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

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.

Saturday, April 09, 2005

Parkinson's, Alzheimer's and Mitochondrial DNA

I wrote a little journalistic article on some work I did last year regarding the biological roots of Parkinson's disease (which I believe has implications for Alzheimer's as well).

The article is here. Read it. For those of you inclined toward sensationalism, there's even a part about a bad batch of heroin.

This work was done in collaboration with Drs. Davis Parker and Rafal Smigrodzki of the U. of Virginia, plus a bunch of my Biomind colleagues. I think it's rather nice stuff.

I don't find this sort of thing as rewarding as AGI work (and in a big-picture sense, I really do think that me spending so much time on stuff besides AGI is a big waste of the human race's resources ;-p), but even so, it's REALLY nice to be able to use narrow-AI technology for a really good purpose -- helping biologists to figure out the many ways in which the human organism degenerates and dies ... and how, hopefully, to repair these problems....

I do think that, via systematic biological research, we humans can beat aging and make our pathetic human bodies live effectively forever. Maybe we can even do it before ancient, 38-year-old Ben dies. I'm strongly in favor of increasing public funding for life extension research by a factor of 20, including full funding for Aubrey de Grey's fascinating proposals.

I don't think we need AGI to beat aging -- but I do think AGI, if we can create it, will be able to vastly accelerate the pace of research in all areas of biology, including life extension. This was my main idea in founding Biomind, although Biomind's work to date has been limited to some fairly small corners of biology (due to funding limitations, and due to the naturally slow pace of most rigorous scientific research). Even in these little corners we've managed to do some good, as this Parkinson's work illustrates. (Though in fact the Parkinson's work was a bit of a deviation from Biomind's primary research and product development, which has been in the area of microarray data analysis.) And we're poised to expand the scope of Biomind's work later this year with the release of a new product, yadda yadda yadda....

Focus, Garry Kasparov, Isaac Newton, AGI, Business Management, Episodic Memory, Buddhists Who Don’t Spill Tea in Hats, etc.... and, oh yeah, Focus....

Well, this is an odd blog entry to post, because I wrote it (except this new introductory babbling) a couple days ago and it doesn't really reflect my mood or thoughts at this moment very well. Right now I'm in a quite perky mood, just about to go outside and play some tennis on a sunny Saturday, and then come back in afterwards and launch into the final revisions on "The Path to Posthumanity" (a book on the future that I wrote a couple years ago, and now need to finish in a hurry since the publisher decided to light a fire under my butt by listing the book on and getting some sales of the as-yet not-quite-existent book...). Hopefully I can finish these revisions in the next week or so (in spare time, since most of my time is spent on software-biz stuff these days) and then plunge into the almost-done Novamente book that I really wish I were able to find more time for...

But anyway, here is the long blog entry that I wrote at the start of a business trip a few days ago, but didn't find time to post until now. A lot of rambling nonsense I'm afraid, but also some interesting nuggets here and there.

By the way, a couple people have emailed me to ask about Captain Zebulon's famous turtle tank. I not only changed it but I replaced the filter with a new, much better Penguin-brand filter that seems much more effective at filtering out the massive amounts of crap that water-turtles produce as compared to fish (thus hopefully reducing the need for frequent manual tank-cleaning). However, the new filter makes quite a loud noise -- you can hear it in the background of my son's latest musical recordings, of his soon-to-be-classic tune "The King of the Jews is Singing the Blues." (Unfortunately, his recording only exists within a videogame he's creating using RPGMaker 2003, so I can't post it here. Trust me, though, it's good. If I could sing as well as Zeb, I'd give up AI and become the next Michael Jackson. Er ... well ... something like that....)

OK OK, here is the biz-trip-blog...

I’m writing these words on my laptop at Gate B44 in the Washington Dulles airport – I missed my 6:10 AM flight due to stupidly forgetting to reset my alarm clock back to Standard Time from Daylight Savings time (so it woke me up at 5AM rather than 4AM). Rescheduled for a 7:40AM flight, I’ve got a bit of extra time in the airport -- so I took 15 minutes and speed-read a business/management book in the airport bookstore. (It’s not a vacation flight, unfortunately – I had a great vacation w/ the wife and kids last week, swimming and snorkeling and canoeing in South Florida, but this is a one-day business trip to California, to meet with some folks potentially interested in funding Biomind … (my bioinformatics business – which, after a few years of work, might eventually yield me enough profit that I can pay myself and a small team enough money to build the fabled Thinking Machine whose design lays mostly-neglected on my desktop….)). Not my usual fare, though I’ve probably read a few dozen business/management books in my life, but this one was moderately interesting. (As always with such books, the core information could be summarized in about 5 pages, but there are lots of evocative anecdotes. This ties in with something I’ve often thought about in the context of the Novamente design: human episodic memory seems to be at least partially organized by “story.” The human brain seems to store episodes different from procedures or declarative knowledge, and it seems to store them in units defined by some sort of conceptual coherence. In Novamente a “story” corresponds to a particular kind of “map,” meaning a set of nodes and links that are joined by HebbianLinks mutually reinforcing each other; a story differs from a generic map in that the nodes and links within it pertain to a set of events unfolding over time.)

But anyway … I digress (which is the main amusing thing about blogging – unlike in the “serious” writing I do, I allow myself to ramble and digress almost unlimitedly. I used to do that in writing fiction, but in the novel I’m writing now I’m orchestrating the digressions in a more careful way, which results in a better product but a less relaxed writing process. True, Jack Kerouac and Philip K. Dick wrote a lot of great stuff via pure “downhill skiing”, and Kerouac allowed a lot of digression in his writing-skiing process, but I don’t seem able to control my writing-skiing as well as those guys in real-time – my real-time verbal-conceptual improvisation is too wide-ranging and whacky, and it needs rational-critical post-processing to be made into something really artistic … unless the (err…) “artistic” nature sought is that of a blog entry, in which case this kind of digression is OK….)

The business book. The theme was one I’ve been thinking about a lot lately: focus. The exact opposite of this blog entry, in other words. Focus.

The basic idea of the book was: To succeed at X, find the one thing essential to X, and focus obsessively on X, to the exclusion of all else. The key to success is not balance, but strategically and tactically appropriate imbalance.


I try really hard to focus. I really do. But there are just so many interesting things in the world. There are dozens of novels well-worked-out in my head, hundreds of musical compositions, hundreds sketches of theorems (70% or so of which are probably correct), three substantially different AGI designs (Novamente, plus one based on Hebbian neural nets, plus one based on automated theorem-proving), even a few movie scripts… Not to mention that outline-for-a-unified-physics-theory…. Egads!

I could get myself to focus 90% of my time on creating an AGI, and push philosophy, music and fiction-writing (the other intellectual/creative pursuits that are necessary for my existence) into the other 10%. But I don’t seem to be able to get myself to focus quite that fully on bioinformatics, or natural language software, or any other business opportunity with the potential to yield the money needed to fund the implementation of my AGI design. I’ve been giving Biomind maybe 60-70% of my focus lately (which is a lot, because I work an awful lot of hours each week compared to what most people consider “full time” – I don’t sleep a lot) – because it needs it -- and pushing AGI into the background, which is extremely painful to me emotionally and intellectually.

(I have no issues with focus in the micro-scale: when I work I work with total mental concentration no matter how much noise and chaos are going on around me and no matter what mood I’m in or how tired I am, etc. (Except when Zadi’s watching South Park on the TV next to my desk, as that tends to be funny enough to distract me…. The episode I just watched almost convinced me that I should give up bioinformatics and fund Novamente via recording a Christian Rock CD…. If Cartman did it, so can I! I like his algorithm: just take a love song from the radio and replace all occurrences of the words “you”, “baby”, “darling” etc. with the words “Jesus” or “Lord.” Try it yourself, it works surprisingly well.) The level of focus that worries me is, rather, the choice of which things to direct my highly-focused micro-attention to. Which is mainly a problem because what I really want to focus on isn’t what the world currently wishes to pay me to focus on, and due to having a family to support I have this irritating ongoing need for money…. Leading to difficult temporal-assignment-of-credit problems, such as how much time to spend actively working toward AGI, versus working on things-I-like-but-don’t-love (bioinformatics, at the moment) that may yield money to pay for AGI research in a couple years, versus things that put me in a peaceful and creative state of mind (music! weird fiction!) so that my work on things-I-don’t-love is more effective, etc….)

If it’s true that sustained narrow-focus is the prerequisite of success, this would certainly explain why the most successful people aren’t generally the most interesting ones. Balance and breadth tend to make people interesting to interact with on a sustained basis. People narrowly obsessed with one thing tend to get tiring quickly – though they can be exciting and fascinating to talk to for brief periods of time. My close friends tend to be broad and balanced people, yet the people I admire most often have more of a narrow-focusing nature.

Now I’m sitting on the airplane – had to stop typing for a few minutes to board the plane, and then wait until the plane was aloft to bring out the laptop, because of the peculiar urban legend (embraced by the FAA) that laptops interfere with airplanes’ navigation equipment. While the plane was taking off I decided to continue the theme of my morning’s reading, and I read a couple articles in a free onboard copy of “Harvard Business Review.” (Also a delightful article on hats in “Ebony,” but I’ll spare you the details of that one….”Make no mistake, it takes a certain amount of bravado to wear a hat. .... It’s like the exclamation point to a fashion statement. … Hats hint at the essence of the wearer, giving a peek into the soul of the Brother underneath….” Ah, humanity! Gotta love it!) The current issue of HBR contains an interview with Garry Kasparov, the recently-retired world chess champion, on the relationship between chess and business.

Amusingly, Kasparov had something to say about focus, in the context of his chess battle with computer program Deep Blue in 1996-1997. He reckoned the contest had been an unfair one, since Deep Blue was trained on transcripts of his prior chess games, whereas all transcripts of Deep Blue’s play were kept secret from him. He also said he thought Deep Blue couldn’t beat him on his best day. But he said he thought one of the big advantages computers had over human chess players was their ability to focus exclusively and narrowly. “Human players have to cope with a lot of external pressures and distractions: you have a family, you write books, you give lectures, you get headaches, you have to earn money. There’s a lot of stuff filling up your brain while you’re playing. A machine, on the other hand, is completely without distractions. This shows the weakness, the shortcomings of the mortal mind, which is a daunting lesson for human beings. We just can’t play with the same consistency as a computer. So it’s all the more fortunate that we have our intuitions to help us play better.”

Kasparov obviously spent most of his life narrow-focusing on chess. Yet, he remains a bit jealous of a computer program’s ability to narrow-focus even more intensively.

And it’s interesting to observe that, for a chess master, Kasparov is an unusually breadth-oriented guy. His style is that of a strategic risk-taker, as opposed to that of his arch-enemy Karpov, who was always more conservative and analytical. Kasparov likes to think about business, literature, politics, and human nature in general – as he says, “I do not like details.” Of course, to become world chess champion he must have learned an awful lot of details – but what made him a master was not merely his mastery of details; it was his mastery of details combined with a truly rare and powerful intuition.

Kasparov’s style of chess could only be conducted by a mind with some breadth as well as narrow-focus, because it relies on general principles and intuitions regarding strategy – principles and intuitions going beyond chess and applicable to other domains as well. On the other hand Karpov’s style of chess was more suited to a purely narrow-focused approach.

AGI, I suspect, is really only susceptible to a Kasparov-style approach -- or really, to an approach that’s even more breadth-centric than Kasparov’s. This may be one of the reasons why AGI is so hard. If achieving anything substantial requires narrow-focus, then how is it possible for anyone to achieve something that by its nature can only be comprehended and mastered by someone with tremendous breadth? Tres dificil, nyet?

Physical sciences and mathematics don’t generally have this property – a very hard problem like creating a relativistic theory of gravity (solved by Einstein a long way back) or unifying gravitational and quantum physics (not solved yet) is nevertheless defined within a fairly delimited formal domain, and can plausibly be solved by a mind narrowly focused on that domain. To do what Newton did, on the other hand, clearly required breadth combined with focus. He had to focus to solve the hard technical problems, but he also had to have a lot of breadth to figure out what were the right questions to address, drawing from the incoherent mess of concepts and ideas that was pre-Newtonian physics. The analogy isn’t perfect nor original but I guess it’s an OK one: the task of creating AGI seems roughly comparable in magnitude to the task of creating Newtonian physics. Both have a conceptual and a technical aspect, though in Newton’s case the technical aspect was mainly mathematical, whereas in the AGI case it involves software design and engineering as much as mathematics.

Newton made his biggest breakthroughs during a three-year period when he was largely isolated in his house, at a time when England was mostly shut down due to the bubonic plague. (And, according to my university philosophy professor, his dog was named “Diamond.”) Maybe that’s what I need right now – a dog named Diamond, and an outbreak of plague to hit Washington, forcing me to sit in my house isolated for three years and do nothing but work on AGI by myself. Of course, the plague would have to hit the Internet too – isolation is harder to come by these days. Nah, that’s just a silly thought – software engineering, unlike mathematics, is better done by a small “extreme programming” style team than by a single individual. Plus, I don’t quite trust myself to teach a baby AI alone; the baby needs a woman as well as a man as a teacher (Izabela, with some help from Zadi?) and it needs a strong dose of Cassio’s conservatism and good judgment. What I need is for the plague to strike when I’m stuck in a house with the 4 or 5 best members of the Novamente team. And preferably it’s a big house, so there’s room for my kids and dogs with their noise and chaos in a separate soundproofed wing! (Yeah, yeah, this is just a stupid joky digression, please don’t quote me as if I seriously want a plague to come down on the world, I don’t…. (I started thinking that, since I happen to live in the Washington DC area, a plague in my local region might end up having some positive effects due to eliminating a lot of politicians. But, the body politic seems to have a self-regenerating characteristic similar to the limbs of certain lizards. And of course, a plague here in DC would probably be mistaken for a terrorist attack, which might cause Dubya to annihilate the continent of Africa by mistake or something … OK OK, enough!)

Wow, this is a long blog entry! I’d better call it to an end now. I’d intended to spend this flight finalizing the manuscript of “The Path to Posthumanity” – which, I recently noticed, the publisher has listed on, even though I have not yet actually sent him the text of book! Well, some things move fast these days. Unfortunately I’m not going to be able to make that book nearly as good as I’d like, due to lack of time rather than lack of ability. I need to get that one out of the way so I can get back to finishing “Foundations of Emergent Cognition” (the shiny new name for the “Novamente book”), which is pretty much done, but just needs a final going-over, addition of references, clarification of which aspects of the discussion pertain to Novamente in particular versus pertaining to “any sensible AGI design,” etc. etc. Still, maybe “Path” will get some sales riding on the coattails of Kurzweil’s “Singularity.” The books cover much of the same ground, but mine gives fewer exponential and hyperexponential charts and more scientific depth – and mine also gives a more transcensionist, less “kinder, gentler” view of the Singularity. (Kurzweil is brilliantly insightful, yet he often seems to downplay the dramatic nature of the Singularity even as he trumpets its inevitability. Sometimes it seems like he foresees a Singularity full of modified or uploaded humans with shiny new gadgets – rather than a fundamental overthrow of the current order of mental, physical and social being. Of course, we may well get BOTH of these, but it seems a bit disingenuous to focus primarily on the former, even though it’s easier to understand and goes down better on Main Street. But of course, these comments are based on not having seen his book, which hasn’t been released yet – they’re based on his prior books and his speeches and online writings – maybe his book will give fair time to the transcensionist aspects as well, we’ll see.)

Enough – enough rambling, Ben – enough. Focus! Focus! Focus! Finish “Path to Posthumanity” and send it to the damn publisher! Write those Biomind press releases! Test the new Biomind ArrayGenius release! Finish the Novamente book! Launch the damn Singularity already so you can give yourself a better temporal-assignment-of-credit algorithm, eat 7 cakes without gaining weight, and push your daughter on the swing and canoe past crocodiles while composing weird jazz fission and programming meta-Haskell and kiss your wife while proving theorems that are themselves hyperdimensional conscious beings… yadda yadda… Focus! Focus! Focus!

Ah – wait – one more afterthought about focus. I had a Buddhist friend once who, every time I made a mechanical mishap like spilling a cup of tea, would point out to me: “See, if you were an enlightened Buddhist master, you’d never do anything like that. You’d never spill your tea because you’d be totally focused on whatever you were doing, in that moment!” In fact, this guy was neither particularly enlightened nor particularly focused nor emotionally balanced himself, though he was highly adept at pointing out the unenlightenment of others -- but he did have a point there. But of course, my retort was always “Fine, but I don’t WANT to focus my total attention on something boring like holding a cup. I’ll accept a certain error rate with boring things in order to focus most of my attention on interesting things. It’s no wonder no Buddhist master has ever achieved anything fascinating in science or mathematics – these things require focus in themselves, which is hard to obtain if one is focusing all one’s attention on drinking tea or raking leaves or breathing!” I think the analogy between Buddhist mindfulness and narrow-focus-for-business-success is not totally spurious. (Yeah, this brief paragraph doesn’t come near doing justice to my thoughts on Buddhism, but that’ll be saved for a later blog, it’s a deep and complicated issue in spite of its perfect simplicity, yadda yadda.) One problem is that the human mind is so painfully limited that it’s hard for it to do even one thing well, and when it divides its attention, it’s bound to make mistakes. Another problem is that we were probably evolved to focus on one intensive task at a time – like hunting, or escaping, or mating – and the modern emphasis on multitasking (on various time-scales) is an abuse of our evolutionary neural and physiological wiring.

Enough, OK, OK. Focus! Focus! Focus!

(I spent the flight from Salt Lake to San Fran sitting next to a very intelligent mining engineering executive who spoke very passionately about nutraceuticals and was bringing in a couple hundred thou a year selling them, via a variant of the classic “multilevel marketing” scheme. The nutraceutical line he was hawking actually seemed decent – founded on reasonable science – and I was almost convinced to give up the idea of making money for AGI through narrow-AI businesses and make the money through selling skin lotions and nutritional supplements instead. It might be a lot easier. I almost followed that plan when I was 13 and now I’m sorta wishing I had. OK, not really. But it’s an amusing thought…. I’m not such a bad salesman if I’m selling something I believe in; if I were selling e.g. life extension oriented supplements with some foundation in biology, I could probably give a convincing rap. My wife knows a lot of vain women in Brazil; maybe we could start the business in Brazil…. I’ve often thought that mixing up making money with AI is a mistake – it might be better just to keep my AI work pure and just accept that I need to spend a percentage of my time on some stupid business in order to pay the bills and hopefully eventually make enough money to pay the Novamente team to actually work on AGI engineering and teaching….. But, yah yah, the problem is that making any business work takes a lot of focus and attention, and it’s hard for me to see myself getting motivated to direct much of my focus and attention to something so boring as selling skin lotions…. The marketing ploy is slighty clever though: they suck women in my selling them skin lotion, and then upsell them to more expensive nutraceuticals, pointing out (correctly) that the key to beautiful skin is good health. Well, this sort of shit is what most humans seem to be interested, right? Beautiful skin, big muscles, good hair, shiny teeth and symmetrical faces. If you can’t have them yourself at least you can watch them on TV! (OK, OK, I’m not really going to quit the AI business to sell skin lotion. Although I’m not sure it would be a stupid idea in the medium term; in the short term I don’t have the stomach for it…. And anyway Biomind’s business prospects are actually looking pretty good right now (sales pitch ahead: anyone want to buy some of the world’s best microarray data analysis software?)