All of TimFreeman's Comments + Replies

Humans can be recognized inductively: Pick a time such as the present when it is not common to manipulate genomes. Define a human to be everyone genetically human at that time, plus all descendants who resulted from the naturally occurring process, along with some constraints on the life from conception to the present to rule out various kinds of manipulation.

Or maybe just say that the humans are the genetic humans at the start time, and that's all. Caring for the initial set of humans should lead to caring for their descendants because humans care about t... (read more)

0Stuart_Armstrong
That seems very hard! For instance, does that not qualify molar pregnancies as people, twins as one person and chimeras as two? And it's hard to preclude manipulations that future humans (or AIs) may be capable of. Easier, but still a challenge. You need to identify a person with the "same" person at a later date - but not, for instance, with list skin cells or amputated limbs. What of clones, if we're using genetics? It seems to me that identifying people imperfectly (a "crude measure", essentially http://lesswrong.com/lw/ly9/crude_measures/ ) is easier and safer than modelling people imperfectly. But doing it throughly, then the model seems better, and less vulnerable to unexpected edge cases. But the essence of the idea is to exploit something that a superintelligent AI will be doing anyway. We could similarly try and use any "human identification" algorithm the AI would be using anyway.

Hyperventilating leads to hallucinations instead of stimulation. I went to a Holotropic Breathwork session once. Some years before that, I went to a Sufi workshop in NYC where Hu was chanted to get the same result. I have to admit I cheated at both events -- I limited my breathing rate or depth so not much happened to me.

Listening to the reports from the other participants of the Holotropic Breathwork session made my motives very clear to me. I don't want any of that. I like the way my mind works. I might consider making purposeful and careful changes to h... (read more)

1ThrustVectoring
Random changes can be useful. Human minds are not good at being creative and exploring solution space. They can't give "random" numbers, and will tend to round ideas they have towards the nearest cached pattern. The occasional jolt of randomness can lead to unexplored sections of solution space.
1Lumifer
With me, hyperventilation leads to just a woozy/l'm-gonna-faint feeling. As an aside, if you hyperventilate for several minutes, you then can stop breathing for a surprisingly long time. You just go around your daily routine -- and not breathe. It's a weird experience :-/

If you give up on the AIXI agent exploring the entire set of possible hypotheses and instead have it explore a small fixed list, the toy models can be very small. Here is a unit test for something more involved than AIXI that's feasible because of the small hypothesis list.

Getting a programming job is not contingent on getting a degree. There's an easy test for competence at programming in a job interview: ask the candidate to write code on a whiteboard. I am aware of at least one Silicon Valley company that does that and have observed them to hire people who never finished their BS in CS. (I'd rather ask candidates to write code and debug on a laptop, but the HR department won't permit it.)

Getting a degree doesn't hurt. It might push up your salary -- even if one company has enough sense to evaluate the competence of a pro... (read more)

I have experienced consequences of donating blood too often.The blood donation places check your hemoglobin, but I have experienced iron deficiency symptoms when my hemoglobin was normal and my serum ferritin was low. The symptoms were twitchy legs when I was trying to sleep and insomnia, and iron deficiency was confirmed with a ferritin test. The iron deficiency symptoms went away and ferritin went back to normal when I took iron supplements and stopped donating blood, and I stopped the iron supplements after the normal ferritin test.

The blood donation pl... (read more)

2A1987dM
IIRC, where I am they don't even allow you to donate blood if you've already done so in the past three months or, if you're a fertile woman, in the past six months.

Well, I suppose it's an improvement that you've identified what you're arguing against.

Unfortunately the statements you disagree with don't much resemble what I said. Specifically:

The argument you made was that copy-and-destroy is not bad because a world where that is done is not worse than our own.

I did not compare one world to another.

Pointing out that your definition of something, like harm, is shared by few people is not argumentum ad populum, it's pointing out that you are trying to sound like you're talking about something people care about

... (read more)
1Jiro
Um. (I suppose you could quibble that you didn't say it was not worse, but "not different" is a subset of "not worse"; you certainly did compare one world to another.)

Nothing I have said in this conversation presupposed ignorance, blissful or otherwise.

I give up, feel free to disagree with what you imagine I said.

Check out Argumentum ad Populum. With all the references to "most people", you seem to be committing that fallacy so often that I am unable to identify anything else in what you say.

-4Jiro
The argument you made was that copy-and-destroy is not bad because a world where that is done is not worse than our own. In turn, your belief that it is not worse than our own is, as far as I can tell, based on the belief that you can compare that world to our own by comparing whether it is good for the people who remain alive, and ignoring whether it is good for the people who are killed. This implies that the fact that the person is killed doesn't count towards making the world worse because being dead, he can't know that he has been harmed, and because the other people don't feel the loss they would feel that goes with a normal death. This amounts to blissful ignorance (although I suppose the dead person can be more accurately described as having 'uncaring ignorance', since dead people aren't very blissful). Pointing out that your definition of something, like harm, is shared by few people is not argumentum ad populum, it's pointing out that you are trying to sound like you're talking about something people care about but you're really not.

This reasoning can be used to justify almost any form of "what you don't know won't hurt you". For instance, a world where people cheated on their spouse but it was never discovered would function, from the point of view of everyone, as well as or better than the similar world where they remained faithful.

Your example is too vague for me to want to talk about. Does this world have children that are conceived by sex, children that are expensive to raise, and property rights? Does it have sexually transmitted diseases? Does it have paternity ... (read more)

1Jiro
I'm not saying that most people think this scheme is bad, I'm saying that most people don't have the definition of harm that you do. Your idea that all harm must be knowing is not one commonly shared. And the example has nothing to do with paternity. Most people would think that a world where people are cheated on but it is not discovered is one where the other partner is being harmed, simply because cheating on someone harms them and harm does not have to be knowing in order to be harm. Or, as I summarized, most people don't think blissful ignorance is a good thing.

OTOH, some such choices are worse than others.

If you have an argument, please make it. Pointing off to a page with a laundry list of 37 things isn't an argument.

One way to find useful concepts is to use evolutionary arguments. Imagine a world in which it is useful and possible to commute back and forth to Mars by copy-and-destroy. Some people do it and endure arguments about whether they are still the "same" person when they got back, some people don't do it because of philosophical reservations about being the "same" person. Since w... (read more)

0Jiro
This reasoning can be used to justify almost any form of "what you don't know won't hurt you". For instance, a world where people cheated on their spouse but it was never discovered would function, from the point of view of everyone, as well as or better than the similar world where they remained faithful. Most of us think the former world is bad and, if pressed, would explain it by saying that blissful ignorance is not a good thing. Even though "my spouse cheats on me but I don't know it" and "my spouse doesn't cheat on me" are indistinguishable, I have been harmed in the former situation.

Suppose we define a generalized version of Solomonoff Induction based on some second-order logic. The truth predicate for this logic can’t be defined within the logic and therefore a device that can decide the truth value of arbitrary statements in this logical has no finite description within this logic. If an alien claimed to have such a device, this generalized Solomonoff induction would assign the hypothesis that they're telling the truth zero probability, whereas we would assign it some small but positive probability.

I'm not sure I understand you c... (read more)

Consider an arbitrary probability distribution P, and the smallest integer (or the lexicographically least object) x such that P(x) < 1/3^^^3 (in Knuth's up-arrow notation). Since x has a short description, a universal distribution shouldn't assign it such a low probability, but P does, so P can't be a universal distribution.

The description of x has to include the description of P, and that has to be computable if a universal distribution is going to assign positive probability to x.

If P has a short computable description, then yes, you can conclude ... (read more)

You're absolutely right that learning to lie really well and actually lying to one's family, the "genuinely wonderful people" they know, everyone in one's "social structure" and business, as well as one's husband and daughter MIGHT be the "compassionate thing to do". But why would you pick out exactly that option among all the possibilities?

Because it's a possibility that the post we're talking about apparently did not consider. The Litany of Gendlin was mentioned in the original post, and I think that when interpreted as ... (read more)

You seem to think that if you can imagine even one possible short-term benefit from lying or not-disclosing something, then that's sufficient justification to do so.

That's not what I said. I said several things, and it's not clear which one you're responding to; you should use quote-rebuttal format so people know what you're talking about. Best guess is that you're responding to this:

[learning to lie really well] might be the compassionate thing to do, if you believe that the people you interact with would not benefit from hearing that you no lon

... (read more)
-2Kenny
And that's why I wrote "You seem to think that ..."; I was describing why I thought you would privilege the hypothesis that lying would be better. You're absolutely right that learning to lie really well and actually lying to one's family, the "genuinely wonderful people" they know, everyone in one's "social structure" and business, as well as one's husband and daughter MIGHT be the "compassionate thing to do". But why would you pick out exactly that option among all the possibilities? Actually it wasn't a rhetorical question. I was genuinely curious how you'd describe the boundary. The reason why I think it's a justified presumption to be honest to others is in fact because of a slippery slope argument. Human being's minds run on corrupted hardware and deception is dangerous (for one reason) because it's not always easy to cleanly separate one's lies from one's true beliefs. But your implication (that lying is sometimes right) is correct; there are some obvious or well-known schelling fences on that slippery slope, such as lying to the Nazis when they come to your house while you're hiding Jews. Your initial statement seemed rather cavalier and didn't seem to be the product of sympathetic consideration of the original commenter's situation. Have you considered Crocker's rules? If you care about the truth or you have something to protect then the Litany of Gendlin is a reminder of why you might adopt Crocker's rules, despite the truth possibly not being the "compassionate thing to do".
nshepperd110

The Litany of Gendlin is specifically about what you should or should not believe, and your feelings about reality. It says nothing about telling people what you think is true — although "owning up to it" is confusingly an idiom that normally means admitting the truth to some authority figure, whereas in this case it is meant to indicate admitting the truth to yourself.

Just drink two tablespoons of extra-light olive oil early in the morning... don't eat anything else for at least an hour afterward... and in a few days it will no longer take willpower to eat less; you'll feel so full all the time, you'll have to remind yourself to eat.

...and then increase the dose to 4 tablespoons if that doesn't work, and then try some other stuff such as crazy-spicing your food if that doesn't work, according to page 62 and Chapter 6 of Roberts' "Shangri-La" Diet" book. I hope you at least tried the higher dose before giving up.

How do you add two utilities together?

They are numbers. Add them.

So are the atmospheric pressure in my room and the price of silver. But you cannot add them together (unless you have a conversion factor from millibars to dollars per ounce).

Your analogy is invalid, and in general analogy is a poor substitute for a rational argument. In the thread you're replying to, I proposed a scheme for getting Alice's utility to be commensurate with Bob's so they can be added. It makes sense to argue that the scheme doesn't work, but it doesn't make sense to pretend it does not exist.

I would expect that peer pressure can make people stop doing evil things (either by force, or by changing their cost-benefit calculation of evil acts). Objective morality, or rather a definition of morality consistent within the group can help organize efficient peer pressure.

So in a conversation between a person A who believes in objective morality and a person B who does not, a possible motive for A is to convince onlookers by any means possible that objective morality exists. Convincing B is not particularly important, since effective peer pressur... (read more)

1wedrifid
"Any means possible" is a euphemism for "really big stick"!
1Richard_Kennaway
As lessdazed has said, that is simply not what the word "fallacy" means. Neither is a utility function, in the sense of VNM, merely a function from world states to numbers; it is a function from lotteries over outcomes to numbers that satisfies their axioms. The TSUF does not satisfy those axioms. No function whose range includes 0, 1, and nothing in between can satisfy the VNM axioms. The range of a VNM utility function must be an interval of real numbers. Ignored.
2Richard_Kennaway
Perhaps you are not reading carefully enough.
lessdazed120

A fallacy is a false statement

Not a pattern of an invalid argument?

With [the universal] prior, TSUF-like utility functions aren't going to dominate the set of utility functions consistent with the person's behavior

How do you know this? If that's true, it can only be true by being a mathematical theorem...

No, it's true in the same sense that the statement "I have hands" is true. That is, it's an informal empirical statement about the world. People can be vaguely understood as having purposeful behavior. When you put them in strange situations, this breaks down a bit and if you wish to understand them as hav... (read more)

Some agents, but not all of them, determine their actions entirely using a time-invariant scalar function U(s) over the state space.

If we're talking about ascribing utility functions to humans, then the state space is the universe, right? (That is, the same universe the astronomers talk about.) In that case, the state space contains clocks, so there's no problem with having a time-dependent utility function, since the time is already present in the domain of the utility function.

Thus, I don't see the semantic misunderstanding -- human behavior is cons... (read more)

This is the Texas Sharpshooter fallacy again. Labelling what a system does with 1 and what it does not with 0 tells you nothing about the system.

You say "again", but in the cited link it's called the "Texas Sharpshooter Utility Function". The word "fallacy" does not appear. If you're going to claim there's a fallacy here, you should support that statement. Where's the fallacy?

It makes no predictions. It does not constrain expectation in any way. It is woo.

The original claim was that human behavior does not conform t... (read more)

0Richard_Kennaway
How do you know this? If that's true, it can only be true by being a mathematical theorem, which will require defining mathematically what makes a UF a TSUF. I expect this is possible, but I'll have to think about it.
0Richard_Kennaway
I was referring to the same fallacy in both cases. Perhaps I should have written out TSUF in full this time. The fallacy is the one I just described: attaching a utility function post hoc to what the system does and does not do. I am disagreeing, by saying that the triviality of the counterexample is so great as to vitiate it entirely. The TSUF is not a utility function. One might as well say that a rock has a utility of 1 for just lying there and 0 for leaping into the air. You have to model them as if they want many things, some of them being from time to time in conflict with each other. The reason for this is that they do want many things, some of them being from time to time in conflict with each other. Members of LessWrong regularly make personal posts on such matters, generally under the heading of "akrasia", so it's not as if I was proposing here some strange new idea of human nature. The problem of dealing with such conflicts is a regular topic here. And yet there is still a (not universal but pervasive) assumption that acting according to a utility function is the pinnacle of rational behaviour. Responding to that conundrum with TSUFs is pretty much isomorphic to the parable of the Heartstone. I know the von Neumann-Morgenstern theorem on utility functions, but since they begin by assuming a total preference ordering on states of the world, it would be begging the question to cite it in support of human utility functions.

The Utility Theory folks showed that behavior of an agent can be captured by a numerical utility function iff the agent's preferences conform to certain axioms, and Allais and others have shown that human behavior emphatically does not.

A person's behavior can always be understood as optimizing a utility function, it just that if they are irrational (as in the Allais paradox) the utility functions start to look ridiculously complex. If all else fails, a utility function can be used that has a strong dependency on time in whatever way is required to matc... (read more)

2taw
Models relying on expected utility make extremely strong assumption about treatment of probabilities with utility being strictly linear in probability, and these assumptions can be very easily demonstrated to be wrong. They also make assumptions that many situations are equivalent (pay $50 for 50% chance to win $100 vs accept $50 for 50% chance of losing $100) where all experiments show otherwise. Utility theory without these assumptions predicts nothing whatsoever.
0kjmiller
Seems to me we've got a gen-u-ine semantic misunderstanding on our hands here, Tim :) My understanding of these ideas is mostly taken from reinforcement learning theory in AI (a la Sutton & Barto 1998). In general, an agent is determined by a policy pi that determines the probability that the agent will make a particular action in a particular state, P = pi(s,a). In the most general case, Pi can also depend on time, and is typically quite complicated, though usually not complex ;). Any computable agent operating over any possible state and action space can be represented by some function pi, though typically folks in this field deal in Markov Decision Processes since they're computationally tractable. More on that in the book, or in a longer post if folks are interested. It seems to me that when you say "utility function", you're thinking of something a lot like pi. If I'm wrong about that, please let me know When folks in the RL field talk about "utility functions", generally they've got something a little different in mind. Some agents, but not all of them, determine their actions entirely using a time-invariant scalar function U(s) over the state space. U takes in future states of the world and outputs the reward that the agent can expect to receive upon reaching that state (loosely "how much the agent likes s"). Since each action in general leads to a range of different future states with different probabilities, you can use U(s) to get an expected utility U'(a,s): U'(a,s) = sum((p(s,a,s')*U(s')), where s is the state you're in, a is the action you take, s' are the possible future states, and p is the probability than action a taken in state s will lead to state s'. Once your agent has a U', some simple decision rule over that is enough to determine the agent's policy. There are a bunch of cool things about agents that do this, one of which (not the most important) is that their behavior is much easier to predict. This is because behavior is determined entir
7Richard_Kennaway
This is the Texas Sharpshooter fallacy again. Labelling what a system does with 1 and what it does not with 0 tells you nothing about the system. It makes no predictions. It does not constrain expectation in any way. It is woo. Woo need not look like talk of chakras and crystals and angels. It can just as easily be dressed in the clothes of science and mathematics.

Before my rejection of faith, I was plagued by a feeling of impending doom.

I was a happy atheist until I learned about the Friendly AI problem and estimated the likely outcome. I am now plagued by a feeling of impending doom.

4khafra
As an atheist, I was seriously bothered by the thought of my inevitable, irreversible death in just a few decades. As a Friendly AItheist, I'm seriously bothered by the thought of highly probable astronomical waste, but cheered by the thought of MWI putting more of my future probability mass in universes that turn out really nifty, especially if I can help out with its creation. Of course, unless something like mangling takes place, MWI + quantum immortality is far more horrifying than astronomical waste.
2wedrifid
I've got the impending doom but I don't bother with the 'plagued' bit. Why on earth should lack of incomprehension oblige me to experience negative emotion or adverse psychological states? That makes no sense.

If everyone's inferred utility goes from 0 to 1, and the real-life utility monster cares more than the other people about one thing, the inferred utility will say he cares less than other people about something else. Let him play that game until the something else happens, then he loses, and that's a fine outcome.

That's not the situation I'm describing; if 0 is "you and all your friends and relatives getting tortured to death" and 1 is "getting everything you want," the utility monster is someone who puts "not getting one thing

... (read more)
-1A1987dM
So are the atmospheric pressure in my room and the price of silver. But you cannot add them together (unless you have a conversion factor from millibars to dollars per ounce).
1Vaniver
What if wants did not exist a priori, but only in response to stimuli? Alice, for example, doesn't care about cookies, she cares about getting her way. If the FAI tells Alice and Bob "look, I have a cookie; how shall I divide it between you?" Alice decides that the cookie is hers and she will throw the biggest tantrum if the FAI decides otherwise, whereas Bob just grumbles to himself. If the FAI tells Alice and Bob individually "look, I'm going to make a cookie just for you, what would you like in it?" both of them enjoy the sugar, the autonomy of choosing, and the feel of specialness, without realizing that they're only eating half of the cookie dough. Suppose Alice is just as happy in both situations, because she got her way in both situations, and that Bob is happier in the second situation, because he gets more cookie. In such a scenario, the FAI would never ask Alice and Bob to come up with a plan to split resources between the two of them, because Alice would turn it into a win/lose situation. It seems to me that an FAI would engage in want curation rather than want satisfaction. As the saying goes, seek to want what you have, rather than seeking to have what you want. A FAI who engages in that behavior would be more interested in a stimuli-response model of human behavior and mental states than a consequentialist-utility model of human behavior and mental states. This is one of the reasons why utility monsters tend to seem self-destructive; they gamble farther and harder than most people would. How do we measure one person's utility? Preferences revealed by actions? (That is, given a mapping from situations to actions to consequences, I can construct a utility function which takes situations and consequences as inputs and returns the decision taken.) If so, when we add two utilities together, does the resulting number still uniquely identify the actions taken by both parties?

There seems to be an assumption here that empathy leads to morality. Sometimes, at least, empathy leads to being jerked around by the stupid goals of others instead of pursuing your own stupid goals, and in this case it's not all that likely to lead to something fitting any plausible definition of "moral behavior". Chogyam Trungpa called this "idiot compassion".

Thus it's important to distinguish caring about humanity as a whole from caring about individual humans. I read some of the links in the OP and did not see this distinction mentioned.

4gwern
Indeed; see http://lesswrong.com/lw/7xr/not_by_empathy_alone/ and in particular the should we section.

I procrastinated when in academia, but did not feel particularly attracted to the job, so option 1 is not always true. Comparison with people not in academia makes it seem that option 3 is not true for me either.

More questions to perhaps add:

What is self-modification? (In particular, does having one AI build another bigger and more wonderful AI while leaving "itself" intact count as self-modification? The naive answer is "no", but I gather the informed answer is "yes", so you'll want to clarify this before using the term.)

What is wrong with the simplest decision theory? (That is, enumerate the possible actions and pick the one for which the expected utility of the outcome is best. I'm not sure what the standard name for that is.) ... (read more)

A common tactic in human interaction is to care about everything more than the other person does, and explode (or become depressed) when they don't get their way. How should such real-life utility monsters be dealt with?

If everyone's inferred utility goes from 0 to 1, and the real-life utility monster cares more than the other people about one thing, the inferred utility will say he cares less than other people about something else. Let him play that game until the something else happens, then he loses, and that's a fine outcome.

I doubt it can measur

... (read more)
-2Vaniver
That's not the situation I'm describing; if 0 is "you and all your friends and relatives getting tortured to death" and 1 is "getting everything you want," the utility monster is someone who puts "not getting one thing I want" at, say, .1 whereas normal people put it at .9999. And if humans turn out to be adaption-executers, then utility is going to look really weird, because it'll depend a lot on framing and behavior. How do you add two utilities together? If you can't add, how can you average? If people dislike losses more than they like gains and status is zero-sum, does that mean the reasonable result of average utilitarianism when applied to status is that everyone must be exactly the same status?

It's understanding of you doesn't have to be more rigorous than your understanding of you.

It does if I want it to give me results any better than I can provide for myself.

No. For example, if it develops some diet drug that lets you safely enjoy eating and still stay skinny and beautiful, that might be a better result than you could provide for yourself, and it doesn't need any special understanding of you to make that happen. It just makes the drug, makes sure you know the consequences of taking it, and offers it to you. If you choose take it, th... (read more)

0Vaniver
It might not need special knowledge of my psychology, but it certainly needs special knowledge of my physiology. But notice that the original point was about human preferences. Even if it provides new technologies that dissolve internal conflicts, the question of whether or not to use the technology becomes a conflict. Remember, we live in a world where some people have strong ethical objections to vaccines. An old psychological finding is that oftentimes, giving people more options makes them worse off. If the AI notices that one of my modules enjoys sensory pleasure, offers to wirehead me, and I reject it on philosophical grounds, I could easily become consumed by regret or struggles with temptation, and wish that I never had been offered wireheading in the first place. I put the argument of internal conflicts first because it was the clearest example, and you'll note it obliquely refers to the argument about status. Did you really think that, if a drug were available to make everyone have perfectly sculpted bodies, one would get the same social satisfaction from that variety of beauty? I doubt it can measure utilities; as I argued two posts ago, and simple average utilitarianism is so wracked with problems I'm not even sure where to begin. A common tactic in human interaction is to care about everything more than the other person does, and explode (or become depressed) when they don't get their way. How should such real-life utility monsters be dealt with? Why do you find status uninteresting?

In some sense, the problem of FAI is the problem of rigorously understanding humans, and evo psych suggests that will be a massively difficult problem.

I think that bar is unreasonably high. If you have conflict between enjoying eating a lot vs being skinny and beautiful, and the FAI helps you do one or the other, then you aren't in a position to complain that it did the wrong thing. It's understanding of you doesn't have to be more rigorous than your understanding of you.

0Vaniver
It does if I want it to give me results any better than I can provide for myself. I also provided the trivial example of internal conflicts- external conflicts are much more problematic. Human desire for status is possibly the source of all human striving and accomplishment. How will a FAI deal with the status conflicts that develop?

For example, maybe you could chill the body rapidly to organ-donation temperatures, garrote the neck,..

It's worse than I said, by the way. If the patient is donating kidneys and is brain dead, the cryonics people want the suspension to happen as soon as possible to minimize further brain damage. The organ donation people want the organ donation to happen when the surgical team and recipient are ready, so there will be conflict over the schedule.

In any case, the fraction of organ donors is small, and the fraction of cryonics cases is much smaller, and ... (read more)

I would think that knowing evo psych is enough to realize [having an FAI find out human preferences, and then do them] is a dodgy approach at best.

I don't see the connection, but I do care about the issue. Can you attempt to state an argument for that?

Human preferences are an imperfect abstraction. People talk about them all the time and reason usefully about them, so either an AI could do the same, or you found a counterexample to the Church-Turing thesis. "Human preferences" is a useful concept no matter where those preferences come from,... (read more)

2Vaniver
Sure. I think I should clarify first that I meant evo psych should have been sufficient to realize that human preferences are not rigorously coherent. If I tell a FAI to make me do what I want to do, its response is going to be "which you?", as there is no Platonic me with a quickly identifiable utility function that it can optimize for me. There's just a bunch of modules that won the evolutionary tournament of survival because they're a good way to make grandchildren. If I am conflicted between the emotional satisfaction of food and the emotional dissatisfaction of exercise combined with the social satisfaction of beauty, will a FAI be able to resolve that for me any more easily than I can resolve it? If my far mode desires are rooted in my desire to have a good social identity, should the FAI choose those over my near mode desires which are rooted in my desire to survive and enjoy life? In some sense, the problem of FAI is the problem of rigorously understanding humans, and evo psych suggests that will be a massively difficult problem. That's what I was trying to suggest with my comment.

The process of vitrifying the head makes the rest of the body unsuitable for organ donations. If the organs are extracted first, then the large resulting leaks in the circulatory system make perfusing the brain difficult. If the organs are extracted after the brain is properly perfused, they've been perfused too, and with the wrong substances for the purposes of organ donation.

3kragensitaker
Oh, thank you! I didn't realize that. Perhaps a process could be developed? For example, maybe you could chill the body rapidly to organ-donation temperatures, garrote the neck, extract the organs while maintaining head blood pressure with the garrote, then remove the head and connect perfusion apparatus to it?

If "humility" can be used to justify both activities and their opposites so easily, perhaps it's a useless concept and should be tabooed.

0Navanen
It seems to me to be the case that when confronting rationalists, those who have a belief they're motivated to continue to hold will attempt to manipulate rationalists into withdrawing skepticism or risk social disapproval. For example, when creationists ask something like "how can you be sure you're absolutely right about evolution?", I believe the actual intention is not to induce humility on the part of the evolutionist, but to appeal and warning for the evolutionist not to risk the creationist's disapproval. So, it's crucial to identify the difference between when someone else wants you to be humble, and when someone wants you to be socially modest so you don't frustrate them by challenging their beliefs. There's better discussion than what I can produce on when humility is and isn't useful in the comments of the SEQ RERUN of this post NOTE: edited for simplicity and grammar.

PMing or emailing official SIAI people should get to link to safer avenues to discussing these kinds of basilisks.

Hmm, should I vote you up because what you're saying is true, or should I vote you down because you are attracting attention to the parent post which harmful to think about?

If an idea is guessable, then it seems irrational to think it is harmful to communicate it to somebody, since they could have guessed it themselves. Given that this is a website about rationality, IMO we should be able to talk about the chain of reasoning that leads to t... (read more)

Make sure that each CSA above the lowest level actually has "could", "should", and "would" labels on the nodes in its problem space, and make sure that those labels, their values, and the problem space itself can be reduced to the managing of the CSAs on the level below.

That statement would be much more useful if you gave a specific example. I don't see how labels on the nodes are supposed to influence the final result.

There's a general principle here that I wish I could state well. It's something like "general ideas... (read more)

1Ronny Fernandez
Well, you can see how labeling some nodes as "can" and some as "can't" could be useful, I'm sure. The "woulds" tell the agent what it can do from a given node, i.e., what nodes are connected to this node and how much pay off there is for choosing this node. The should labels are calculated from the "woulds" and utility function, i.e., the should label's value tells the agent to take the action or not take it. I'm not trying to solve the specific parts of the problem in this post, I'm trying to pose the problem so that we can work out the specific parts; that's why it is called "Towards a New Decision Theory for Parallel Agents" rather than "A New Decision Theory for Parallel Agents". That's also why I am trying to assemble a team of people to help me work out the more specific parts of the problem. What you quoted was a suggestion I gave to any team that might pursue the goal of an axiomatic parallel decision theory independently, any such team, I would imagine, would understand what I meant by it, specially if they looked at the link right above it: http://lesswrong.com/lw/174/decision_theory_why_we_need_to_reduce_could_would/ .

Well, one story is that humans and brains are irrational, and then you don't need a utility function or any other specific description of how it works. Just figure out what's really there and model it.

The other story is that we're hoping to make a Friendly AI that might make rational decisions to help people get what they want in some sense. The only way I can see to do that is to model people as though they actually want something, which seems to imply having a utility function that says what they want more and what they want less. Yes, it's not true, ... (read more)

2Ronny Fernandez
That's suggestion five on the list: Figuring out exactly how it is that our preferences, i.e., our utility function, emerge from the managing of our subagents is my main motivation for suggesting the construction of a parallel decision theory, as well as understanding how our problem space emerges from the managing of other CSAs.

Okay, I watched End of Evangelion and a variety of the materials leading up to it. I want my time back. I don't recommend it.

3Raw_Power
You watched EoE without watching the series first? Instead you watched "Death And Rebirth"? ... That's probably the wrongest possible way to do it. It's like watching 2001 a Space Odyssey starting from when Dave gets on the pod and into the Jupiter monolith. Like, there's no point to EoE if you aren't already very familiar with the characters AND very very invested in them and the plot.

So many people might be willing to go be a health worker in a poor country where aid workers are commonly (1 in 10,000) raped or killed, even though they would not be willing to be certainly attacked in exchange for 10,000 times the benefits to others.

I agree with your main point, but the thought experiment seems to be based on the false assumption that the risk of being raped or murdered are smaller than 1 in 10K if you stay at home. Wikipedia guesstimates that 1 in 6 women in the US are on the receiving end of attempted rape at some point, so someone... (read more)

The story isn't working for me. A boy or novice soldier, depending on how you define it, is inexplicably given the job of running a huge and difficult-to-use robot to fight with a sequence of powerful similarly huge aliens while trying not to do too much collateral damage to Tokyo in the process. In the original, I gather he was an unhappy boy. In this story, he's a relatively well-adjusted boy who hallucinates conversations with his Warhammer figurines. I don't see why I should care about this scenario or any similar scenarios, but maybe I'm missing s... (read more)

0Raw_Power
It's not pseudo profound, but, like The Matrix, it has a lot of window-dressing and pomous wanking around absolutely legitimate questions. It's also frustrating in that many of the questions are asked, but few are resolved. And they're mainly a framework for the character arcs to develop. Eva has a very simple plot, which it doses very carefully in order to make it more interesting, so that it comes off as a Jigsaw puzzle. The most interesting thing is how the characters evolve and... really, I don't want to spoil anything, but you should definitely give it a try: it's a character story where the characters are extremely human, layered, and rich, and their stories are extremely poignantes. If you don't want to watch the original, all I can tell you is, the "inexplicable" turns out to be "not explained yet". Everything will be revealed in due time. As for why it is interesting... well, if you watch EVA, and especially the final movie, The End Of Evangelion, you might identify a lot with Shinji, put a lot of yourself into him. This is especially true if you watch it as a teenager of the same age. And then... well, stuff happens to him, and to you, by proxy. Seeing him well-adjusted, happy, strong, while still having the same fundamental character traits... it's a very intense feeling.

Your strength as a rationalist is your ability to be more confused by fiction than by reality.

Does that lead to the conclusion that Newcomb's problem is irrelevant? Mind-reading aliens are pretty clearly fiction. Anyone who says otherwise is much more likely to be schizophrenic than to have actual information about mind-reading aliens.

0XiXiDu
This reminds me of the very first comment on the Pascal's Mugging post. Thought experiments are good "to ask how meaningful would someone’s position on an issue be if it were taken to its logical extreme".
2[anonymous]
I'm pretty sure Eliezer thinks this heuristic should be applied to events that occurred in the past, not ones that will occur in the future--it's a way of assessing whether a piece of evidence should be trusted or whether we should defy it. It's also a way of weeding out hypotheses that don't actually make experimental predictions. I don't think he's trying to say that we should ignore things that seem weird, particularly because he speaks out against the absurdity heuristic later on.

When dealing with trolls, whether on the Internet or in Real Life, no matter how absolutely damn sure you are of your point, you have no time to unravel their bullshit for what it is, and if you try it you will only bore your audience and exhaust their patience. Debates aren't battles of truth: there's publishing papers and articles for that. Debates are battles of status.

I agree. There's also the scenario where you're talking to a reasonable person for the purpose of figuring out the truth better than either of you could do alone. That's useful, and ... (read more)

-1Raw_Power
That's okay for Internet trolls, but sometimes you'll have to confront people in Real Life. These people won't be aiming to make a point, they'll be aiming to discredit you, by whatever means necessary. When I wrote this article, one of the scenarios I had in mind was "What if I was forced to confront Bill O'Reily (or some similarly hostile, dirty opponent) on the topic of Less Wrong, and how do I not only "not lose points" but actually come out making us look even cooler than before? Bonus point if he loses status, not among those who already despise him, but among his own fans". Ideally destroying his career, but that's a pretty big dream.

Terror Management seems to explain the reactions to cryonics pretty well. I've only skimmed the OP enough to want to trot out the standard explanation, so I may have missed something, but so far as I can tell the Historical Death Meme and Terror Management make the same predictions.

It is in fact absolutely unacceptable, from a simple humanitarian perspective, that something as nebulous as the HDM -- however artistic, cultural, and deeply ingrained it may be -- should ever be substituted for an actual human life.

Accepting something is the first step to changing it, so you'll have to do better than that.

Please tell me you've at least read Methods Of Rationality and Shinji and Warhammer40k.

I read the presently existing part of MoR. I could read Shinji 40K. Why do you think it's worthwhile? Should I read or watch Neon Genesis Evangelion first?

0Raw_Power
Hm, reading the original EVA is not compulsory, the story stands very well on its own... but since you ask, I heartily recommend you watch EVA and Gurren Lagann. They are both flawed, but they are still very good, and very memorable.

I have a fear that becoming skilled at bullshitting others will increase my ability to bullshit myself. This is based on my informal observation that the people who bullshit me tend to be a bit confused even when manipulating me isn't their immediate goal.

However, I do find that being able to authoritatively blame someone else who is using a well-known rhetorical technique for doing that is very useful, and therefore I have found reading "Art of Controversy" to be very useful. The obviously useful skill is to be able to recognize each rhetorical technique and be able to find a suitable retort in real time; the default retort is to name the rhetorical technique.

1Raw_Power
True story. I know a girl that has completely lost the ability to distinguish between her lies and reality. For example, if for some reason she says she doesn't like an item of food that she is known to like, just to piss off her parents, she will henceforth always act as if she hates it. If you slip it into the food and she aks what's making the food so delicious, and you tell her what's in it, she will immediately stop liking it even though she was relishing it a minute ago. That's just one of the examples I can summon. She believes in her bullshit very strongly on a conscious level, but subconsciously, what is true remains so, and this leads to some very amusing behavior (amusing because she insists she is fine the way she is and is generally a very obnoxious person).
2deepthoughtlife
Why shouldn't you want to bullshit yourself? You'll get to believe you are the most successful man on earth, even after getting evicted. Your children will all be geniuses who will change the world, even after flunking out of high school. Your arguments will be untouchable, even after everyone else agrees you lost. Obviously, I believe said fear is highly legitimate, if the premise is true. People who are talking bullshit do generally seem to be confused in my experience as well, but BS being caused at least in part by that confusion seems to be a highly likely scenario. Some things done in an external setting do affect similar internal processes, but not all. An (quick and dirty) inductive argument follows: Premise 1: It is far easier to BS than to logically analyze and respond. Premise 2: It is far faster to BS than to logically analyze and respond. Premise 3: People prefer to do things that are easier, ceteris paribus. Premise 4: People prefer to do things that are faster, ceteris paribus. Premise 5: People very strongly do not want to be wrong. Premise 6: Losing the argument is a significant proxy for being wrong. Premise 7: Winning the argument is a significant proxy for being right. (Intermediate)Conclusion 1: If BS wins you the argument, you will prefer BS to logical analysis and response. (Intermediate)Conclusion 2: If BS loses you the argument, you will regard BS far more poorly as an option. (Intermediate)Conclusion 3: Being good enough at BS to consistently win (necessarily avoid losing) arguments drastically increases the chance you will not resort to logical analysis and response, at all. Final Conclusion: If you BS to others, you will BS to yourself. ---------------------------------------- On the idea that it is useful to know when another is using one of the devices of blowing smoke, you are obviously correct, but it can be very tempting to misuse such knowledge simply to browbeat your opponent, when they haven't actually done it. In a similar

minds are behavior-executors and not utility-maximizers

I think it would be more accurate to say that minds are more accurately and simply modeled as behavior-executors than as utility-maximizers.

There are situations where the most accurate and simple model isn't the one you want to use. For example, if I'm wanting to cooperate with somebody, one approach is to model them as a utility-maximizer, and then to search for actions that improve everybody's utility. If I model them as a behavior-executors then I'll be perceived as manipulative if I don't get ... (read more)

4Strange7
That's the difference between trying to save cute pandas and trying to rebalance a broken ecosystem. To give somebody good advice, you need to understand what they actually want. Then you can introduce an idea into their mind for a behavior which will lead to them succeeding. The customer never knows what he really needs ; if he did, he wouldn't be a customer.

An alternative to CEV is CV, that is, leave out the extrapolation.

You have a bunch of non-extrapolated people now, and I don't see why we should think their extrapolated desires are morally superior to their present desires. Giving them their extrapolated desires instead of their current desires puts you into conflict with the non-extrapolated version of them, and I'm not sure what worthwhile thing you're going to get in exchange for that.

Nobody has lived 1000 years yet; maybe extrapolating human desires out to 1000 years gives something that a normal h... (read more)

Peter Wakker apparently thinks he found a way to have unbounded utilities and obey most of Savage's axioms. See Unbounded utility for Savage's "Foundations of Statistics," and other models. I'll say more if and when I understand that paper.

We can't use Solomonoff induction - because it is uncomputable.

Generating hypotheses is uncomputable. However, once you have a candidate hypothesis, if it explains the observations you can do a computation to verify that, and you can always measure its complexity. So you'll never know that you have the best hypothesis, but you can compare hypotheses for quality.

I'd really like to know if there's anything to be known about the nature of the suboptimal predictions you'll make if you use suboptimal hypotheses, since we're pretty much certain to be using suboptimal hypotheses.

I agree with jsteinhardt, thanks for the reference.

I agree that the reward functions will vary in complexity. If you do the usual thing in Solomonoff induction, where the plausibility of a reward function decreases exponentially with its size, so far as I can tell you can infer reward fuctions from behavior, if you can infer behavior.

We need to infer a utility function for somebody if we're going to help them get what they want, since a utility function is the only reasonable description I know of what an agent wants.

Surely we can talk about rational agents in other ways that are not so confusing?

Who is sure? If you're saying that, I hope you are. What do you propose?

Either way, just because something is mathematically proven to exist doesn't mean that we should have to use it.

I don't think anybody advocated what you're arguing against there.

The nearest thing I'm willing to argue for is that one of the following possibilities hold:

  • We use something that has been mathematically proven to exist, now.

  • We might be speaking nonsense, depending on whether the conc

... (read more)
Load More