Ethics of Brain Emulation 2013-12-04T19:19:37.048Z


Comment by summerstay on Some concepts are like Newton's Gravity, others are like... Luminiferous Aether? · 2015-08-12T15:27:16.778Z · LW · GW

Under theories like loop quantum gravity, doesn't some "fabric of spacetime" exist? I would call that a refinement of the idea of the ether. It has odd properties in order to allow relativity, but it hasn't been ruled out.

Comment by summerstay on Rationality Quotes Thread March 2015 · 2015-04-07T18:18:47.795Z · LW · GW

This is Hari's business. She takes innocuous ingredients and makes you afraid of them by pulling them out of context.... Hari's rule? "If a third grader can't pronounce it, don't eat it." My rule? Don't base your diet on the pronunciation skills of an eight-year-old.


Comment by summerstay on Open thread, Oct. 27 - Nov. 2, 2014 · 2014-10-27T13:52:51.786Z · LW · GW

It would be a lot harder to make a machine that actually is conscious (phenomenally conscious, meaning it has qualia) than it would be to make one that just acts as if is conscious (in that sense). It is my impression that most LW commenters think any future machine that acts conscious probably is conscious.

Comment by summerstay on What false beliefs have you held and why were you wrong? · 2014-10-19T11:19:31.204Z · LW · GW

I only recently realized that evolution works, for the most part, by changing the processes of embryonic development. There are some exceptions-- things like neoteny and metamorphosis-- but most changes are genetic differences leading to differences in, say, how long a process of growth is allowed to occur in the embryo.

Comment by summerstay on Books on consciousness? · 2014-09-24T16:22:48.377Z · LW · GW

There's a reason everyone started calling it "the hard problem." Chalmers explained the problem so clearly that we now basically just point and say "that thing Chalmers was talking about."

Comment by summerstay on Simulate and Defer To More Rational Selves · 2014-09-18T17:09:22.421Z · LW · GW

This is exactly the point of asking "What Would Jesus Do?" Christians are asking themselves, what would a perfectly moral, all-knowing person do in this situation, and using the machinery their brains have for simulating a person to find out the answer, instead of using the general purpose reasoner that is so easily overworked. Of course, simulating a person (especially a god) accurately can be kind of tricky. Similar thoughts religious people use to get themselves to do things that they want to abstractly but are hard in the moment: What would I do if I were the kind of person I want to become? What would a perfectly moral, all-knowing person think about what I'm about to do?

Comment by summerstay on Dissolving the Thread of Personal Identity · 2014-06-01T20:37:14.153Z · LW · GW

I assumed that was the intention of the writers of Donnie Darko. The actual shapes coming out of their chests we got were not right, but you could see this is what they were trying to do.

Comment by summerstay on an ethical puzzle about brain emulation · 2013-12-17T15:09:01.345Z · LW · GW

I think that arguments like this are a good reason to doubt computationalism. That means accepting that two systems performing the same computations can have different experiences, even though they behave in exactly the same way. But we already should have suspected this: it's just like the inverted spectrum problem, where you and I both call the same flower "red," but the subjective experience I have is what you would call "green" if you had it. We know that most computations even in our brains are not accompanied by conscious perceptual experience, so it shouldn't be surprising if we can make a system that does whatever we want, but does it unconsciously.

Comment by summerstay on an ethical puzzle about brain emulation · 2013-12-17T14:58:18.576Z · LW · GW

Sorry, I was just trying to paraphrase the paper in one sentence. The point of the paper is that there is something wrong with computationalism. It attempts to prove that two systems with the same sequence of computational states must have different conscious experiences. It does this by taking a robot brain that calculates the same way as a conscious human brain, and transforms it, always using computationally equivalent steps, to a system that is computationally equivalent to a digital clock. This means that either we accept that a clock is at every moment experiencing everything that can be experienced, or that something is wrong with computationalism. If we take the second option, it means that two systems with the exact same behavior and computational structure can have different perceptual consciousness.

Comment by summerstay on an ethical puzzle about brain emulation · 2013-12-16T16:12:29.219Z · LW · GW

Check out "Counterfactuals Can't Count" for a response to this. Basically, if a recording is different in what it experiences than running a computation, then two computations that calculate the same thing in the same way, but one has bits of code that never run, experience things differently.

Comment by summerstay on Ethics of Brain Emulation · 2013-12-05T14:27:33.258Z · LW · GW

I found the draft via this post from the end of June 2013.

Comment by summerstay on What do we already have right? · 2013-11-25T18:11:37.172Z · LW · GW

One rational ability that people are really good at that is hard (i.e. we haven't made much progress in automating) is applying common sense knowledge to language understanding. Here's a collection of sentences where the referent is ambiguous, but we don't even notice because we are able to match it up as quickly as we read:

Comment by summerstay on Replicating Douglas Lenat's Traveller TCS win with publicly-known techniques · 2013-10-27T13:12:11.241Z · LW · GW

You can read a paper on EURISKO here. My impression is that the program quickly exhausted the insights he put in as heuristics, and began journeying down eccentric paths that were not of interest to a human mathematician.

Comment by summerstay on What should normal people do? · 2013-10-25T16:13:35.775Z · LW · GW

Here's my advice: always check Snopes before forwarding anything.

Comment by summerstay on The Ultimate Newcomb's Problem · 2013-09-10T15:03:20.826Z · LW · GW

Yes, that's what I'm saying. The other ones are meant to prove a point. This one is just to make you laugh, just like the one it is named after.

Comment by summerstay on The Ultimate Newcomb's Problem · 2013-09-10T14:36:20.389Z · LW · GW

I think most of the commenters aren't getting that this is a parody. Edit: It turns out I was wrong.

Comment by summerstay on How sure are you that brain emulations would be conscious? · 2013-08-26T18:00:31.098Z · LW · GW

It's a life and death matter: if the upload won't be ikrase, then he will be killed in the process of uploading. Naturally he doesn't care as much about whether or not a new person will be created than whether he will continue to exist.

Comment by summerstay on How sure are you that brain emulations would be conscious? · 2013-08-26T17:43:06.185Z · LW · GW

We know that some complex processes in our own brains happen unaccompanied by qualia. This is uncontroversial. It doesn't seem unlikely to me that all the processes needed to fake perceptual consciousness convincingly could be implemented using a combination of such processes. I don't know what causes qualia in my brain and so I'm not certain it would be captured by the emulation in question-- for example, the emulation might not be at a high enough level of detail, might not exploit quantum mechanics in the appropriate way, or whatever. Fading and dancing qualia arguments are not really convincing to me because I don't trust my intuition to guide me well in situations where my core self is directly being operated on.
In other words, I am uncertain and so would tend to stick with what I know works (my biological brain) instead of trusting an uploading process to maintain my qualia. (note: 'qualia' may be an unfamiliar term. It means what it is like to experience something, the redness of red. It's a better word to use than consciousness for this because it is more specific.)

Comment by summerstay on New Monthly Thread: Bragging · 2013-08-21T13:45:26.197Z · LW · GW

I turned in my PhD dissertation. Here's the title and first paragraph of the abstract:


Image comprehension is the ability to summarize, translate, and answer basic questions about images. Using original techniques for scene object parsing, material labeling, and activity recognition, a system can gather information about the objects and actions in a scene. When this information is integrated into a deep knowledge base capable of inference, the system becomes capable of performing tasks that, when performed by students, are considered by educators to demonstrate comprehension.

(Basically it is computer vision combined with Cyc.)

Comment by summerstay on Where Are We the Weakest? · 2013-07-10T15:19:16.816Z · LW · GW

Perhaps a good place to start would be the literature on life satisfaction and happiness. Statistically speaking, what changes in life that can be made voluntarily lead to the greatest increase in life satisfaction at the least cost in effort/money/trouble?

Comment by summerstay on For FAI: Is "Molecular Nanotechnology" putting our best foot forward? · 2013-06-25T13:49:49.083Z · LW · GW

I think the reason AI and nanotech often go together in discussions of the future is summed up in this quote by John Cramer: "Nanotechnology will reduce any manufacturing problem, from constructing a vaccine that cures the common cold to fabricating a starship from the elements contained in sea water, to what is essentially a software problem."

Comment by summerstay on Robust Cooperation in the Prisoner's Dilemma · 2013-06-10T10:39:23.718Z · LW · GW

When people make purchasing decisions, pricing models that are too complex make them less likely to purchase. If it's too confusing to figure out whether something is a good deal or not, we generally tend to just assume it's a bad deal. See (Choice Environment, Market Complexity and Consumer Behavior: A Theoretical and Empirical Approach for Incorporating Decision Complexity into Models of Consumer Choice), for example.

Comment by summerstay on [SEQ RERUN] Real-Life Anthropic Weirdness · 2013-04-12T11:24:38.233Z · LW · GW

I occasionally read the blog of Scott Adams, the author of Dilbert. He claims to believe that the world is a simulation, but who can blame him? His own situation is so improbable he must cast about for some explanation. I predict that among celebrities (and the unusually successful in other fields), there is an unusually high amount of belief that just by wanting things hard enough they will come to you-- because, like everyone else, they wished for something in life, but unlike most people, they actually got it.

Comment by summerstay on Rationality Quotes April 2013 · 2013-04-08T14:53:39.841Z · LW · GW

Perhaps Columbus's "genius" was simply to take action. I've noticed this in executives and higher-ranking military officers I've met-- they get a quick view of the possibilities, then they make a decision and execute it. Sometimes it works and sometimes it doesn't, but the success rate is a lot better than for people who never take action at all.

Comment by summerstay on Rationality Quotes March 2013 · 2013-03-04T13:56:06.009Z · LW · GW

This sort of argument was surprisingly common in the 18th and 19th century compared to today. The Federalist Papers, for example, lay out the problem as a set of premises leading inexorably to a conclusion. I find it hard to imagine a politician successfully using such a form of argument today.

At least that's my impression; perhaps appeals to authority and emotion were just as common in the past as today but selection effects prevent me from seeing them.

Comment by summerstay on Calibrating Against Undetectable Utilons and Goal Changing Events (part1) · 2013-02-21T14:27:09.850Z · LW · GW

I really enjoyed the first part of the post-- just thinking about the fact that my future goals will be different from my present ones is a useful idea. I found the bit of hagiography about E.Y. at the end weird and not really on topic. You might just use a one or two sentence example: He wanted to build an A.I., and then later he didn't want to.

Comment by summerstay on Generalizing from One Trend · 2013-01-18T17:26:24.155Z · LW · GW

Regarding Cyberpunk, Gibson wasn't actually making a prediction, not in the way you're thinking. He was always making a commentary on his own time by exaggerating certain aspects of it. See here, for instance:

Comment by summerstay on Morality is Awesome · 2013-01-09T18:04:13.045Z · LW · GW

Great! This means that in order to develop an AI with a proper moral foundation, we just need to reduce the following statements of ethical guidance to predicate logic, and we'll be all set:

  1. Be excellent to each other.
  2. Party on, dudes!
Comment by summerstay on Intelligence explosion in organizations, or why I'm not worried about the singularity · 2012-12-27T16:45:53.293Z · LW · GW

I think trying to understand organizational intelligence would be pretty useful as a way of getting a feel for the variety of possible intelligences. Organizations also have a legal standing as artificial persons, so I imagine that any AI that wanted to protect its interests through legal means would want to be incorporated. I'd like to see this explored further. Any suggestions on good books on the subject of corporations considered as AIs?

Comment by summerstay on Against NHST · 2012-12-21T16:17:29.142Z · LW · GW

Perhaps you would suggest showing the histograms of completion times on each site, along with the 95% confidence error bars?

Comment by summerstay on Against NHST · 2012-12-21T16:07:37.415Z · LW · GW

Can you give me a concrete course of action to take when I am writing a paper reporting my results? Suppose I have created two versions of a website, and timed 30 people completing a task on each web site. The people on the second website were faster. I want my readers to believe that this wasn't merely a statistical coincidence. Normally, I would do a t-test to show this. What are you proposing I do instead? I don't want a generalization like "use Bayesian statistics, " but a concrete example of how one would test the data and report it in a paper.

Comment by summerstay on [LINK] The most important unsolved problems in ethics · 2012-10-22T14:47:40.607Z · LW · GW

Wait, there are solved problems in ethics?

Comment by summerstay on Is xkcd "Think Logically" talking about this site? · 2012-09-25T18:07:54.240Z · LW · GW

I think a lot of people are misunderstanding the linked xkcd, or maybe I am. The way I see it, It's not about misusing the word "logic." It's about people coming in from the outside, thinking that just because they are smart, they know how to solve problems in a field that they are completely inexperienced in, and have spent very little time thinking about compared to those who think about it as a full time job.

Comment by summerstay on Is xkcd "Think Logically" talking about this site? · 2012-09-25T13:51:33.908Z · LW · GW

I thought that Randall Munroe might be talking about LW, but I wasn't sure, so I asked if anyone else had the same impression. At least one other person did. Most people didn't.

Comment by summerstay on Is xkcd "Think Logically" talking about this site? · 2012-09-25T12:52:21.256Z · LW · GW

Look, I like Less Wrong. It's fun. But if you want to have an influence on the world, you need to engage with the discussions the professionals are having. You need to publish in scientific journals. You need to play the game that's out there well enough to win. I don't think people should feel insulted by my suggesting this. Getting insulted by ideas that make us uncomfortable isn't what I feel this place is about.

Comment by summerstay on Is xkcd "Think Logically" talking about this site? · 2012-09-24T22:40:41.371Z · LW · GW

Thanks, I'll try that.

Comment by summerstay on Is xkcd "Think Logically" talking about this site? · 2012-09-24T15:24:25.042Z · LW · GW

I tried to search for it before I posted, but failed to find it. Nice to see at least one other person felt the same way on reading the comic. I feel like we as a group are sometimes guilty of trying to reinvent the wheel instead of participating in the scholarly philosophy and AI communities by publishing papers. It's a lot easier this way, and there's less friction, but some of this has been said before, and smart people have already thought about it.

Comment by summerstay on Cleaning up the "Worst Argument" essay · 2012-09-06T18:48:22.293Z · LW · GW

"it doesn't share any of the characteristics that make you object to murder of the usual sort." I disagree -- it shares the most salient aspect of murder, namely the harm it does to the future of the human being being murdered. The other features are also objectionable, but a case of murder that doesn't have any of those features (say, the painless murder of a baby with no close acquaintances, friends or family) is still rightfully considered murder. This is why most abortion advocates (unlike the author of this article) do not consider a fetus a "human being" at all. If they did, they would have to confront this argument head on.

Comment by summerstay on Rationality Quotes August 2012 · 2012-08-04T14:41:24.310Z · LW · GW

Interviewer: How do you answer critics who suggest that your team is playing god here?

Craig Venter: Oh... we're not playing.

Comment by summerstay on Reply to Holden on The Singularity Institute · 2012-07-18T14:06:22.541Z · LW · GW

There are very few people who would have understood in the 18th century, but Leibniz would have understood in the 17th. He underestimated the difficulty in creating an AI, like everyone did before the 1970s, but he was explicitly trying to do it.

Comment by summerstay on Applied Picoeconomics · 2012-05-07T12:36:08.493Z · LW · GW

Oh, it's not so bad a quote. If we define sanity around here as being more Bayesian (that's the waterline we're trying to raise, right?) then defining insanity as refusal to update when more data comes would make sense.

Comment by summerstay on Harry Potter and the Methods of Rationality discussion thread, part 14, chapter 82 · 2012-05-02T18:11:29.908Z · LW · GW

I was thinking the same thing. The things he thinks should be obvious by now (such as the quirrel/voldemort connection) ought to be made explicit in an appropriate point-of-view so we can puzzle over the things that he wants the reader to be puzzling over.

Comment by summerstay on Harry Potter and the Methods of Rationality discussion thread, part 13, chapter 81 · 2012-04-04T13:29:02.353Z · LW · GW

When we exert willpower or mental effort, it uses up glucose from the blood in the brain. One way you could explain the exhaustion that comes from using magic is that it requires mental effort to the point of creating dangerously low levels of blood sugar in the brain.

Comment by summerstay on Harry Potter and the Methods of Rationality discussion thread, part 13, chapter 81 · 2012-04-04T13:22:37.137Z · LW · GW

I'm kidding, by the way. Anyone who has seen it would know that it has a lot of broad slapstick humor.

Comment by summerstay on Harry Potter and the Methods of Rationality discussion thread, part 13, chapter 81 · 2012-04-01T01:11:27.300Z · LW · GW

Fawlty Towers is a good example of the understated and deadpan nature of British comedy.

Comment by summerstay on Harry Potter and the Methods of Rationality discussion thread, part 11 · 2012-03-19T12:44:15.005Z · LW · GW

One book that takes a very mechanical approach to story plot is Dramatica Theory (free, online, see link below). If I were to try to write a program to write fiction, I'd start with this and see what I could automate.

cultureulterior is talking about plots to overthrow governments.

Comment by summerstay on The Strangest Thing An AI Could Tell You · 2012-02-06T16:43:29.995Z · LW · GW

No effect from practice? How would the necessary mental structures get built for the mapping from the desired sound to the finger motions for playing the violin? Are you saying this is all innate? What about language learning? Anyone can write like Shakespeare in any language without practice? Sorry, I couldn't believe it even if such an AI told me that.

Comment by summerstay on The problem with too many rational memes · 2012-02-06T16:32:16.410Z · LW · GW

This kind of attitude is common among my friends who are more technical, but it can really damage communications with most people. "You're an idiot" doesn't just communicate "you're wrong" it says that you lack the ability to think at all, so all of your conclusions, whether related to this subject at all, are worthless. A good friend might take that in the way you intend, but there's no reason anyone else should. What is being called a Dark Art is something that Hermione would use; something that shows that you care about the other person's feelings, that you want to avoid causing pain where you can. It's a kindness. Sure, most of us can handle rough sports like intellectual boxing when we know what we're getting into, but most people aren't expecting to be sparring in a conversation.

Comment by summerstay on Rationality quotes January 2012 · 2012-01-03T13:26:22.098Z · LW · GW

Summa Theologica is a good example of what happens when you have an excellent deductive system (Aquinas was great at syllogisms) and flawed axioms (a literal interpretation of the Bible).

Comment by summerstay on Babyeater's dilemma · 2011-11-18T12:41:40.929Z · LW · GW

Dolphins do in fact engage in infanticide, among other behaviors we would consider evil if done by a human. But no one suggests we should be policing them to keep this from happening.