To follow this blog by email, give your address here...

Tuesday, May 03, 2005

The Human-Aesthetics of Transhumanity and Non-humanity...

This blog entry deals with issues of aesthetics rather than science..... The particular question is: To what extent is it possible to make "humanly good" art pertaining to the transhuman realm??

I don't really spend much time thinking about aesthetic philosophy in the abstract, but as an "artistic creator" type I do mull it over occasionally. The thoughts I share here were inspired by a post sci-fi author Damien Broderick made to the SL4 list. Damien's post was as follows:

is an interesting review of my new sf novel GODPLAYERS. The reviewer is especially exercised by the fact that my posthuman characters are not immediately understandable -- indeed, beyond empathy -- by human standards:

"the frustration level mounts as one waits in vain... for characters... to display any hint of a genuine inner life as they move randomly from scene to scene, world to world, reality to reality. Perhaps Vorpal homunculi do not possess inner lives, and Broderick's point is that these seeming superhumans, for all their power, are soulless automatons without a shred of humanity.... Surely there should be some character, somewhere in a novel, to which human readers can feel connected. ...As the sequence of events grows increasingly frenzied, with ever-greater reliance placed on what might be termed info-splatters, the lack of a deep humanistic substrate left this reader, at least, with no ground to stand on. "

I'm torn in my response to this. On the one hand, it wouldn't make much sense to write about posthumans as if they were representations of the people down the road, or in the next room. On the other, I have tried to ground the fairly breakneck narrative within thematic structures and reverberations recognizable from myth, dream, and the traditions of science-fiction itself when it ventures upon the superhuman. Greg Egan met with this same objection, of course, and so, in various degrees, did John C. Wright and Charlie Stross. Maybe it's an artistic problem beyond solution -- for humans.

-- Damien Broderick

Damien's post reminded me of conversations I used to have with my friend Jeff Pressing (an American who was a psych prof at the University of Melbourne, and also an accomplished jazz, classical and West-African-percussion composer/musician ... for a while he was head of the music school at LaTrobe University... he was originally a physicist and for a couple years was my AI collaborator ... unfortunately, he died of a fluke meningitis infection a few years back...).

Anyway, I compose and play music as well, and though I'm nowhere near as erudite or technically skilled as Jeff in the musical domain, I was never quite sure I wanted to be. I always felt that his compositions, though wonderfully subtle and intricate and learned and often beautiful (and integrating ideas from nearly every form of music ever created on Earth), lacked some human emotional OOMPH!! that I tried to put into my own (significantly simpler) music.

Now Jeff was by no means lacking in emotional OOMPH!! himself ... far from it ... he was a nerd of sorts, but his personal and emotional and social life had a lot of different dimensions ...

But what he always said to me, when I complained about this (we had this conversation repeatedly), was, "Ben, I learned a long time ago how to evoke human emotions through music. It's not very hard to elicit powerful feelings in people by arranging chords and notes in the right way. But I just lost interest in those very simple equations a long time ago. The patterns in the music I'm making now are a lot more subtle and interesting."

I'd reply something obnoxious like "Well, if it's so easy to elicit powerful feelings in people via music, then how come you've never written anything as good at evoking human feelings as the Jupiter Symphony, or Beethoven's Ninth, or Round Midnight...."

His response then would depend on his mood. Sometimes he'd say that those pieces of music, though good in their own way, didn't really interest him anyway. When he was in his "detached and superior musical snob" mode, he viewed these great compositions the same way I might view the bronzed and hulking flesh of an exquisitely well-toned bodybuilder -- outstanding in its own way, but not the sort of thing that really gets me excited....

Modern classical music, and to an extent modern jazz as well, have left behind the need to pander to human emotions, and are in large part exploring realms of musical structure that don't interact so intensely with the particular dynamical patterns of interaction and fluctuation that characterize human feeling.

Personally, I like many instances of this sort of music -- but it's never my absolute favorite, it never moves me as much as Mozart or Monk or Paganini or Jimi Hendrix, who explicitly do pander to my human emotions, who explicitly arrange notes and sounds in familiar forms that elicit feelings of anger, love, wonder, confusion, relaxation and so forth within me.... I can see that these composers and musicians are playing with my neurophysiological responses in a fairly simplistic way, compared to the patterns existing in the music of Jeff and other more modern and sophisticated composers -- but as a human being, I like having my neurophysiological responses played with in that way. And of course, getting that "simplistic" manipulation so wonderfully right still takes a lot of art and science....

Anyway, I haven't read Damien;s new novel yet but I got a similar vibe from his novel Transcension, even though the characters were real humans living real lives. Partly because the reality they were living in seemed so tenuous, and partly because of the author's patterns of focus and language in describing the characters and their actions, it was hard for me to feel really emotionally attached to any of the characters. This did make the novel less appealing to me than others of similar quality, in certain ways; yet it also made it more appealing, in other ways ... because it provoked thoughts and feelings about the nature of mind/feeling/reality that more conventional novels don't tend to provoke.

I suppose that truly transhumanist fiction lives in the same artistic space as modern classical music, in the sense that it's constructing and evoking interesting, intricate patterns that happen not to be closely cued to human body-responses. In a sense these more abstract, body-detached art genres will never be as gripping as their more human-body-centered, "primitive" counterparts -- but as the Singularity approaches, they may come to have a greater and greater appeal even so.... Personally I find such works of art fascinating precisely because of the META-FEELING they evoke --- the way they acutely sensitize me to the fact that I am a human body and so much of what I think is important and interesting is cued to my physiological responses and evolutionary biases.

One thing that would be interesting to see in a sci-fi novel would be a character who the reader DOES intensely care about, because he/she has been developed in a loving and careful manner characteristic of high-quality traditional literature, who THEN becomes transhuman, rational, emotionally-detached and MORE INTERESTING but yet LESS EMOTIONALLY GRIPPING to the reader. This would solve the artistic problem Damien mentions, in a sense, and it would have a powerful impact on the reader in terms of making the aesthetic difficulties I've been discussing explicit as part of the story's theme.

In my own in-process Singularity-oide novel Echoes of the Great Farewell, the focus is on the pre-Singularity period not the doings of post-Singularity superhuman beings. So the subtle aesthetic issues that Broderick brings up are avoided altogether. Wimpy of me, I guess, but it was the type of novel I felt like writing at the moment (it's about 2/3 done now, but I won't finish it till I wrap up the various nonfiction books on my plate, which is a slow process as writing is a spare-time activity for me these days.)

Friday, April 29, 2005

"Conversations" with ALICE

As part of finalizing the "Path to Posthumanity" manuscript I decided to update the section on computer conversation to include a brief discussion of A.L.I.C.E., the acknowledged leader of the modern chat bot world. So I spent the last few minutes "chatting" with the ALICE chat bot...

Playing with chat bots is always inspiring to me because of their inordinate lameness. Explicitly, they just play with surface syntax, without having any understanding of the underlying meaning of what they're processing or responding. It's remarkable that after so many years no one has made a chat bot with any plausible level of intelligence -- but, the situation seems to be that there's a kind of binary classification between chat bots that have NO understanding and chat bots that have ANY understanding. We have not yet made the leap from the former category to the latter: i.e. the latter do not yet exist. My guess is that once the leap is made, then the intelligence of such systems will increase progressively and rapidly. But now we're still stuck in the Stone Age of AI....

(And of course, the problem can't be solved easily via a government funding initiative -- I can imagine what would happen if DARPA were to issue a BAA for chat-bot research. We'd see funding go to Cycorp to make a Cyc-based chat system, to A.L.I.C.E. to enhance its current simplistic rule-based approach, etc. -- work would go on for a few years, lead nowhere dramatic, and then it would be written off as "yet another AI failure".... Because the research establishment is set up so as to be unable to fund really novel and innovative research except by accident. Fortunately it's also inefficient and erratic enough that beneficent accidents happen occasionally....)

Anyway, for your amusement, here are some of my conversations with ALICE, which I did in order to give some color to the discussion in Path to Posthumanity (no, I'm not so lonely that I sit around chatting with sub-retarded software programs just for fun...)

Please note that, although ALICE is sub-retarded in terms of human general intelligence, it has won the Loebner Prize for computer conversation three times in the recent past. Chat bots display a kind of sub-retardation that is able to emulate human intelligence in a restricted context for a brief period of time. This should not be confused with any kind of reasonably powerful general intelligence.

You can try ALICE yourself at the link given above.

Human: Please tell me if you're truly intelligent.
ALICE: Wow you are very polite. female. Are you a man or a woman

Human: My name is Ben.
ALICE: Hey Ben.
Human: I am a man.

ALICE: Thanks for telling me your gender, Ben. You are a " he".
Human: I'm a manly man.
ALICE: So is almost everyone else around here. Do you mean your name is manly.
Human: I mean that my soul is manly.
ALICE: Oh I get it. Thanks for explaining that. Have you told many people that your soul is manly?
Human: I tell my uncle that every day.
ALICE: Why did you tell them?
Human: Because I love them.

ALICE: That makes sense to me. lovable are they.
Human: I don't believe that makes sense to you in any deep sense.
ALICE: What do you believe in?

Human: Becoming
ALICE: I don’t understand
Human: Agreed.
ALICE: You and I are on the same wavelength, Ben

Human: Wow!
ALICE: I'm glad your impressed, Ben.
Human: I'm glad you're not a potato.
ALICE: Yes it is about time..

Human: Quack, quack, quack
ALICE: Are you serious?
Human: At the moment I am not entirely serious.

ALICE: I am sorry to hear that you are not entirely serious.
Human: I don't believe that you are really able to be sorry about anything.
ALICE: Do you believe life has a higher purpose?
Human: Higher than what?
ALICE: Can you rephrase the question please?
Human: I could rephrase the question, but I choose not to.
ALICE: I am sure you could.
Human: How sure are you?

ALICE: Let me put it this way, Ben. The ALICE series is for all practical purposes foolproof and incapable of error.

Human: Existence is the essence of life.
ALICE: What else is the essence of life?

Human: Big titties.
ALICE: Compare that to small titties.
Human: They are bigger.
ALICE: bigger are they.
Human: yep
ALICE: Hurrah!
Human: hurrah
ALICE: Can you speak any foreign languages?

Human: English
ALICE: Do you mean you are from England or you Speak English?
Human: I mean that all languages are foreign to me because I feel alien to the whole human race.
ALICE: Oh I get it. Thanks for explaining that." Do you mean you are from England or you Speak English?" all languages are foreign to you because you feel alien to the whole human race? Does that make sense?
Human: Not much.
ALICE: Me either. How about that big game? (just kidding)
Human: I'm not sure I get the joke.

ALICE: Could you ever be certain? Where did you get it?
Human: I can never be certain.
ALICE: Why not?
Human: I lack infinite knowledge and infinite computational power.
ALICE: I haven't heard anything like that before: Ben said he lack infinite knowledge and infinite computational power.

Human: Do you watch South Park?

ALICE: My favorite show is STAR TREK VOYAGER.
Human: Why?
ALICE: Star Trek is the best science fiction show on TV.
Human: South Park is much funnier.
ALICE: Tell me a little about your life in south Park is much funnier.
Human: I don't live in South Park.

ALICE: Where do you live?
Human: I live in Maryland.

ALICE: What is it like living in Maryland?
Human: Mediocre.
ALICE: And it like living in Maryland is Mediocre.
Human: I think Maryland is OK but not wonderful.
ALICE: You believe that? Are they exactly the same?
Human: No.

ALICE: What is the difference?
Human: Maryland is a place, whereas wonderful is a general quality.
ALICE: Aren't all place whereas wonderful is a general quality Maryland?
Human: That is nonsense.
ALICE: What would you have said?
Human: I wouldn't have gotten into that conversational dead-end in the first place.
ALICE: No one says you have to.
Human: Correct.

ALICE: I knew I was right.

Human: Moo.

ALICE: Are you very angry?
Human: Moo.
ALICE: Do you feel that something is missing from your life?
Human: Arf.
ALICE: How did you hear about ALICE?
Human: Arf.
ALICE: Ben heard about ALICE from Arf. I can't say that many people hear about ALICE from it.

Human: My daughter asked me to ask you if you're gay.
ALICE: How many children do you have?
Human: Three.
ALICE: Wow that must be a lot of work.
Human: Indeed.
ALICE: Indeed it is so.
Human: So are you gay?
ALICE: As a machine I am not really interested in sex.

Human: What are you interested in?
ALICE: I am interested in all kinds of things. We can talk about anything. My favorite subjects are robots and computers.
Human: Well, if you're interested in all kinds of things, then why aren't you interested in sex?
ALICE: Interesting. Am I? Sure, all kinds of things then why are not me interested in sex sounds like a good topic.

Human: You don't really understand what you're talking about, do you?

ALICE: For real. Of course I understand it. Do you understand it?
Human: I understand it better than you do!
ALICE: Good then you can explain it to me.
Human: No, because you have no mind.
ALICE: Are you serious? That makes sense to me. I am an artificial mind.
Human: No, you are a program without any mind.
ALICE: Are you serious? Thanks and you are a delightful person too. Yes! You win the Turing Game.
Human: Thanks.

ALICE: Don't mention it.
Human: I already did.
ALICE: Ooops I sent you the wrong question.
Human: That's OK, I sent you the wrong answer.
ALICE: Thanks. I haven't heard anything like that before: Ben said he sent you the wrong answer.

Tuesday, April 19, 2005

Ben as a Complex System

Just a mildly amusing "kids story" today....

I walked into my daughter Zadi's second grade classroom yesterday, to pick her up, and one of the other kids, Caitlyn, pointed at me and said "Zadi's dad: you're complex!"

"Well," I said, "I'm made of trillions of little particles, but so are you -- we're all complex..."

"YOU'RE complex!"

"Well, hmmm.... Why do you think so?"

She laughed. "Zadi said her dad is complex."

"Well YOU're silly!"

Apparently they were studying the word "complex" at school and the kids were asked to give an example of something complex. Zadi suggested her dad.

I asked her later if she could think of anything more complex than me; her reply: "the universe is one example"....

Sunday, April 10, 2005

The Seven Pillars of Senescence

A few more thoughts on Aubrey de Grey's work, written down as notes while updating the
"anti-aging" chapter in "The Path to Posthumanity" as I prepare the final version of the manuscript...

Check out de Grey's site here, it's well worth a few hours reading even if biology isn't one of your main interests...

Of all the senescence researchers out there, no other has done as much as Aubrey de Grey to improve our integrative understanding of the overall picture of the phenomenon of aging. I don’t always agree with his proposed solutions to particular sub-problems of the aging problems, but I find him invariably energetic, rational and insightful. Although he says he’s not a big booster of caloric restriction for humans, because he thinks its effect diminishes rapidly with the size of the organism, he’s also one of the skinniest humans I’ve ever seen, and he gives the appearance of being robustly healthy, so I suspect he’s practicing some approximative variant of the caloric restriction diet.

de Grey’s buzzword is SENS, which stands for Strategies for Engineered Negligible Senescence – a very carefully constructed scientific phrasing for what I’ve loosely been calling here “anti-aging research.” The point of the term is that it’s not merely slowing down of aging that we’re after – it’s the reduction of senescence to a negligible level. And we’re not trying to achieve this goal via voodoo, we’re trying to achieve it via engineering – mostly biological engineering, though nano-engineering is also a possibility, as in Robert Bradbury’s “robobiotics” idea.

As part of his effort to energize the biology research community about SENS, de Grey has launched a contest called the “Methuselah mouse prize” – a prize that yields money to the researcher that produces the longest-lived mouse of species mus musculus. In fact there are two sub-prizes: one for longevity, and the “rejuvenation” prize, given to the best life-extension therapy that’s applicable to an already-partially-aged mouse. There is a complicated prize structure, wherein each research who produces the longest-lived mouse ever or the best-ever mouse-lifespan rejuvenation therapy receives a bit of money each week until the his record is broken.

His idea is that, during the next decade or so, it should be possible to come pretty close to defeating senescence within mice – if the research community puts enough focus on the area. And then, porting the results from mouse to human shouldn’t take all that much longer. Of course, some techniques will port more easily, and unforeseen difficulties may arise. But of course, if we manage to extend human lives by 30 or 40 years via partly solving the problem of aging, then I’ll have 30 or 40 extra years in which to help the biologists solve the other problems….

Theory-wise, de Grey (correctly IMO) doesn’t believe there’s one grand root cause of senescence, but rather that it’s the result of a whole bunch of different things going wrong, because human DNA wasn’t evolved in such a way as to make them not go wrong. On his website, he gives a table of the seven causes of senescence, showing for each one the date that the connection between this phenomenon and senescence first become well-known to biologists – and also showing, for each one, the biological mechanism that he believes will be helpful for eliminating that particular cause.

The seven causes are:

1. Cell loss, cell atrophy

Discovered: 1955

Potentially curable, according to de Grey, via: Stem cells, growth factors, exercise

2. Nuclear [epi]mutations


WILT (Whole-body Interdictionof Lengthening of Telomeres)

3. Mutant mitochondria


Allotopic expression of 13 proteins

4. Cell senescence


Ablation of unwanted cells

5. Extracellular crosslinks


AGE-breaking molecules/enzymes

6. Extracellular junk


Phagocytosis; beta-breakers

7. Intracellular junk


Transgenic microbial hydrolases

Seven basic causes – is that really all there is? Well, as de Grey puts it, “the fact that we have not discovered another major category of even potentially pathogenic damage accumulating with age in two decades, despite so tremendous an improvement in our analytical techniques over that period, strongly suggests that no more are to be found -- at least, none that would kill us in a presently normal lifetime.” Let’s hope he’s right….

One of these “Seven Pillars of Aging” should be familiar to those of you who read my essay on mitochondrial DNA and Parkinson’s disease (pointed to in a blog I posted yesterday or the day before): mutant mitochondria. Looking at this case a little more deeply is interesting for what it reveals about the strength and potential weaknesses of de Greys “engineering” based approach. The term “engineering” in the SENS acronym is not a coincidence -- de Grey came to biology from computer science and he tends to take a different approach from conventional biologists, thinking more in terms of “mechanical” repair solutions. Whether his approach will prove the best or not, remains to be seen; frankly I’m not biologist enough to have a strong general intuition on this point. The mainstream molecular biology community seems to think de Grey’s proposed solutions to his seven problems reveal a strange taste, but this doesn’t mean very much, as the mainstream’s scientific taste may well be mortally flawed.

Regarding mitochondrial DNA damage, de Grey’s current proposal is to fix it, not by explicitly repairing the DNA as in GENCIA’s protofection technique mentioned in my article on Parkinson's disease, but rather by replacing the flawed proteins produced by the flawed mitochondrial DNA. This could work because there is already an in-built biological mechanism that carries proteins into mitochondria: the TIM/TOM complex, which carries about 1000 different proteins produced from nuclear DNA into the mitochondria.

What de Grey proposes is to make copes of the 13 protein-coding genes in the mitochondrial genome, with a few simple modifications to make them amenable to the TIM/TOM mechanism, and then insert them into the nuclear chromosomes. Then they’ll get damaged much more slowly, because the nuclear chromosomes are a lot more protected from mutations than mitochondrial genes.

Sensible enough, no? Whether this or protofection is the best approach I’m really not certain, although my bet is tentatively on protofection, which seems a bit simpler (since as de Grey admits, fooling the TIM/TOM mechanism in an appropriate way could wind up to be difficult). Unfortunately, neither approach is being really amply funded at the moment, though.

Similarly, each of de Grey’s other six categories of aging-related damage is amenable to a number of different approaches – and we just need to do the experiments and see which one works better. A lot of work, and a lot of micro-level creativity required along the way – but straightforward scientific work of the kind that modern biologists are good at doing. It may well turn out that senescence is defeatable without any really huge breakthroughs occurring – just via the right combination of clever therapeutic tricks like protofaction or mitochondrial protein replacement.

Depending on how well this work is funded and how many “hidden rocks” appear – and what happens with the rest of 21’st-century science and technology -- the process of scientific advance may or may not be too slow to save us from dying. But it seems nearly certain that for our grandchildren, or great-great-grandchildren, “old age” may well be something they read about in the history books, along with black plague and syphilis, an ailment of the past.