So, I have next to no academic knowledge. I have literally not read or perhaps even picked up any book since eighth grade, which is where my formal education ended, and I turn 20 this year, but I am sitting on some theories pertaining to my understanding of rationality, and procrastinating about expressing them has gotten me here. I'd like to just propose my theory on why censorship is wrong, here. Please tell me whether or not you agree or disagree, and feel free to express anything else you feel you would like to in this thread. I miss bona fide argument, but this community seems way less hostile than the one community I was involved in elsewhere....

Also, I feel I should affirm again that my academic knowledge is almost entirely just not there... I know the LessWrong community has a ton of resources they turn to and indulge in, which is more or less a bible of rationality by which you all abide, but I have read or heard of none of it. I don't mean to offend you with my willful ignorance. Sorry. Also, sorry for possibly incorporating similes and stuff into my expression... I know many out there are on the autistic spectrum and can't comprehend it so I'll try to stop doing that unless I'm making a point.

Okay, so, since the following has been bothering me a lot since I joined this site yesterday and even made me think against titling this what I want, consider the written and spoken word. Humans literally decided as a species to sequence scribbles and mouth noises in an entirely arbitrary way, ascribe emotion to their arbitrary scribbles and mouth noises, and then claim, as a species, that very specific arbitrary scribbles and mouth noises are inherent evil and not to be expressed by any human. Isn't that fucking retarded?

I know what you may be thinking. You might be thinking, "wow, this hoofwall character just fucking wrote a fucking arbitrary scribble that my species has arbitrarily claimed to be inherent evil without first formally affirming, absolutely, that the arbitrary scribble he uttered could never be inherent evil and that writing it could never in itself do any harm. This dude obviously has no interest in successfully defending himself in argument". But fuck that. This is not the same as murdering a human and trying to conceive an excuse defending the act later. This is not the same as effecting the world in any way that has been established to be detrimental and then trying to defend the act later. This is literally sequencing the very letters of the very language the human has decided they are okay with and will use to express themselves in such a way that it reminds the indoctrinated and conditioned human of emotion they irrationally ascribe to the sequence of letters I wrote. This is possibly the purest argument conceivable for demonstrating superfluity in the human world, and the human psyche. There could never be an inherent correlation to one's emotionality and an arbitrary sequence of mouth noises or scribbles or whatever have you that exist entirely independent of the human. If one were to erase an arbitrary scribble that the human irrationally ascribes emotion to, the human will still have the capacity to feel the emotion the arbitrary scribble roused within them. The scribble is not literally the embodiment of emotionality. This is why censorship is retarded.

Mind you, I do not discriminate against literal retards, or blacks, or gays, or anything. I do, however, incorporate the words "retard", "nigger", and "faggot" into my vocabulary literally exclusively because it triggers humans and demonstrates the fact that the validity of one's argument and one's ability to defend themselves in argument does not matter to the human. I have at times proposed my entire argument, actually going so far to quantify the breadth of this universe as I perceive it, the human existence, emotionality, and right and wrong before even uttering a fuckdamn swear, but it didn't matter. Humans think plugging their ears and chanting a mantra of "lalala" somehow gives themselves a valid argument for their bullshit, but whatever. Affirming how irrational the human is is a waste of time. There are other forms of censorship I shout address, as well, but I suppose not before proposing what I perceive the breadth of everything less fundamental than the human to be.

It's probably very easy to deduce the following, but nothing can be proven to exist. Also, please do bear with my what are probably argument by assertion fallacies at the moment... I plan on defending myself before this post ends.

Any opinion any human conceives is just a consequence of their own perception, the likes of which appears to be a consequence of their physical form, the likes of which is a consequence of properties in this universe as we perceive it. We cannot prove our universe's existence beyond what we have access to in our universe as we perceive it, therefore we cannot prove that we exist. We can't prove that our understanding of existence is true existence; we can only prove, within our universe, that certain things appear to be in concurrence with the laws of this universe as we perceive it. We can propose for example that an apple we can see occupies space in this universe, but we can't prove that our universe actually exists beyond our understanding of what existence is. We can't go more fundamental than what composes our universe... We can't go up if we are mutually exclusive with the very idea of "up", or are an inferior consequence of "up" which is superior to us.

I really don't remember what else I would say after this but, I guess, without divulging how much I obsess about breaking emotionality into a science, I believe nudity can't be inherent evil either because it is literally the cause of us, the human, and we are necessary to be able to perceive good and evil in the first place. If humans were not extant to dominate the world and force it to tend to the end they wanted it to anything living would just live, breed, and die, and nothing would be inherently "good" or "evil". It would just be. Until something evolved if it would to gain the capacity to force distinctions between "good" and "evil" there would be no such constructs. We have no reason to believe there would be. I don't know how I can affirm that further. If nudity- and exclusively human nudity, mind you- were to be considered inherent evil that would mean that the human is inherent evil, that everything the human perceives is is inherent evil and that the human's understanding of "rationality" is just a poor, grossly-misled attempt at coping with the evil properties that they retain and is inherently worthless. Which I actually believe, but an opinion that contrary is literally satanism and fuck me if I think I'm going to be expounding all of that here. But fundamentally, human nudity cannot be inherent evil if the human's opinions are to be considered worth anything at all, and if you want to go less fundamental than that and approach it from a "but nudity makes me feel bad" standpoint, you can simply warp your perception of the world to force seeing or otherwise being reminded of things to be correlated to certain emotion within you. I'm autistic it seems so I obsess about breaking emotionality down to a science every day but this isn't the post to be talking about shit like that. In any case, you can't prove that the act of you seeing another human naked is literal evil, so fuck you and your worthless opinions.

Yeah... I don't know what else I could say here, or if censorship exists in forms other than preventing humans from being exposed to human nudity, or human-conceived words. I should probably assert as well that I believe the human's thinking that the inherent evil of human nudity somehow becomes okay to see when a human reaches the age of 18, or 21, or 16, or 12 depending on which subset of human you ask is retarded. Also, by "retarded" I do not literally mean "retarded". I use the word as a trigger word that's meant to embody and convey bad emotion the human decides they want to feel when they're exposed to it. This entire post is dripping with the grossest misanthropy but I'm interested in seeing what the responses to this are... By the way, if you just downvote me without expressing to me what you think I'm doing wrong, as far as I can tell you are just satisfied with vaguely masturbating your dissenting opinion you care not for even defining in my direction, so, whatever makes you sleep at night, if you do that... but you're wrong though, and I would argue that to the death.

A putative new idea for AI control; index here.

A lot of my ideas rely upon taking counterfactuals of events that have tiny ε probabilities of ever happening. This introduces some extra risks, mainly centred around human behaviour. For the counterfactual methods to work, we need the alternate world to be sensible, without things going crazy due to human action.

For instance, imagine that X defines an event where an AI would get turned on, with ¬X (of probability ε) corresponding to the AI failing to get turned on. There are two risks here: the first is that humans would react by saying "wow, an event of probability of ε actually happened; all our models must be wrong! Let's go crazy! Yay!". The second is that humans react by saying: "well, that was embarrassing - let's turn the AI on anyway."

To avoid this issue, imagine the following setup:

The "ON" signal first goes through an event Y, which has 99% chance of letting it through, then to the event X, which (as before) has a 1-ε chance of letting it through. The setup is designed so that humans cannot distinguish between ¬Y (the signal gets blocked at the first stage) and ¬X (the signal gets blocked at the second stage). This only needs to fool humans, not the AI itself.

The AI defines counterfactuals, as before, by looking at ¬X (possibly conditioning on Y versus ¬Y, if this is needed). Everything proceeds as previously from its perspective.

From the human perspective, however, the ¬X world is not distinguishable from the ¬Y one. Given (¬Y or ¬X), humans would conclude that ¬Y is the much more likely option:

P(¬Y|¬Y or ¬X)≈1-100ε.

So the ¬X counterfactual world (for the AI) is one where humans behave as if they were in the ¬Y world.

And ¬Y has one chance in a hundred of happening, which is unlikely, but not enough for humans to assume that their whole model of reality is wrong. Also, this is sufficiently likely that humans would give serious thought as to what to do in the ¬Y case, maybe arranging various pre-commitments or insurance options, making it possible to arrange (with high probability) that humans don't just ignore the result and try again immediately.

Note that this method can't be used (obviously) if ¬X is something hideously dangerous (like an unleashed UFAI), but in all other cases, it seems implementable.

Do Virtual Humans deserve human rights?

Slate Article

I think the idea of storing our minds in a machine so that we can keep on "living" (and I use that term loosely) is fascinating and certainly and oft discussed topic around here. However, in thinking about keeping our brains on a hard drive we have to think about rights and how that all works together. Indeed the technology may be here before we know it so I think its important to think about mindclones. If I create a little version of myself that can answer my emails for me, can I delete him when I'm done with him or just turn him in for a new model like I do iPhones? 

I look forward to the discussion.

TRIGGER WARNING: PHILOSOPHY.  All those who believe in truly rigorous, scientifically-grounded reasoning should RUN AWAY VERY QUICKLY.

Abstract: Human beings want to make rational decisions, but their decision-making processes are often inefficient, and they don't possess direct knowledge of anything we could call their utility functions.  Since it is much easier to detect a bad world state than a good one (there are vastly more of them, so less information is needed to classify accurately), humans tend to have an easy time detecting bad states, but this emotional regret is no more useful for formal reasoning about human rationality, since we don't possess a causal model of it in terms of decision histories and outcomes.  We tackle this problem head-on, assuming only that humans can reason over a set of beliefs and a perceived state of the world to generate a probability distribution over actions.

Consider rationality: optimizing the world to better and better match a utility function, which is itself complete, transitive, continuous, and gives results which are independent of irrelevant alternatives.  Now consider actually existing human beings: creatures who can often and easily be tricked into taking Dutch Book bets through exploitation of their cognitive structure, without even having to go to the trouble of actually deceiving them with regards to specific information.

Consider that being one of those poor sods must totally suck.  We believe this provides sufficient motivation for wanting to help them out a bit.  Unfortunately, doing so is not very simple: since they didn't evolve as rational creatures, it's very easy to propose an alternate set of values that captures absolutely nothing of what they actually want out of life.  In fact, since they didn't even evolve as 100% self-aware creatures, their emotional qualia are not even reliable indicators of anything we would call a proper utility function.  They know there's something they want out of life, and they know they don't know what it is, but that doesn't help because they still don't know what it is, and knowledge of ignorance does not magically reduce the ignorance.

So!  How can we help them without just overriding them or enslaving them to strange and alien cares?  Well, one barest rudiment of rationality with which evolution did manage to bless them is that they don't always end up "losing", or suffering.  Sometimes, even if only seemingly by luck or by elaborate and informed self-analysis, they do seem to end up pretty happy with themselves, sometimes even over the long term.  We believe that with the door to generating Good Ideas For Humans left open even just this tiny crack, we can construct models of what they ought to be doing.

Let's begin by assuming away the thing we wish we could construct: the human utility function.  We are going to reason as if we have no valid grounds to believe there is any such thing, and make absolutely no reference to anything like one.  This will ensure that our reasoning doesn't get circular.  Instead of modelling humans as utility maximizers, even flawed ones, we will model them simply as generating a probability distribution over potential actions (from which they would choose their real action) given a set of beliefs and a state of the real world.  We will not claim to know or care what causes the probability distribution of potential choices: we just want to construct an algorithm for helping humans know which ones are good.

We can then model human decision making as a two-player game: the human does something, and Nature responds likewise.  Lots of rational agents work this way, so it gives us a more-or-less reasonable way of talking algorithmically about how humans live.  For any given human at any given time, we could take a decent-sized Maximegalor Ubercomputer and just run the simulation, yielding a full description of how the human lives.

The only step where we need to do anything "weird" is in abstracting the human's mind and knowledge of the world from the particular state and location of its body at any given timestep in the simulation.  This doesn't mean taking it out of the body, but instead considering what the same state of the mind might do if placed in multiple place-times and situations, given everything they've experienced previously.  We need this in order to let our simulated humans be genuinely affected and genuinely learn from the consequences of their own actions.

Our game between the simulated human and simulated Nature thus generates a perfectly ordinary game-tree up to some planning horizon H, though it is a probabilistic game tree.  Each edge represents a conditional probability of the human or Nature making some move given their current state.  The multiplication of all probabilities for all edges along a path from the root-node to a leaf-node represents the conditional probability of that leaf node given the root node.  The conditional probabilities attached to all edges leaving an inner node of the tree must sum to 1.0, though there might be a hell of a lot of child nodes.  We assume that an actual human would actually execute the most likely action-edge.

Here is where we actually manage a neat trick for defying the basic human irrationality.  We mentioned earlier that while humans are usually pretty bummed out about their past decisions, sometimes they're not.  If we can separate bummed-out from not-bummed-out in some formal way, we'll have a rigorous way of talking about what it would mean for a given action or history to be good for the human in question.

Our proposal is to consider what a human would say if taken back in time and given the opportunity to advise their past self.  Or, in simpler simulation terms, we consider how a human's choices would be changed by finding out the leaf-node consequences of their root- or inner-node actions, simply by transferring the relevant beliefs and knowledge directly into our model of their minds.  If, upon being given this leaf-node knowledge, the action yielded as most likely changes, or if the version of the human at the leaf-node would, themselves, were they taken back in time, select another action as most likely, then we take a big black meta-magic marker and scribble over that leaf node as suffering from regret.  After all, the human in question could have done something their later self would agree with.

The magic is thus done: coulda + woulda = shoulda.  By coloring some (inevitably: most) leaf-nodes as suffering from regret, we can then measure a probability of regret in any human-versus-Nature game-tree up to any planning horizon H: it's just the sum of all conditional probabilities for all paths from the root node which arrive to a regret-colored leaf-node at or before time H.

We should thus advise the humans to simply treat the probability of arriving to a regret-colored leaf-node as a loss function and minimize it.  By construction, this will yield a rational optimization criterion guaranteed not to make the humans run screaming from their own choices, at least not at or before time-step H.

The further out into time we extend H, the better our advice becomes, as it incorporates a deeper and wider sample of the apparent states which a human life can occupy, thus bringing different motivational adaptations to conscious execution, and allowing their reconciliation via reflection.  Over sufficient amounts of time, this reflection could maybe even quiet down to a stable state, resulting in the humans selecting their actions in a way that's more like a rational agent and less like a pre-evolved meat-ape.  This would hopefully help their lives be much, much nicer, though we cannot actually formally prove that the limit of the human regret probability converges as the planning horizon grows to plus-infinity -- not even to 1.0!

We can also note a couple of interesting properties our loss-function for humans has, particularly its degenerate values and how they relate to the psychology of the underlying semi-rational agent, ie: humans.  When the probability of regret equals 1.0, no matter how far out we extend the planning horizon H, it means we are simply dealing with a totally, utterly irrational mind-design: there literally does not exist a best possible world for that agent in which they would never wish to change their former choices.  They always regret their decisions, which means they've probably got a circular preference or other internal contradiction somewhere.  Yikes, though they could just figure out which particular aspect of their own mind-design causes that and eliminate it, leading to an agent design that can potentially ever like its life.  The other degenerate probability is also interesting: a chance of regret equalling 0.0 means that the agent is either a completely unreflective idiot, or is God.  Even an optimal superintelligence can suffer loss due to not knowing about its environment; it just rids itself of that ignorance optimally as data comes in!

The interesting thing about these degenerate probabilities is that they show our theory to be generally applicable to an entire class of semi-rational agents, not just humans.  Anything with a non-degenerate regret probability, or rather, any agent whose regret probability does not converge to a degenerate value in the limit, can be labelled semi-rational, and can make productive use of the regret probabilities our construction calculates regarding them to make better decisions -- or at least, decisions they will still endorse when asked later on.

Dropping the sense of humor: This might be semi-useful.  Have similar ideas been published in the literature before?  And yes, of course I'm human, but it was funnier that way in what would otherwise have been a very dull, dry philosophy post.

As many of you probably know, Robin Hanson is writing a book, and it will be geared toward a popular audience. He wants a term that encompasses both humans and AI, so he's soliciting your opinions on the matter. Here's the link: http://www.quicksurveys.com/tqsruntime.aspx?surveyData=AYtdr2WMwCzB981F0qkivSNwbj1tn+xvU6rnauc83iU=

H/T Bryan Caplan at EconLog.