Subjectively the regular use of these tests has increased my metacognitive and self monitoring ability. Anyone have other suggestions? How about tests one can do without the aid of external devices?

In complement to determining whether one's brain isn't in its best state there is the question of how to improve or fix it. Keeping with the general spirit of this thread, what are some strategies people use to improve their cognitive functioning (as it pertains to low level properties such as short term memory) in the short term without the use of external aids? A few I use are priming emotional state with posture, expression, and words, doing mental arithmetic, memorizing arbitrary information, and doing the above mental tests.

Minneapolis Meetup: Survey of interest

2009-09-18T18:52:50.278Z · score: 7 (8 votes)

Causes of disagreements

2009-07-16T21:51:57.422Z · score: 28 (29 votes)
Comment by justinshovelain on Rationality Quotes - July 2009 · 2009-07-03T01:02:57.352Z · score: 2 (2 votes) · LW · GW

I do not agree with all interpretations of the quote but primed by:

That's not right. It's not even wrong. -- Wolfgang Pauli

I interpreted it charitably with "critical" loosely implying "worth thinking about" in contrast to vague ideas that are not even wrong. Furthermore, from thefreedictionary.com definition of critical, "1. Inclined to judge severely and find fault.", vague statements may be considered useless and so judged severely but much of the time they are also slippery in that they must be broken down into precise disjoint "meaning sets" where faults can be found. So vague ideas cannot necessarily be criticized directly in the fault finding sense. (Wide concepts that have useful delimitations in contrast to arbitrary ill-formed vague ones can be useful and are a powerful tool in generalization. In informal contexts these two meanings of vague overlap).

Comment by justinshovelain on Rationality Quotes - July 2009 · 2009-07-02T23:25:44.219Z · score: 2 (4 votes) · LW · GW

Make everything as simple as possible, but not simpler.

-- Albert Einstein

Comment by justinshovelain on Rationality Quotes - July 2009 · 2009-07-02T22:55:13.524Z · score: 11 (15 votes) · LW · GW

Many highly intelligent people are poor thinkers. Many people of average intelligence are skilled thinkers. The power of a car is separate from the way the car is driven.

-- Edward de Bono

Comment by justinshovelain on Rationality Quotes - July 2009 · 2009-07-02T22:51:23.423Z · score: 6 (12 votes) · LW · GW

In a sense, words are encyclopedias of ignorance because they freeze perceptions at one moment in history and then insist we continue to use these frozen perceptions when we should be doing better.

-- Edward de Bono

Comment by justinshovelain on Rationality Quotes - July 2009 · 2009-07-02T22:45:58.396Z · score: 3 (11 votes) · LW · GW

Some people are always critical of vague statements. I tend rather to be critical of precise statements; they are the only ones which can correctly be labeled 'wrong'.

-- Raymond Smullyan

Comment by justinshovelain on Controlling your inner control circuits · 2009-06-29T23:39:24.252Z · score: 0 (0 votes) · LW · GW

From pwno: "Aren't true theories defined by how useful they are in some application?"

My definition of "usefulness" was built with the express purpose of relating the truth of theories to how useful they are and is very much a context specific temporary definition (hence "define:"). If I had tried to deal with it directly I would have had something uselessly messy and incomplete, or I could have used a true but also uninformative expectation approach and hid all of the complexity. Instead, I experimented and tried to force the concepts to unify in some way. To do so I stretched the definition of usefulness pretty much to the breaking point and omitted any direct relation to utility functions. I found it a useful thought to think and hope you do as well even if you take issue with my use of the name "usefulness".

Comment by justinshovelain on Controlling your inner control circuits · 2009-06-29T22:52:06.964Z · score: 0 (2 votes) · LW · GW

define: A theory's "truthfulness" as how much probability mass it has after appropriate selection of prior and applications of Bayes' theorem. It works as a good measure for a theory's "usefulness" as long as resource limitations and psychological side effects aren't important.

define: A theory's "usefulness" as a function of resources needed to calculate its predictions to a certain degree of accuracy, the "truthfulness" of the theory itself, and side effects. Squinting at it, I get something roughly like: usefulness(truthfulness, resources, side effects) = truthfulness * accuracy(resources) + messiness(side effects)

So I define "usefulness" as a function and "truthfulness" as its limiting value as side effects go to 0 and resources go to infinity. Notice how I shaped the definition of "usefulness" to avoid mention of context specific utilities; I purposefully avoided making it domain specific or talking about what the theory is trying to predict. I did this to maintain generality.

(Note: For now I'm polishing over the issue of how to deal with abstracting over concrete hypotheses and integrating the properties of this abstraction with the definitions)

Comment by justinshovelain on What's In A Name? · 2009-06-29T19:04:16.068Z · score: 2 (2 votes) · LW · GW

I agree that it may plausibly be argued that the difference should rarely fall into the small margin: U(good name) - U(bad name) (up to varying priors, utility functions, ...). However, should people calculate to the point that they can resolve differences of that order of magnitude? A fast and dirty heuristic may be the way to go practically speaking; the difference in utility would be less than the utility lost in calculating it.

Comment by justinshovelain on What's In A Name? · 2009-06-29T18:49:09.942Z · score: 3 (3 votes) · LW · GW

Is this whole bias caused by the exposure effect? Would there be any obstacle in unifying the two? Do people also prefer to live in towns that are associated with their parents' names? Do people who fall for this effect also name their pets or children after themselves to a greater extent?