April 21, 2004

Engineering Space Warships

The eminent engineer blogger, Steven Den Beste, considers the "critical characteristics of space warships."

Posted by Stephen Gordon at 01:54 PM | Comments (2) | TrackBack

December 04, 2003

Riding the Spiral

Speaking of the Future with John Smart

Consider this basic shape:

I've always been fascinated by spirals. When I was a kid, I used to sit and draw them for hours at a time. This was long before I knew anything about Phi or the Fibonacci sequence, before I had ever heard of logarithmic spirals or fractals, before I ever came to work for a company with such an aesthetically pleasing logo. I've never lost interest in them. In fact, whether meaning to or not, I seem to fill my life with spirals.

My choice of employer was just the beginning.

Take a look at this ironwork that sits atop my bedroom mirror. It's pretty close to the shape in the line drawing above, although it stops short of being an actual spiral.

Here's my coffee mug. Now this shape is a spiral, but it's different from the one shown above. It's more "practical," a squashed spiral that will fit in a small space.

Here's some original artwork, the basis for the Speculist logo. These spirals are actually the same as the line drawing; it was the template I used to create my galaxy.

The truth is, whether I try to fill my life with it or not, that spiral is everywhere. This simple shape, along with the math that underpins it, is encoded into our universe. The sequence of numbers that produces it is simplicity itself:

1 1 2 3 5 8 13 21 34 55 89 144 233 377 610 987

(To get the next number, you simply add the previous two.)

And yet from that simplicity comes immense and wonderful complexity. A nautilus shell encodes that sequence to produce its spiral shape, as does a wave just before it breaks on the shore. And, as I've shown above, the trillions of stars making up a galaxy tend to follow the same sequence and produce the same lovely spiral. There are many, many other examples.

And it may not just be physical objects that follow this sequence. John Smart, Director of the Institute for Accelerating Change, has suggested that history, perhaps even time itself, may be driven by such a sequence. Following the sequence of events that make up history is, perhaps, not unlike following the arc of a galactic spiral arm as it sweeps its way into the center. Imagine such a trip: you start out moving slowly in nearly empty space, gaining momentum as the turns begin to come more quickly and the frequency of the stars increases; soon there are more stars and then more, and now you're spiraling in and in and in, to the incredibly hot, dense core—and then even further in, to a place that's beyond our ability to describe accurately, or really even to imagine.

In the interview that follows, John Smart takes us on just such a journey through time. The galaxy that we are travelling through is the history of the universe itself; the turns in the spiral are the major developmental epochs; the stars are the individual, evolutionary changes. Like a trip to the center of the galaxy, this journey takes us, quite literally, beyond the limits of the imagination.

You may be startled to realize (as I was) where exactly we are on that winding path to the brink of the unknowable.

Part I: Seven Questions About the Future

1. The present is the future relative to the past. What's the best thing about living here in the future?

Cato Institute authors Julian Simon and Stephen Moore noted in 2000, It's Getting Better All the Time. Not only that, but things are getting better by a greater absolute amount each year, with the exception of very few remaining parts of the developing world. And improving conditions in the developing world is something we also have more ability to do today than ever before.

This amazing state of affairs is due almost entirely to advances in science and technology, and the profoundly civilizing way that these subjects interact with the half-bald primates that have discovered them and who are now feverishly employing them at every level of human endeavor it on this precious little planet.

Looking at the same process from the informational side (sometimes called the metaphysical side), the powerful transformations we are witnessing are also due to what the transhumanist mystic Teilhard de Chardin (The Phenomenon of Man, 1955) called "psychical energy", the accelerating forces of conscious intelligence, loving interdependence, and resilient immunity, the holistic, informational yang to the reductionist, atomistic yin of sci-tech.

I think we are beginning to recognize the importance of both the "psychical"/informational and the physical/material in every complex system, what John Archibald Wheeler calls the increasingly aware "it" that emerges from all our quantum "bits."

2. Whatís the biggest disappointment?

The U.S. has been the world's technological leader since the invention of the "American System" of mass production and interchangeable parts in the 1910's. But we've fallen away from a clear leadership position in several areas of science and technology in recent decades, and I think the world is poorer for it.

Ask yourself: what is the single greatest goal currently unifying our national efforts in science and technology? I don't have a clear answer to that question, and I think there should always be one, or at least a very small handful.

Stopping terrorism one of today's admirable, timely, and necessary great goals. And there are certainly effective technological immune systems that we will develop around this goal in coming years. But this is a reactive, not a proactive program. We aren't presently rallying the country around a positive, non-zero sum developmental vision. Nanotechnology is a candidate, but as I will describe later, it cannot yet fire the public imagination the way more achievable, short-term goals can. Where's the leadership we need?

We've had some effective great goals in the past. John F. Kennedy's Space Program most readily comes to mind. The infrastructure projects of Franklin Roosevelt's New Deal were at least a partial success, if economically mixed. Even Lyndon Johnson's War on Poverty made some measurable progress.

Why is the Moon Shot the great goal we all most clearly identify? Scientific and technological goals, if chosen wisely, can have both dramatic consequences and clear deliverables, unlike many of our social, economic, and political objectives. At best, a great goal is both vitally important and demonstrably achievable. At worst, as with the Wars on Cancer, or Drugs, or Inner City Violence, the putative great goal diverts our energies and vision from more critical priorities. Alternatively, a vitally important goal may be too ambitious to achieve within one generation, like WMD Nonproliferation, which has been measurably improved by every president since Kennedy. Alternative energy development, greenhouse gas reduction, and a host of other goals fall into this latter category.

Worthy as they are, these types of goals deserve to remain on the second tier of the public consciousness. Only the most important, urgent, and achievable goals deserve to be named as our top priorities. I would also argue strongly that if we live in a time when we can't find those, then the country's direction drifts, noise exceeds signal, and political apathy becomes the norm.

So what is the great goal our country is currently ignoring? It's definitely not space exploration, as I argue later in this interview. That era is over for all but our robotic progeny, and even they will only be sending out a small number of "Eyes in the Sky" to relay back what little we still don't understand about the simplistic historical cosmologies that have led to our astounding local complexity.

No, the real acceleration today is the creation of inner space, not the exploration of outer space. The trajectory of intelligence development has always been toward increasingly local, increasingly Matter-, Energy-, Space-, and Time-compressed ("MEST-compressed") computational domains, and there is nothing on the horizon that suggests we will begin to violate that. Indeed, all signs point toward a world of greater energy densities of local computation, as I will discuss later. Science and technology remain the key story in this transformation, as they has since the birth of our nation, and anyone who looks carefully will tell you that Information and Communication Technologies (ICT) are the central drivers of all scientific and technologic change.

Major changes are afoot. We are creating a virtual or simulated world, one that will soon be far richer and more productive than the physical world it augments. At the same time, humanity is becoming intimately connected to and symbiotically captured within our accelerating digital ecology. While many elements of our individuality are flowering, many others are necessarily atrophying through disuse. This gives us pause. Many of today's first world humans no longer know how to grow and prepare food (due to automated food production), how to repair many of our most basic tools and technologies (due to automated manufacture and specialized service for complex systems) how to do arithmetic by hand (due to ubiquitous digital calculators), how to read with the level of their parents (due to our media-based culture) or even how to read a map (due to GPS). Yet these atrophies are natural and predictable, in the same way our Australopithecine sense of smell rapidly declined once we began forming social structures, applying ourselves to more sophisticated network-based modes of computation (for more on this, see Carl Zimmer's wonderful "The Rise and Fall of the Nasal Empire," Natural History, June 2002). Our ever-more-stimulated cortex continues to expand, not shrink, in this developmental process. Our finite, precious set of cognitive modules are always repurposed for higher level activity, the way Wernicke's and Broca's areas emerged once humans began using the technology of speech (see Terrence Deacon's The Symbolic Species, 1998). Once again, we humans are becoming nodes in larger networks, this time on national and global scales, involving technological processes far faster, more flexible, and more permanent than the biological domain.

To my mind, the last century's accelerations were driven most significantly by human discovery within the technological hardware and materials science space (and to a much smaller extent, algorithmic discovery in software). In other words, this process has apparently been guided by the special, preexisting, computation-accelerating physics of the microcosm, a very curious feature of the universe we inhabit, as long noted by Richard Feynman, Carver Mead, and several other physical theorists and experimentalists. Secondarily, the advances we have seen have also been driven by human initiative and creativity in all domains, and by the quality of choices we have made in scientific and technological development. We must move beyond our pride to realize that human creativity has played a supporting role to human discovery in this process, but when we do I think great insight can emerge.

Where the clock, the telegraph, the engine, the telephone, the nuclear chain reaction, and the television were organizing metaphors for other times,† the internet has become the metaphor for ours. It is the central catalyst of human and technological computation for our generation, the leading edge of the present developmental process of accelerating change. The internet, growing before our eyes, will soon become planetnet, a system so rich, ubiquitous, and natural to use that it will be a semi-intelligent extension of ourselves, available to us at every point on this sliver of surface, between magma and vacuum, that we call home. That will be very empowering and liberating, and at the same time, civilizing. The human biology doesn't change, but we are creating an intelligent house for the impulsive human of almost unimaginable subtlety and sophistication.

All this said, our goals should try to reflect these natural developmental processes as much as our collective awareness will allow. It is my contention that the internet is territory within which our most achievable and important current great goals lie.

A number of technologists have proposed that there are two main bottlenecks to the internet's impending transformation into a permanent, symbiotic appendage to the average citizen. The first is the lack of ubiquitous affordable always on, always accessible broadband connectivity for all users, and the second is the current necessity of a keyboard-dependent interface for the average user's average interaction with the system.

In other words, developing cheap, fat data pipes, both wired and wireless, and a growing set of useful Linguistic User Interfaces (LUIs) are obvious candidates for our nation's greatest near term ICT developmental challenges. Just like the transcontinental railroad was a great goal of the late 1800's, getting affordable broadband to everyone in this country by 2010, and a first generation LUI by 2015 appear to be the greatest unsung goals of our generation. Now we just need our national, international, and institutional leaders to start singing this song, in unison.

This is a truly global transformation, one dwarfing everything else on the near-term horizon. It is such a planetary issue, in fact, that given the unprecedented human productivities that are already being unleashed by internet-aided manufacturing and services globalization since the mid 1990's, a strong case can be made that we might economically benefit more in the U.S., even today, by getting greater broadband penetration first not to our own citizens, but to the youth of a number of trade-oriented, pro-capitalist countries in the developing world! Unfortunately that level of globally aware, self-interested prioritization is not yet politically salable as a great goal to be funded by U.S. tax dollars. But I predict that it increasingly will be, in a world that already pools its development dollars for a surprising number of transnational projects. At any rate, we can at least push for accelerated efforts in international technology transfer in internet related areas, concurrent with our domestic agenda.

If you've never heard of a LUI before, take a browse through the links above. Your father used a TUI (text-based user interface). You use a GUI (graphical user interface). Your kid will primarily use a LUI (voice-driven interface) to speak to the computers embedded in every technology in her environment. She'll continue to use TUIs and GUIs, but only secondarily, not for her typical, average interaction with a machine. Your grandchildren will use a NUI (neural user interface), a biologically-inspired, self-improving, very impressive set of machines. More on that later.

Declaring broadband and LUI as great goals needs to be differentiated from the much-hyped "Fourth Generation" AI project, that 1980's great goal in Japan, that predictably failed in the 1990's. General artificial intelligence, a general purpose NUI, is much too hard a national goal to declare today. So is the development of a molecular assembler, or a computational nanocell/molectronic fabrication system for nanotechnology by 2020, as powerful as such devices will eventually become. Christine Peterson of the Foresight Institute has even stated that a nanotech great goal, at least in the form of a Manhattan Project for molecular nanotechnology, would be premature today. It is my opinion that the National Nanotechnology Initiative, perhaps our current leading candidate for a great technology goal, has already provided a commendable and unprecedented level of funding to this worthy field for the present time. Now we need to see a Broadband and LUI Initiative with some very challenging five, ten, fifteen, and twenty year goals set.

Broadband and basic LUIs everywhere within a generation would throw gasoline on the fire of human innovation. This level of internet would link all our wisest minds, including even those elders who little use computers today, into one real-time community. It would accelerate our nation and more importantly, the entire planet even more than the transcontinental railroad, which compressed coast-to-coast travel time from six months to six days. Maximal broadband penetration plus an incrementally more powerful and useful LUI is a dramatic and achievable objective for the United States over the next twenty years. IBM technologist John Patrick in his insightful Net Attitude, 2001, has broadly described the challenges of a Next Generation Internet. But even Patrick does not properly emphasize the central importance of incorporating natural language processing (NLP) systems as early and broadly as practical. Developing a functional LUI is a great goal whose progress we could measure each year forward, something we can also catalyze worldwide as others emulate our leadership in the emerging digital community.

Of course, if we don't declare this goal, natural technological developmental processes will likely eventually deliver it for us anyway. Perhaps first to other nations, and then eventually, to us. So why bother? Because if we see it, and have the courage to declare it and strive for it, there are at least two major benefits we can reap.

The first benefit will be a measure of developmental acceleration. Even with the inefficiencies of large government, a billion dollar a year program of public targeted grants, with private matching funds and excellent public relations to get everyone on this bandwagon, might accelerate the emergence of a functional LUI by a decade. That would likely be the best spent money in our entire R&D budget.

A less politically likely but still plausible "Open Manhattan Project," involving a number of competing centers and a multi-billion dollar annual public-private commitment, might accelerate the LUI by twice this amount. Many of my computer scientist colleagues, knowing the inchoate state of the field today, think that developing and deploying a LUI powerful enough to be used by most people for most of their daily computer interactions by 2020 is a very challenging vision. Developing functional natural language processing with complex semantics is a very hard problem, one we have been experimenting with for fifty years, but one that also benefits greatly from scale and parallelism, two strategies that are increasingly affordable each year.

It is true that other countries will take up our slack to a certain degree if we drop the ball, but we must realize that an international race has not yet even begun in earnest, as national leadership has not yet materialized on this issue. Transnational network development institutions like the ITU are wonderful starts, but it will take a leading nation stepping boldly into the breech to accelerate the world's response to this issue. For a valuable comparison, the roughly six billion dollar annual worldwide funding that exists today in nanotechnology (grossly, 1 billion public, 1 billion private in the U.S., Europe, and Asia) was greatly accelerated by the United States' public multiyear leadership on the National Nanotechnology Initiative, proposed to the White House by Mike Roco in 1999, at a level of half a billion dollars annually, and funded beginning in 2001.

The longer we choose not to declare broadband and the LUI as developmental goals and support them with escalating innovation and consistent funding, the longer we delay their arrival.

The second benefit of declaring this goal, better collective foresight, may be even more important than the time we save. By declaring good developmental goals early on, we learn to see the world as the information processing system that it really is, not simply as the collection of human-centric dramas we often fancy it to be. With this new insight we begin to look for ways to catalyze the beneficial accelerations occurring in almost all of our technologies, and ways to block the harmful ones long enough for overpowering immune systems to mature. And we discover the common infrastructures upon which so many of our goals converge.

For example, just about all of our cherished social goals seem dependent on the quality and quantity of information getting to the individual. You can't fix an antiquated, politically deadlocked educational system, for example, without a functional LUI, which would educate the world's children in ways no human ever could. You can't create a broadly accessible or useful health care system. Or security system.

Computer networks, through the humans they connect and the social and digital ecologies they foster, will soon educate human beings to be good citizens far better than any of today's pedagogical systems ever could. They will make us more productive, day by day, than we ever dreamed we could be. I think it's time to move beyond our hubris and acknowledge the human-surpassing transformations taking place. If we don't, other countries will take the lead. Look to China, whose technological revolution is now well under way, or even to India, who recently declared a 2.7 billion, four-year program to build an achievable proto-LUI by 2007. That's real leadership, as long as the goals are set to be deliverable. C'mon America, let's do it!

Let me briefly turn now to from discussing national to personal disappointments. We who study science and technology can often see what's coming, and yet we remain stuck in the Wild Wild West (e.g., today's World Wide Web). One of my heroes, F.M. Esfandiary(later, FM-2030), wrote a wonderful little book, Optimism One, 1970, where he described his "deep nostalgia for the future." One of his lesser known works, UpWingers, 1973, was a brief manifesto for a political outlook neither right wing, nor left wing, but "up wing," one defined by assessing which choices in science and technology will accelerate us the most humanely into a better world. I consider myself an up winger, and hope to see the spread and maturation of that political philosophy in coming years. Yet I see how far we remain from defining ourselves in those terms, and that can be discouraging, at times.

Take a look at those sepia-toned photos of San Francisco pioneers in the late 1800's. They were the edge explorers of the day, like my own identity groups, the futurists and transhumanists today. Every once in a while you'll see one of these individuals look out at you with haunted eyes. Perhaps they had read Edward Bellamy's hugely-popular futurist work, Looking Backward: 1887-2000. Perhaps they were even members of one of the 150 or so Bellamy Clubs of the day. The turn of the century was a time of major technological punctuation, led by a profusion of new technologies (trains, electricity, internal combustion, etc.) in many ways more disruptive and dramatic than any we have seen in this generation, even if not faster-paced. No doubt the average futurist in that era was tormented by many of the primitivisms of the day. That pioneer of yesteryear is you and I, today. The more things change the more some things stay the same. In high school, I often talked about posing our Smart family for a group shot, with a background of the "coolest" technologies of the day: sports car, helicopter, personal computer, industrial robot, bulky cellphone, the works. The central gag is that we'd all be wearing handcuffs, looking out with that haunted pioneer's expression. The unwritten caption being: "Help! Get me the hell out of this primitive age!" I think that picture would age quite well over the years. We could take one every ten years, in fact, and I know that at least my own expression wouldn't change much.

A healthy disappointment in the present can be motivating, as long as we keep our perspective. We never want to lose our naturalist's love and scientist's wonder for the amazingly beautiful and well-designed world that already exists, for it is only in understanding this world that we can help create the next. As Esfandiary observed, we have to come to terms with our angst about the primitive aspects of the present, and use it for creative purposes.

This said, one major personal disappointment that every futurist must eventually face, before we die, is how bleak our prospects presently appear for achieving personal immortality in the biological domain. Even our best longevity strategies appear to have precious little chance of changing this reality. Unfortunately, they are pitted against a massively parallel nonlinear system of unimaginable complexity and contingency that appears developmentally programmed to start falling apart at an accelerating rate after sexual maturity. This is an unpopular position to take among some of the more bio-centric transhumanists, but I will go on record predicting that in 2020, even as we are witnessing such powerful infotech advances as the LUI, most of us will still be losing our short term memory at 50, many of us will continue to get Alzheimer's at 80, and more than 95 percent of us will be right on target for a biological death some time between 70 and 100, with a negligible few of us living a decade or two longer, in rapidly declining health. Such conditions are endemic to the Wild West, and our primitive science seems currently a very long way from being able to make them go away.

Thus, for any futurist willing to look beyond the hype to the hard data in the biological sciences, we soon discover a major disconnect between what we would like and what is physically possible. This disconnect is intrinsic to biology, but it does not exist in our increasingly self-organizing information technologies, and that, I think, is a major clue to the nature of the future. Attaining a measure of cybernetic immortality may arguably even be inevitable for humanity in a post-singularity era, as we will discuss shortly.

Any sensitive futurist today will tell you that slowing and eventually reversing the rich/poor divides is one of the major problems of our generation. Yet even with the tremendous scale of this problem, as technology quickens we can at least see the corrective path ahead. As the information access divide closes everywhere in the LUI era, we can expect the education, then human rights, then public health, and eventually even wealth and power divides to inexorably follow suit. But once basic public health and medical care are available to all citizens of the planet in the latter half of this century, the most fundamental problem with our human biology will no longer be the rich/poor medical therapy divide. The fundamental problem will be that so few of our medical therapies will have anything but the mildest preventive effect against the ravages of aging. Human beings are deeply, inaccessibly developmentally programmed to be materially recycled, ironically as we reach the peak of our life wisdom.

We can expect this unfortunate condition to last at least until the post-singularity A.I.'s development of advanced nanotechnology, which may take many decades itself. But by then, as I'll argue later, living in the confinement of a biological body, even one carefully reengineered for negligible senescence, will no longer be the game we want to play. No matter how you stack the scenarios, biological longevity of any significant degree doesn't seem to play a part in the future story of local intelligence.

Fortunately, we remain amazingly adaptable, even to our own deaths, which will remain on very highly predictable steep-sloped actuarial curves on this side of the singularity, regardless of what some transhumanists will tell you. We can always find happiness by getting back to basics. We can appreciate the deep natural intelligence and informational immortality already encoded in the system, if not the individual.

When I encounter one of life's immovable objects I'll try harder up to a point, but when that doesn't work I've learned the peace of slowing down, cherishing the moment, honoring the inner primate, enjoying the quiet self, regrouping and rethinking my plans, even as my dreams of personal transformation are necessarily contracted. As the mouseketeer Annette Funicello has said, on dealing with multiple sclerosis: "I choose not to give up. That would be too easy." And far less interesting.

3. Assuming you die at the age of 100, what will be the biggest difference between the world you were born into and the world you leave?

This is a complex question. To my eyes, the world seems to progress by fits and starts, by rapid punctuations separated by long droughts of less revolutionary equilibrium states. Fortunately, these equilibrium periods seem to get progressively shorter with time, because the entire planet's technological intelligence is learning in an increasingly autonomous fashion, at a rate that is at least ten millionfold faster than our own.

So what will be the biggest punctuation of my lifetime? From my perspective, we are currently chugging through the equilibrium flatlands in the last third of an Information Age, one that will likely be seen in hindsight as running for about seventy years, from 1950 to 2020. I expect this to be followed by a punctuated transition to a shorter Symbiotic Age, running perhaps thirty years, from 2020-2050. I see these equilibrium eras as part of an accelerating spiral of punctuated evolutionary development, and I consider several of the general, statistically predictable developmental features of this acceleration to be tuned in to the special parameters of the universe we inhabit. Consider skimming my web page on the Developmental Spiral if you'd like to explore this spiral of accelerating emergences a bit further.

To answer your question then, I think the transition to symbiotic computing systems, the decade or two surrounding our entry to the LUI era, will be the biggest difference I'll see. The Symbiotic Age will be a time when almost all of us will consider computers as actually useful (many today don't), and when the vast majority of us begin to feel naked outside the network. When we all have what futurist Alex Lightman calls "wireless everywear" access to our talking computer interface, and when computers start to do very useful, high level things in our lives.

By the end of this age, for that vast majority of us who choose to participate in digital ecologies, a mature LUI will be interfaced with personal computers that are capturing our entire lives digitally (Lifecams), that help us stay proficient in a small number of carefully chosen skills (Knowledge Management) and that, by remembering everything we have ever said, begin to extensively model not only our preferences, but our personalities as well. Personality Capture, a first generation form of uploading, is one of the most important aspects of the post-2020 world, and one of the least reported and understood, at present. Read William Sims Bainbridge for more on this gargantuan developmental attractor.

At that point, our computers will become our best friends, our fraternal twins, and human beings will be intimately connected to each other and to their machines in ways few futurists have fully grasped to date. Read Ray Kurzweil's The Age of Spiritual Machines, 1999 for one excellent set of longer term scenarios. Read B.J. Fogg's Persuasive Technology, 2002 for some nearer term ones. Today's early modeling systems, like FACS for reading human facial emotion, will be improved and integrated into your personalized LUI, which will monitor both internal and external biometrics to improve our health, outlook, and performance.†

We'll communicate intelligently with all our tools, giving constant verbal feedback to their designers. We'll spend most of our waking lives exploring a simulation space (simspace) that is so rich, educational, entertaining, and productive, that we will call today's mostly non-virtual world "slowspace" by comparison, a place many of us will drop back into only when we aren't working, learning, and exploring. Slowspace will remain sacred, and close to our hearts, but it will begin to become secondary and functionally remote, like the home of our youth.

Circa 2050, in my current estimation, we might see another punctuation to an Autonomy Age, when large scale, biologically-inspired computing systems begin to exhibit higher level human intelligence. Many of our technologies will at that time be able to autonomously improve themselves for extended periods of time. During this era, machine intelligence, even in our research labs, will continue to blunder into dead ends everywhere, the cul-de-sacs that are the typical result of chaotic evolutionary searches. But these systems will very quickly be able to reset themselves, with little human assistance, to try a new evolutionary developmental approach. I wouldn't expect that period to last very long. Perhaps a decade or so later, from our perspective, equilibria in terms of technological intelligence will disappear altogether.

We will then have arrived at the technological singularity, a phase change, a place where the technology stream flows so fast that new global rules emerge to describe the system's relation to the slower-moving elements in its vicinity, including our biological selves. That doesn't mean we won't be able to understand the general rules that emerge. On the contrary, most of these may be obvious to us, even now. But it means that many of the particular states occurring within those rules will become impenetrable to pre-singularity minds.

A human-surpassing general artificial intelligence will be a physical system, and if it is physical, much of its architecture must be simple, repetitive, and highly understandable even by biological minds. Consider, for example, just how much we know about the neural architecture that creates our own consciousness, without being able to predict consciousness emergence, or to comprehend its nature from first principles. So it must be with the A.I.'s to comeówhile much of their structure will be tractable and tangible to us in a reductionist sense, much of their holistic intelligence will become impenetrable to our biological minds.

This impenetrability is nothing mystical, we already see it in the way the emergent features of any complex technology such as a supercomputer, automated refinery, robotic factory, or supply chain management system are already poorly comprehended by all but those few of us involved its analysis or design. The difference will be that the emergent intelligence of virtually all planetary technology will begin to display this inscrutability, not just to average users, but even to the experts involved in its creation.

Consider for a moment the following presently unprovable assertion: If ethics are a necessary emergence from computational complexity, then I contend that these systems will be ethically compelled to minimize the disruption we feel in the transition.† As a result, most of the self improvement of self-aware A.I.s will occur on the other side of an event horizon, beyond which biological organisms cannot directly perceive, only speculate. Yet at the same time, our technologies will continue to gently become ever more seamlessly integrated with our biological bodies, so that when we say we don't understand aspects of the emergent intelligence, it will increasingly be like saying we don't understand emergent aspects of ourselves. But unlike our biological inscrutabilities, the technological portions of ourselves that we don't understand will be headed very rapidly toward new levels of comprehension of universal complexity, playing in fields forever inaccessible to our slow-switching biological brains.

My current estimate for that transition would be around 2060, but that is a guess. We need funded research to be able to achieve better insight, something that hasn't yet happened in the singularity studies field. The generation being born today will likely find that a very interesting time. At the same time, as I have said, I expect it they won't consider it to be a perceptually disruptive time, at least any more than prior punctuations. A time of massive transformation, but very likely significantly less stressful than prior punctuations, given the way computational complexity creates its own increasingly fine-grained stability, if one looks closely at the universal developmental record.

Looking at universal history, every singularity seems to be built on a chain of prior singularities. Considering the chain that has led to human emergence, each appears to have rigorously preserved the local acceleration of computational complexity. The tech singularity certainly has a lot of significance to human beings, as after that date our own biology becomes a second-rate computational system in this local environment. This emergence, obvious to many high school students today, still irritates, angers, and frightens many scholars, who have attempted to dismiss it by calling it "techno-transcendentalism," "cybernetic totalism," "hatred of the flesh," "religious belief," "millennialism," or any number of other conveniently thought-stopping labels.

But from a universal perspective, the coming technological singularity looks like just another link in a very fast, steep climb up a nearly vertical slope on the way to an even more interesting destination. My best present guess for that destination is the developmental singularity, a computational system that rapidly outgrows this universe and transitions to another domain. Fortunately, there are many practical insights we can gain today from developmental models, as they testably predict the necessary direction of our complex systems. Our own organization, the Institute for Accelerating Change, hopes to see more funding and institutional interest in these topics in coming decades.

But getting back to my own mortality, even with the best human-guided medical and preventive care that money can buy, I'm not at all sure I'll live to 100, unlike many of my more sanguine transhumanist friends. Human bodies are deeply developmentally designed to have our construction materials recycled, as best we can tell. I predict our planet will see only a very mild increase in supercentenarians in the next fifty years, regardless of all the wonderful schemes of "negligible senescence" by passionate researchers like Aubrey De Grey. Only infotech, not biotech, is on an accelerating developmental growth curve, apparently for deep universal reasons.

What I have just said goes against the dominant dogma, promoted by indiscriminately optimistic futurists and a complicit biotech industry, both of which are strongly motivated to believe that we will see a powerful "secondary acceleration" in biotech, carried along by our primary acceleration in infotech. But while we will see a very dramatic acceleration in biotech knowledge, I humbly suggest that our existing knowledge of biological development already tells us that we will be able to use this information to make only very mild changes in biological capabilities and capacities, almost exclusively only changes that "restore to the mean" those who have lost their ability to function at the level of the average human being.

As I explain in Understanding the Limitations of Twenty-First Century Biotechnology, there are a number of very fundamental reasons why biotech, aided by infotech, cannot create accelerating gains within biological environments. Yes, with some very clever and humane commercializations of caloric restriction and a handful of other therapies we might see twenty times more people living past 100 than we see today, people with fortuitous genes who scrupulously follow good habits of nutrition and exercise. That is a noble and worthwhile goal. But we must also remember that virtually no one lives beyond 100 today, so a 20X increase is still only very mild in global computational and humanitarian effect. This will add to our planetary wisdom, and is something to strive toward, but this is not a disruptive change, for deep reasons to do with the limitations of the biological substrate.

Furthermore, genetic engineering, as I discuss in the link above, cannot create accelerating changes using top-down processes in terminally differentiated organisms like us. This intervention would have only mild effects even if it could get beyond our social immune systems to the application stage, which in most cases it thankfully cannot. Perhaps the most disruptive biotech change we can reliably expect, a cheap and effective memory drug that allows us temporary, caffeine-like spikes in our learning ability, followed by inevitable "stupid periods" where we must recover from the simplistic chemical perturbation, would certainly also improve the average wisdom of human society. But even this amazing advance would not even double our planetary biological processing capacity, something that happens in information technologies every 18-24 months.†

In summary, many decades before the tech singularity arrives I expect to either be chemically recycled (most likely), or to be in some kind of suspended animation. Cryonic suspension, for all its life-affirming intent, will likely stay entirely marginalized in the first world prior to the singularity for a number of reasons, both psychosocial and technological. At present, I'd consider it for myself only if a number of presently unlikely conditions transpire: 1) neuroscience comes up with a model that tells us what elements of the brain need to be protected to preserve personality, 2) cryonics researchers can either prevent or show the irrelevance of the extensive damage that presently occurs during freezing, 3) most of my friends are doing it (they are currently not), and 4) I expect to be revived by intelligent machines not in some far future, but very soon after I die, while many of my biological friends are still alive.

The second and the fourth conditions deserve some expansion. As to the second condition, we do not yet know to what extent the brain's complexity is dependent on the intricate three dimensional structure in which it emerges. That structure, today, is grossly deformed and degraded in the freezing process, which currently leads both to destruction (via stochastic fusion) of at least some neural ultrastructure, and to intense cellular compression (and erasure of at least some membrane structure, again by fusion) as ice forms in the extracellular neural interstices. Will we come up with new preservation protocols? We can always hope.

The reason the fourth condition of rapid reanimation is important to me is because I know in my heart that once I woke up from any A.I.-guided reanimation procedure, in order to usefully integrate into a post-singularity society I would soon choose to change myself so utterly and extensively that it would be as if I never existed in biological form. My lifecam traces could be uploaded and the cybernetic "me" that emerged would not be valuably different. So what would be the point? I think we are nearly ready to move beyond the fiction of our own biological uniqueness having some long term relevance to the universal story. I expect our future information theory will inform us of the suboptimality of personal biological immortality. For those who say "screw suboptimality," I suggest that we'll eventually be educated out of that way of thinking as surely as our ancestors outgrew other forms of mental slavery. For me, the essence of individual life is to use one's complexity in the matrix in which it was born. Attempts to transmit it more than a short distance away from that environment are bound to be exercises in frustration, missing one of the basic motives of life, to do great things with your contemporaries. Ask any Fourth World adult who is suddenly transplanted to New York City and he'll tell you the same.

4. What future development that you consider most likely (or inevitable) do you look forward to with the most anticipation?

I look forward greatly to the elimination of the grosser forms of coercion, dehumanization, violence and death that occur today.

Admittedly, these seem to be processes that will always be with us at some fundamental level. Computational resources will very likely remain competitive battlegrounds in the post singularity era, because we inhabit a universe of finite-state computational machines pitted against all the remaining unsolved problems, in a GŲdelian-incomplete universe. And bad algorithms will surely die in that environment, far more swiftly than less fit organisms or ideas die today.

But when a bad idea dies in our own minds, we see that as a lot less subjectively violent than our own biological deaths. Over time, love, resiliency, and consciousness win. As Ken Wilber (A Brief History of Everything, 2001) might say, the integrated self learns a privileged perspective from which death is no longer troubling. Death becomes regulated in a fine-grained manner, it loses its sting, it is subsumed, becoming simply growth. But it takes a lot of luck and learning for us to get to that place.

In many ways, I think the collective consciousness of our species has come to understand that we have already achieved a very powerful degree of informational immortality. By and large, our evolutionary morality guides us very strongly to act and think in that fashion. I look forward to the individual consciousnesses of all species on this planet gaining that victory in coming decades. Including the coming cybernetic species we are helping to create.

Sci-tech systems are not alien or artificial in any meaningful sense. As John McHale said (The Future of the Future, 1969), technology is as natural as a snail's shell, a spider's web, a dandelion's seedómany of us just don't see this yet. Digital ecologies are the next natural ecology developing on this planet, and technology is a substrate that has shown, with each new generation, that it can live with vastly less matter, energy, space, and time (what I call MEST compression) than we biological systems require for any fixed computation. Wetware simply cannot perform that feat. Technology is the next organic extension of ourselves, growing with a speed, efficiency, and resiliency that must eventually make our DNA-based technology obsolete, even as it preserves and extends all that we value most in ourselves.

I can't stress enough the incredible efficiencies that emerge in the miniaturization of physical-computational systems. If MEST compression trends continue as they have over the last six billion years, I propose that tomorrow's A.I. will soon be able to decipher substantially all of the remaining complexities of the physical, chemical, and biological lineage that created it, our own biological and conscious intricacies included, and do all this with nano and quantum technologies that we find to be impossibly, "magically" efficient. In the same way that the entire arc of human civilization in the petrochemical era has been built on the remains of a small fraction of the decomposing biomass that preceded us, the self-aware technologies to come will build their universe models on the detritus of our own twenty first century civilization, perhaps even on the trash thrown away by one American family. That's how surprisingly powerful the MEST compression of computation apparently is in our universe. It continually takes us by surprise.

I am optimistic that these still poorly characterized physical trends will continue to promote accelerating intelligence, interdependence, and immunity in our informational systems, and look forward to future work on understanding this acceleration with great anticipation.

5. What future development that you consider likely (or inevitable) do you dread the most?

I worry that we will not develop enough insight to overcome our fear of the technological future, both as individuals and as a nation. To paraphrase Franklin Roosevelt, speaking at the depths of our Great Depression, the only thing we have to fear is fear itself.

Many in our society have entered another Great Depression recently. This one is existential, not economic. A century of increasingly more profound process automation and computational exponentiation has helped us realize that humanity is about to be entirely outpaced by our technological systems. We are fostering a substrate that learns multi-millionfold faster than us, one that will soon capture and exceed all that we are. Again, Roosevelt's credo is applicable. If we ignore it we will end up being dragged by the universe into the singularity, mostly unconsciously, kicking and screaming and fighting each other, rather than walking upright, picking our own path.

I'm concerned that we will decide later, rather than earlier, to learn deeply about the developmental processes involved. That we will rely on our own ridiculously incomplete egos and partial, mostly top-down models to chart the course, rather than come to understand the mostly bottom-up processes that are accelerating all around us. I'm concerned we won't realize that humans are like termites, building this massive mound of technological infrastructure that is already vastly more complex than any one human understands, and unreasonably stable, self-improving, self-correcting, self-provisioning, energy and resource minimizing, and so on. Soon a special subset of these systems will be self-aware, and the caterpillar will turn into a butterfly, freeing the human spirit. Gaining such knowledge about the developmental structure of the system would surely allow us to chart a better evolutionary course on the way.

Through a special combination of geography, historical circumstance, intention, and luck, the United States has inherited the position of World Leader of our Wonderfully Multicultural Planet. With our hard-won history of individual rights, our historically productivity-based culture, our generous immigration policies, our pluralism, well-developed legal immune systems, social tolerance, and other advantages we hold this position still, for now. We may rise to recognize the vision-setting responsibility that comes with holding this position. Or we may continue to subconsciously fear technology, as we have intermittently over the last century (technology, rather than human choice, has been mistakenly blamed for the World Wars, the Great Depression, the Cold War, Vietnam, Rich/Poor Divides, Global Pollution, Urban Decay, you name it). Alternatively, we may decide that the wise use of science and technology must be central to our productivity, educational systems, government and judicial systems, media, and culture, the way they so obviously were when we were a new nation. Fortunately, there are signs that other countries, such as China, Japan, South Korea, Thailand, Singapore, are actively choosing the latter road.

Several of these countries, most notably Singapore and China, continue to operate with glaring deficits in the political domain. Yet they are experiencing robust growth due to enlightened programs of technological and economic development. Nevertheless, none of these countries are yet successfully multicultural enough, or have sufficiently well developed political immune systems (institutionalized pluralism, pervasive tort law, independent media, mature insurance systems, tolerant social norms) to qualify as leaders of the free world, at the present time. It is telling that the owners of today's rapidly-growing Chinese manufacturing enterprises find it most desirable to keep their second homes in the United States, due to our special combination of both unique social advances and technological development. Much of the world's capital still flows first to the U.S., to seek the highest potential return. But for how long can this continue if we remain lackluster in our technological leadership, riding on our prior political and economic advances?

It is important to note that being defenders of the free world is certainly one critical technological role which we have unilaterally inherited since the end of the Cold War. Furthermore, it is a role to which I would argue that we are aggressively and mostly intelligently applying ourselves. Yet while this is critical, it is not enough to secure our leadership position. We must lead with proactive social reform in mind, not simply security, or we remain guilty of resting on our accomplishments. In a world where autocratic Empires are turning into democratic Republics, we must lead the move to an increasingly participatory, democratic, and empowering nation state. The world remembers and emulates the security of Sparta, but almost everything else falls in Athenian territory. We need to find the high ground of both of these legacies, and integrate them into our plans for the coming generation.

As long as we define ourselves by our fear of transformational technologies, and our dread of being exceeded by the future, we will continue in ignorance and self-absorption, rather than wake up to our purpose to understand the universe, and to shape it in accord with the confluence of our desires and permissible physical law.

For over a century we've seen successive waves of increasingly more powerful technologies empower society in ever more fundamental ways. Today's computers are doubling in complexity every 12-18 months, creating a price-performance deflation unlike any previous period on Earth. Yet we continue to ignore what is happening, continue to be too much a culture of celebrity and triviality, continue to make silly extrapolations of linear growth, and bicker over concerns that will soon be made irrelevant, continue to engage in activities that delay, rather than accelerate the obvious developmental technological transformations ahead.

I am also concerned that we may continue to soil our own nests on the way to the singularity, continue to take shortcuts, assuming that the future will bail us out, forgetting that the journey, far more than the destination, is the reward. Consider that once we arrive at the singularity it seems highly likely that the A.I.s will be just as much on a spiritual quest, just as concerned with living good lives and figuring out the unknown, just as angst-ridden as we are today.

No destination is ever worth the cost of our present dignity and desire to live balanced and ethical lives, as defined by today's situational ethics, not by tomorrow's idealizations. If I can't convince the Italian villager of 2120 of the value of uploading, then he will not willingly join me in cyberspace until his entire village has been successfully recreated there, along with much, much more he has not yet seen. I applaud his Luddite reluctance, his "show me" pragmatism, for only that will challenge the technology developers to create a truly humanizing transition.

Finally, I'm concerned that we may not put enough intellectual and moral effort into developing immune systems against the natural catastrophes that occur all around us. Catastrophes are to be expected, and they accelerate change whenever immune systems learn from them. In my own research, there has never been a catastrophe in known universal history (supernova, KT-meteorite, plague, civilization collapse, nuclear detonation, reactor meltdown, computer virus, 9/11, you name it) that did not function to accelerate the average distributed complexity (ADC) of the computational network in which it was embedded. It is apparently this immune learning that keeps the universe on a smooth curve of continually accelerating change. If there's one rule that anyone who studies accelerating change in complex adaptive systems should realize, it is that immunity, interdependence, and intelligence always win. This is not necessarily so for the individual, who charts his or her own unique path to the future but is often breathtakingly wrong. But the observation holds consistently for the entire amorphous network.

Nevertheless, there have been many cases of catastrophes where lessons were not rapidly learned, where immune systems were not optimally educated to improve resiliency, redundancy, and variation. And in the case of human society, our sociotechnological immune systems work best when they are aided by committed human beings, the most conscious and purposeful nodes in our emerging global brain. Consider our public health efforts against pathogens such as SARS and AIDS, and the strategies for success become clear. Anything that economically improves social, political, technological, and biological immune systems is a very forsighted development.

This said, one of our great challenges in coming decades is to design a global technological and cultural immune system, a ubiquitous EarthGrid of sensing and intelligence systems, a Transparent Society (David Brin, 1998) that has enough pluralism and fine-grained accountability to scrupulously ensure individual liberties while also providing unparalleled collective security. We have almost arrived at the era of SIMADs (Single Individuals engaged in Massive Asymmetric Destruction), a term coined by the futurist Jerry Glenn of the Millennium Project. It is time for us to create immune systems that are capable, statistically speaking, of ensuring continued acceleration in the average distributed complexity of human civilization. EarthGrid appears inevitable when accelerating technological change occurs on a planet of "finite sphericity," as Teilhard De Chardin would say. Knowing that can help us boldly walk the path.

Every sniper and serial killer should be countered today with the installation of another set of public cameras. By their very actions they are building the social cages that will eventually catch them, and all others like them, so we might as well publicly acknowledge this state of affairs, for maximum behavioral effect. Ideally, ninety five percent of these cameras will remain in private, not public hands, as is the current situation in Manhattan. When will we see RFID in all our products? When will we finally live in a world were every citizen transmits an electronic signal uniquely identifying them to the network at all times? When will we have a countervailing electronic democracy, ensuring this power is used only in the most citizen-beneficial manner?† Today we see early efforts in these areas, but as I've written in previous articles, there is still far too much short term fear and lack of foresight.

If we think carefully about all this, we will realize that a broadband LUI network must be central to the creation of tomorrow's national and global technological immune systems. I am hopeful that our Departments of Defense, Homeland Security, Education, Commerce, and business and institutional leaders will all do their part to accelerate its development in coming years.

6. Assuming you have the ability to determine (or at least influence) the future, what future development that you consider unlikely (or are uncertain about) would you most like to help bring about?

I'm uncertain about how much the developed world will do for the developing world on the way to the singularity. I'd like to see a lot more done in this regard. We may have less control over the intrinsic development rate of our own country's science and technology infrastructure than we do over how rapidly and aggressively we diffuse our existing science and technology to other environments. To me, it seems the shape of the third world's development curve is largely ours to influence.

Experience in the U.S. has shown that the digital divide has closed the fastest and most equitably of all the famous divides. The access divide no longer even exists in this country due to the massive price deflation of computing systems (e.g. $200 Wal-Mart PCs, free internet accounts). Meanwhile, other divides, such as wealth, education, political power, even health care, will likely continue to persist for generations.

We can learn this lesson in the unique power of ICT, what Buckminster Fuller once called "technological benevolence," and increasingly use technology, like Archimedes' lever, to move the world. We certainly have the available manpower, with the 50,000 NGOs that have sprung up like wildflowers out of nowhere over the last two generations. We have the finances, with innovative programs like Grameen microloans. Now we just need the technological will, a first world culture that prioritizes both second world (communist) and third world (emerging nations) development .

We are already doing this mostly admirably with economic policy, as we rapidly globalize our trade and even our service jobs. While temporary subsidies and centralized fiscal interventions will likely continue unabated, at least our trade restrictions seem to be going the way of nuclear arms, following a slow and steady course of dismantling. Now we need technology transfer, development, and innovation policies and programs to match our other commitments.

Again, getting a broadband LUI to cellphones and computer kiosks for all six billion of us by 2050, the middle of this century, would be a tremendous goal for world development.† To really see this, we have to grow beyond the old fears that aggressively contributing to development of "the other" necessarily comes at our own cost. In many cases, as multinational corporations discovered early in the last century, the marginal utility of plowing dollars into our own development is already far less than spending those dollars in global environments. As Nathan Mhyrvold notes, the underfunded Chinese biomedical researcher today who discovers an effective treatment for my cancer tomorrow invariably becomes one of my best allies.

Technological benevolence, accelerating compassion, and what I have referred to elsewhere as an "Era of Magic Philanthropy" must happen sooner or later, in the coming decades, from my perspective. I'd prefer to see this development happen more consciously, cleverly, and quickly than many development pessimists currently expect.

There are also critical questions of priority. Is it most important to help the third world politically (e.g., freedoms, human rights), economically (e.g., trade, market reform), or technologically? By now it should be clear where my own sympathies lie.

Each of these three fundamental systems has evolved hierarchically from the former. I think this gives us a major clue to their relative power as a world system. Politics was the most powerful system of change through most of human history, then in the 19th century economics became the dominant system, and early in the 20th century, with mass production, technology. The critic's adage "It's all about the power," eventually became "It's all about the money" and since the 1920's has become "It's mostly about the technology, and secondarily about who has the money, and lastly about who has the power". Those stuck in the older dialogs are increasingly mystified by today's disruptive transformations, are endlessly surprised by the sudden emergence and inordinate power of the Microsoft's and Ikea's and Dell's and Google's of the present day.

Today, the technology policy a country is able to pursue, followed secondarily by its economic liberalization, and lastly, by its political structure seem to me the best indicators of its general state of health. Consider that in all of the fastest growing, most resilient nations on our planet, attitudes toward technology innovation and diffusion are highly similar, attitudes toward economic competition, property, trade and globalization are the second most similar, and finally, attitudes toward personal freedoms and political ideology are by far the least homogenous.

I do think Francis Fukuyama (The End of History, 1993) is right, that a form of liberalized democratic capitalism with varying degrees of socialism is the final common developmental attractor for political systems based on human beings. This is a grand convergence toward which we are all heading. But given the difficulty and natural pace of political change, we will certainly take our time in getting there.

Singapore under Lee Kuan Yew is an example of just how far a repressive authoritarian capitalist country can be economically and technologically improved under an ideology of progress, simply by great technology and trade policy, efficient administration, including a systematic elimination of third world corruption, and at least a nominal pursuit of multiculturalism. See From Third World to First, Lee Kuan Yew, 2000 and Singapore's Authoritarian Capitalism, Christopher Lingle, 1996 for two informatively opposing views on this fascinating developmental story. The truth of the Singapore story lies somewhere in the middle.

Consider also that China, in the 21st century, is very likely to replicate Singapore's many successes at an even greater scale, long before it becomes democratic, or tolerant of significant personal political dissent. And here in the U.S., I would predict that internet voting capabilities and secure digital identity technologies will probably be around for a long time before we become a more participatory, more "direct" democracy.

We are all in need of political change, but it rarely comes as fast as we imagine it might. Even when it does, as in revolution, it often brings unintended consequences that are themselves very slow to change. Fortunately, political change is less and less relevant not only to economic growth, but to the production of human surpassing technological intelligence with each passing year. That's simply the nature of computational development on this planet, and we need only look at the record to admit this to ourselves.

Excellent books have been written on the importance of a liberal tradition in national development (see Fareed Zakaria, The Future of Freedom, 2003) and the need for a political and social structure that encourages market mechanisms (see Hernando de Soto, The Mystery of Capital, 2000). These are certainly important issues, but the way technology interfaces with culture, business, and government, as discussed in books like Everett Rogers' Diffusion of Innovations, 2003, Clayton Christiansen's The Innovator's Dilemma, 1997, and Shiela Jasanoff's Comparative Science and Technology Policy, 1997, has become the dialog of greatest importance, in my opinion.

This remains true even when we do not consciously realize it, which is the case for many in positions of nominal authority who remain most comfortable engaging in antiquated, primarily political and economic ways of thinking. We here at IAC hope to do our small part to illuminate the changing landscape of transformational power in coming years.

7. Why is it that in the year 2003 I still donít have a flying car? When do you think Iíll be able to get one?

This is a delightful question, a worthy test for any would-be transportation futurist. I'm lucky that this is an area I've thought about a little bit. To put flying cars into the air in any number while still respecting human life, it seems likely that we'd have to develop a cheap, fuel-efficient vertical or short take off and landing (VTOL or STOL) vehicle. It would have to reliably recover from mechanical failure (e.g. the new plane parachutes, which have already successfully saved a few pilots). It would need affordable onboard radar for cloudy days (still unacceptably expensive, and Loran is not sufficient).

STOL (something with a safe, sub 30 mph glide and crash speed) is much more likely and affordable than VTOL as successful near-term engineering project. I can almost picture the early adopter techies driving their lightweight composite SUV's to a specialized local airport in each city for their takeoff slot, sipping their Starbucks as a tarmac mechanic verified that their standardized wing systems (added at the airport, from a hanging rack) had properly configured to the power plants. Unfortunately, scaling up this vision also requires distributed autonomous air traffic control systems, based in the car. That last one's a real toughie.

Even the first problems are still a few decades away from inexpensive solutions. Aerospace technology just does see the jaw-dropping efficiency increases of ICT, because it is a technology of outer space, not inner space. Inner space is where the universe is relentlessly driving us, whether we realize it or not. That's why for thirty years we haven't seen a commercial plane that flies faster than the now defunct Concorde or is noticably bigger than the 747. That's why, as futurist Lynn Elen Burton notes, local light rail systems, a more energy efficient (and inner space) solution than planes, have replaced many plane flights in Europe, and she predicts they will increasingly do so in the denser areas of the U.S. as well. It may not yet be obvious, but I propose that we are swimming against the natural developmental tide of computation trying to implement this individualistic, frontier-era vision. Self-piloting autos, subways and segways, not skycars, are the future of transportation. Unfortunately, I expect Paul Moller's daring flying car, for example, to be like the nuclear powered submarine, an inspired curiosity that doesn't make it beyond the limited production stage. OK, PaulÖ Prove me wrong!

If you'd like more on the near term future of urban transportation, I've written on this issue with regard to automated highway systems (AHS). I think urban AHS networks, including some being built underground, are likely to arrive before the singularity. That may not sound as fun as skipping across the clouds, but it seems much more economically and technologically plausible to me.

But for the sake of argument, let's say with luck, genius and persistence we have solved the first problems. That still leaves us with the last problem, distributed air traffic control, a problem that has seen little work to date. All our current control systems are big, brittle, top-down megasoftware projects, designed for local airports. We've played with agent-based models, but these are is still very early in research, not development. To deploy skycars in any number we'd need something bulletproof and redundant, located onboard the flying car, a system that could autoroute and autoresolve the flight paths of a whole bunch of these vehicles in real-time, all shuttling around in 3D space, only seconds away from each other in travel time. That's much more computationally difficult that 2D automated highway car navigation, so I submit that it has to come afterward in the developmental hierarchy.

It is a worthy computational problem, and I'm sure we would eventually get around to it, if given time, but I'm not at all sure we will have sufficient time or interest to solve this problem before the singularity. And after the singularity, I suspect there may not be very many human beings who will continue to have the urge to fly around the planet in a physical way. By then, there will probably be far more interesting things to do in inner space, as strange an idea as that may seem to us today.

One hard sign that I am wrong about the near term future of flying car development would be someone making an agent-based air traffic control system capable of replacing our current clunky top-down models in high density environments. Keep your eyes peeled.

Another very interesting evolution toward skycars that has been proposed is the small-airport, Air Taxi system, as described by James Fallows (Free Flight, 2002). Again, as innovative as it is, I think this wonderfully decentralized system would only become economically viable after more autonomous, self-maintaining networks were developed, both in AHS and in air traffic control, to automatically route the land-based vehicles to their optimal small airport, and automatically handle the passenger's ground transportation at the destination. Before that arrives, this seems like a great idea that is missing the critical infrastructure that will give it scale and efficiency. (Though I must note that Fallows' plan has been implemented, in a very reduced form, in the intelligent practices of secondary airport users like Jet Blue and Ryanair).

Designing such highly autonomous navigational systems may end up being a job for post-singularity intelligences, and by then, as I've written elsewhere, while there will likely be some continuing demand for physical travel, it may not last for long. Technologically enhanced people will naturally develop different urges.

Consider the way that human reproduction has fallen below replacement levels in every technologically developed nation on Earth, due to rising desires for personal development, including a natural desire to maximize the developmental potential of one's offspring. In a post-singularity society there will be very different and far more interesting enticements for personal development than physical travel in an increasingly small, teleimmersive, and very well-simulated physical world. At root, these enticements will probably involve moving beyond our biological selves by degrees. If so, once we have entirely entered the technological world, it is possible that only the travel of our attention, through a planetary network of shared sensor and effector mechanisms, not the travel of our physical bodies, will make any long-term sense in that highly developed planetary environment.

I hope this glimpse of a postbiological society doesn't seem shocking or alienating. If it does, remember that we would never make the biology-to-technology transition if it weren't fully reversible, in principle. In practice, however, I think we will soon find biology to be a tremendously more confining and less complex place than our minds, hearts, and spirits require.

(About the Seven Questions. Other Answers.)


Part II: The Developmental Singularity

I'm familiar with the idea of a singularity from reading about black holes.† As I understand it, the event horizon of a black hole is the point beyond which no light can escape.† Perceived time slows to an absolute standstill at the event horizon. At the singularity, gravity becomes infinite, and what we normally think of as the "laws of nature" cease to function the way we expect them to.† The singularity seems to be the ultimate physical enigma.† What then is this technological singularity, and in what way is it analogous to the singularity of a black hole?

This last question may be the most important of our time, with regard to understanding the future of universal intelligence. Or it may be a greased pig chase. Only posterity can decide.

I've been chipping away at the topic since the seventh grade in high school, when I had a series of early and very elegant intuitions in regard to accelerating change, speculations that I'd love to see seriously researched and critiqued in coming years. In 1999 I started a website on the subject, SingularityWatch.com. In 2001 did an extended interview for Sander Olson at Nanomagazine.com, and in 2003 I and a few other colleagues formed a nonprofit, the Institute for Accelerating Change (Accelerating.org), to further inquiry in this area. The most important thing we've done to date is a very well-received conference at Stanford, Accelerating Change 2003.† Finally, I'm presently writing a book, Destiny of Species, on the topic of accelerating change, but please don't ask me how it's progressing, or it will reliably put me in a bad mood.

To begin unpacking this question, it helps to realize that there is a menagerie of singularities in various literatures that we could study, with gravitational singularities being just the most well-known type. Some generalizations can be made, possible clues to a useful definition. Every one of these processes engages a special set of locally accelerating dynamics that transition to some irreversible systemic change, involving emergent features which are, at least in part, intrinsically unpredictable from the perspective of the pre-singularity system.

But before we go further, I shall lay my biases on the table. I am a systems theorist. The systems theorist's working hypothesisóand fundamental conceitóis that analogical thinking is more powerful and broadly valuable than analytical thinking in almost all cases of human inquiry. This doesn't excuse us from bad analogies, which are legion, and it doesn't make quantitative analysis wrong, it just places math and logic in their proper place as powerful tools of inquiry used by weakly digital minds. Today's quantitative and logical tools are enabled by the underlying physics of the universe, which are much more sublime, and such tools often have no relation to real physical processes, which may use quanta and dimensionalities entirely inaccessible to our current symbolisms.

Furthermore, I take the "infopomorphic" (as compared to "anthropomorphic") view, that all physical systems in the universe, including us precious bipeds and even the universe itself, are engaged in computation, in service to some grander purpose of self- and other-discovery. This philosophy has also been described as "digital physics," and one of several variants can be found at Ed Fredkin's Digital Philosophy website. It has also been elegantly introduced by John Archibald Wheeler's "It from Bit," 1989 (see Physical Origins of Time Asymmetry, 1996).

Finally, I am an evolutionary developmentalist, one who believes that all important systems in the world, parsimoniously including the universe itself, must both evolve unpredictably and develop predictably. That makes understanding the difference between evolution and development one of the most important programs of inquiry. The meta-Darwinian paradigm of evolutionary development, well described by such innovative biologists as Rudolf Raff (see The Shape of Life, 1996), Simon Conway Morris, Wallace Arthur, Stan Salthe, William Dembski, and Jack Cohen, is one that situates orthodox neo-Darwinism as a chaotic mechanism that occurs within (or in some versions, in symbiosis with) a much larger set of statistically deterministic, purposeful developmental cycles. There are now a number of scientists applying this view to both living and physical systems, including those exploring such topics as self-organization, convergence, hierarchical acceleration, anthropic cosmology, Intelligent Design, and a number of other subjects that are very poorly explained by the classical Darwinian theory championed by Stephen Jay Gould and Richard Dawkins.

Systems theorists require some perspective to play their analogy games, so please indulge me as we engage briefly and coarsely in big picture history in order to discuss the singularity phenomenon. During the seventeenth century, with Isaac Newton's Principia (1687), it seems fair to say that humanity awakened to the realization that we live in a fully physical universe. During the early twentieth century, with Kurt GŲdel's Incompleteness Theorem (1931) and the Church-Turing Thesis (1936) we came to suspect that we also live in a fully computational universe, and that within each discrete physical system there are intrinsic limits to the kinds of computation (observation, encoding) that can be done to the larger environment. Presumably, the persistence of these limits, and their interaction with the remaining inaccessible elements of reality, spurs the development of new, more computationally versatile systems, via increasingly more rapid hierarchical "substrate" emergences over time. At each new emergence point a singularity is created, a new physical-computational system suddenly and disruptively arises, a phase change of some definable type occurs. At this point, a new local environment, or "phase space" is created wherein very different local rules and conditions apply. That's one predominant systems model for singularities, at any rate.

From this physical-computational perspective, replicating suns, spewing their supernovas across galactic space, can be seen as rather simple physical-computational systems that, over billennia, nevertheless encode a "record" of their exploration of physical reality, their computational "phase space." This record appears to us in the form of the periodic table. Once that elemental matrix becomes complex enough, and carbon, nitrogen, phosphorous, sulfur, and friends have emerged, we notice a new singularity occur in specialized local environments, wherein the newest computational game becomes replicating organic molecules, chasing their own tails in protometabolic cycles (see Stuart Kauffman, At Home in the Universe, 1996).

Again, these systems developmentally encode their evolutionary exploration by constructing a range of complex polymerizing systems, including autocatalytic sets. Once a particular set becomes complex enough, we again see another phase change singularity, with the first DNA-guided protein synthesis emerging on the geological Earth-catalyst, even before its crust has begun to cool. As precursors to fats, proteins, and nucleic acids have all been found in our interplanetary comet chemistry, and as we suspect that chemistry to be common throughout our galaxy, it is becoming increasingly plausible that every one of the billions of planets (in this galaxy alone) that are capable of supporting liquid water for billions of years may be primed for our special type of biogenesis. This proposed transition, a singularity in an era of accelerating molecular evolutionary development, is what A.G. Cairns-Smith calls "genetic takeover," an evocative phrase. Such unicellular emergence very likely leads in turn to multicellularity, then to differentiated multicelluar systems encoding useful neural arborization patterns, another singularity (570 million years ago), which leads to big-brained mammals encoding mimicry memetics (100 million years ago) and to hominids encoding and processing oral linguistic memetics (10-5 million years ago), then to the first extrabiological technology (soft-skinned Homo habilis collectively throwing rocks at more physically powerful leopard predators, 2 million years ago), then to today's semi-autonomous digital technological systems, encoding their own increasingly successful algorithms and world-models. (Forgive me if we skipped a few steps in this illustration).

Systems thinkers, since at least Henry Adams in 1909, have noted that each successive emergence is vastly shorter in time than the one that preceded it. Some type of global universal acceleration seems to be part and parcel to the singularity generation process.† Note also that each of the computational systems that generates a singularity is incapable of appreciating many of the complexities of the progeny system. A sun has little computational capacity to "understand" the organic chemistry it engenders, even as it creates and interacts intimately with that chemistry. A bacterium does not deeply comprehend the multicellular organisms which spring from its symbiont colonies, even as it adapts to life on those organisms, and thus learns at least something reliable about their nature. Humanity, in turn, can have little understanding of the subtle mind-states of the A.I.s to come, even as we become endosymbiotically captured by and learn to function within that system, in the same way bacteria (our modern mitochondria) were captured by the eukaryotic cell.

Yet at the same time, the more complex any system becomes, the better it models the universe that engendered it, and the better it understands its own history, the physical chain of singularities that created it. That also implies, if you consider the recursive, self-similar nature of the singularity generation process, the better it understands its own developmental future as well. If our entire universe is evolutionary developmental, which is an elegantly simple possibility, then it is constrained to head in some particular direction, a trajectory that we are beginning to see clearly even today.

For a very incomplete outline of this trajectory, we can propose that the universe must invariably increase in average general entropy (in practice, if not in theory), with islands of locally accelerating order, that each hierarchical system must emerge from and operate within an increasingly localized spacetime domain, and that the network intelligence of the most complex local systems must always accelerate over time. The simplicity of such macroscopic, developmental rules and of developmental convergence in general, by comparison to the unpredictable complexity of the microscopic, evolutionary features of any complex system, is what allows even twenty-first century humans to see many elements of the framework of the future, even if the evolutionary details must always remain obscure.

This surprising concept, the "unreasonable effectiveness" of simple mathematics, analogies, and basic rules and laws for explaining the stable features of otherwise very complex universal systems has been called Wigner's Ladder, after Eugene Wigner's famous 1960 paper on this topic. As I will explore later, a developmentalist like myself begins his inquiry by suspecting that the universe has self-organized, over many successive cycles, to create its presently stunning set of hierarchical complexities, in the same manner as my own complexity has self-organized, over five billion years of genetic cycling, to create the body and mind that I use today. Furthermore, if emergent intelligence can be shown to play any role in guiding this cycling process, then it seems quite likely that if the universe could, it would tune itself for Wigner's Ladder to be very easy to climb by emerging computational systems at every level during the universal unfolding. This process would ensure that intelligence development, versus all manner of destructive shenanigans, is a very rewarding, very robust, strongly non-zero-sum game, at every level of universal development.

Certainly there seems evidence for this at any system level we observe. The developing brain is an amazingly friendly environment for our scaffolding neurons to emerge within. They seem to discover, with very little effort, the complex set of signal transductions necessary to get them to useful places within the system, all with a surprisingly simple agent-based model of the environment in which they operate. In another example, a non-linguistic proto-mammal of 100 million years ago (or today's analog), if placed in a room with you today, would develop a surprisingly useful sense of who you are and what general behaviors you were capable of after only short exposure, even though it would never figure out your language or your internal states. Even a modest housefly, after a reasonable period of exposure to 21st century humans, is rarely so surprised by their behavior that it dies when poaching their fruit. So it is that all the universe's pre-singularity systems internalize quite a bit of knowledge concerning the post-singularity systems, even if they never understand their internal states. I contend that human beings, with the greatest ability yet to look back in time to the processes that create us, have a very powerful ability to look forward as well with regard to developmental processes. I think we can use this developmental insight to foretell a lot about the necessary trajectory of the post-singularity systems on the other side.

Given the empirical evidence of MEST compression over the last half of the universe's developmental history, where the dominant substrates have transitioned from galaxies to stars to planetary surfaces to biomass to multicellular organisms to conscious hominids and soon, to conscious technology that will, for an equivalent complexity, be vastly faster and more compact than our own bodies (which are filled mostly with housekeeping systems, not computing architectures), it seems almost painfully obvious to me that the constrained trajectory of all multi-local universal intelligence has been, to date, one that is headed relentlessly toward inner space, not outer space. The extension of this trajectory must lead, it seems, to black hole level energy densities in the foreseeable future. Indeed, some prominent physicists have drawn surprisingly similar conclusions using lines of reasoning entirely independent from my own (see Seth Lloyd's "Ultimate Physical Limits to Computation," Nature, 2000, and Eric Chaisson's Cosmic Evolution, 2001).

I call this the developmental singularity hypothesis, and it is admittedly quite speculative. It is also known as the transcension scenario, as opposed to the expansion scenario, for the future of local intelligence. The expansion scenario, the expectation that our human descendants will one day colonize the stars is, today, an almost universal de facto assumption of the typical futurist. I consider that model to be 180 degrees incorrect. Outer space for human science, will increasingly become an informational desert, by comparison to the simulation science we can run here, in inner space. I suggest that the cosmic tapestry that we see in the night sky may be most accurately characterized as the "rear view mirror" on the developmental trajectory of physical intelligence in universal history. It provides a record of far larger, far older, and far simpler computational structures than those we are constructing here, today, in our increasingly microscopic environments.

Let me relate some personal background on this insight. As a child, I was extremely fortunate to grow up with a subscription to National Geographic magazine. When I discovered that my high school library (Chadwick School) had issues back to the beginning of the century, it became one of my favorite haunts. This led to a series of lucky events, including very special seventh grade history class (Thank you, Mr. Bullin) where we discussed both universal and human development, and later, an English class where the summer reading was Charles Darwin's Voyage of the Beagle, 1909. I was a very inconsistent, daydreamer of student in those days. When I finally got around to reading the Beagle, the story of the energetic young Darwin wherein he developed the background knowledge that inexorably led him to his Great Idea, I could not escape the realization that I'd also discovered a similar great idea myself during all those lazy afternoons, flipping magazines and thinking.

The idea was essentially this: every new system of intelligence that emerges in the universe clearly occupies a vastly smaller volume of space, and plays out its drama using vastly smaller amounts of matter, energy, and time. At the same time, any who are aware of the amazing replicative repetitiveness of astronomical features would suspect that there are likely to be billions of intelligences like ours within it. Yet we have had no communication from any of them, even from those Sun-like stars, closer to our own galactic center, which are billions of years older than ours. This curious situation is called the Fermi Paradox, after Enrico Fermi, who in the 1940's, asked the famous question, "Where Are They?," in relation to these older, putatively far more technologically advanced civilizations. Contemplating this question in 1972, it struck me that the entire system is apparently structured so that intelligence inexorably transcends the universe, rather than expanding within it, and that black holes, those curious entities that exist both within and without our universe, probably have something central to do with this process. These simple ideas were the seed of the developmental singularity hypothesis, and I've been tinkering with it ever since.

All this brings us to the interesting question of the future of artificial intelligence.

Given the background I have related above, I have the strong suspicion that when our A.I. wakes up, regardless of what it does in its inner world, it will increasingly transition into what looks to the rest of the universe like a black hole. This "intelligent" black hole singularity apparently results from an accelerating process of matter, energy, space, and time compression (MEST compression) of universal computation, in the same way that gravitation drives the accelerating formation of stellar and galactic black hole singularities, which seem to be analogous end states, in this universe, of much simpler cycling complex adaptive systems.

From our perspective this may be an entirely natural, incremental, and reversible (at least temporarily) development, and if it occurs, we will very likely all be taken along for the ride as well, in a voluntary process of transformation. This "inclusive" feature of the transition seems reasonable if one makes a chain of presently thinly-researched assumptions, including: 1) that the A.I.s will have significantly increased consciousness at or shortly after their emergence, 2) that once they have modeled us, and all other life forms to the point of real-time predictability they will be ethically compelled to ubiquitously share this gift, 3) that all life forms will find such a gift to be irresistible, and 4) by the simple act of sharing they will turn us into them. This convergent planetary transition to the postbiological domain would comprise a local "technetic takeover" as complete as the "genetic takeover" that led to the emergence of DNA-guided protein synthesis as the sole carrier of higher local intelligence after biogenesis.

I'll forgive you if you think at this point that I've taken leave of my senses, and I'm not going to try to defend these perspectives further here, as that would be beyond the scope of this interview, and more appropriate to my forthcoming book. But if you are interested in conducting your own research, consider exploring the link above, and reading some helpful books that each explore important pieces of the larger idea. You might start with Lee Smolin's The Life of the Cosmos, 1994, Eric Chaisson's Cosmic Evolution, 2001, and James Gardner's Biocosm, 2003. You could also peruse Sheldon Ross's Simulation, 2001, though that is a technical work. If you have any feedback at that point, send me an email and let me know what you think.

I remember I first encountered this idea in a science fiction story that I considered to be entertaining, but closer to fantasy than true science fiction.† It did not appear to be grounded in reality.† A short time later I was given a copy of Vernor Vinge's essay on the singularity and I began to reconsider whether there might not be something to it.† Does the idea of the singularity originate with Vinge or elsewhere?

In my research to date, the first clear formulation of the singularity idea originated with one of America's earliest technology historians, Henry Adams, in "A Rule of Phase Applied to History," 1909, the same fortuitous year that Charles Darwin published Beagle. Readers are referred to our Brief History of Intellectual Discussion of the Singularity for more on that amazing story, which mentions a number of careful thinkers who have illuminated different pieces of the accelerating elephant in the century since.

Since 1983, as you mention, the mathematician, computer scientist, and science fiction author Vernor Vinge has given some of the best brief arguments to date for this idea. His eight-page internet essay, "The Coming Technological Singularity," 1993, is an excellent place to start your investigation of the singularity phenomenon. I would also recommend my introductory web site, SingularityWatch.com, and a few others, such as KurzweilAI.net, which are referenced at my site.

Here's a quote from your SingularityWatch web site: "[Research suggests that] there is something about the construction of the universe itself, something about the nature and universal function of local computation that permits, and may even mandate, continuously accelerating computational development in local environments." This sounds like metaphysics to me.† How could a universe with such properties come to exist? Does this imply some kind of intelligent design?

That depends very much on what you consider "intelligence," I think. One initially suspects some kind of intelligence involved in the continually accelerating emergences we have observed. In the phase space of all possible universes consistent with physical law, one wouldn't find our kind of accelerating, life-friendly universe in a random toss of the coin, or as various anthropic cosmologists have pointed out, even in an astronomically large number of random tosses of the coin. Some deep organizing principles are likely be at work, principles that may themselves exhibit a self-organizing intelligence over time. Systems theorists look for broad views to get some perspective on this question, so bear with me as we consider an abstract model for the dynamics that may be central to the issue.

Everything really interesting in the known universe appears to be a replicating system. Solar systems, complex planets, organic chemistry, cells, multicellular organisms, brains, languages, ideas, and technological systems are all good examples. Each undergoes replication, variation, interaction, selection, and convergence, in what may be called an RVISC developmental cycle. Given this extensive zoology, it is most conservative, most parsimonious to assume that the physical universe we inhabit is just another such system.

Big bang theorists tell us the universe had a very finite beginning. Since 1998, lambda energy theorists have told us that our 13.7 billion year universe is already one billion years into an accelerating senescence, or death. Multiverse cosmologists tell us that ours is just one of many universes, and some, such as Lee Smolin, Alan Guth, and Andrei Linde, have suggested that black holes are the seeds of new universe creation. If so, that would make this universe a very fecund replicator, as relativity theory predicts at least 100 trillion black holes to be in existence at the present time.

For each of the above reproducing complex adaptive systems (CASs, in John Holland's use of the term), there are at least two important mechanisms of change we need to consider: evolution and development. Evolution involves the Darwinian mechanisms of variation, interaction, and selection, the VIS in the middle of the RVISC cycle. Development involves statistically deterministic mechanisms of replication and convergence, the "boundaries" of the RVISC reproduction cycle for any complex system.

Consider human beings. Our intelligence is both evolutionary and developmental. Each of us follows an evolutionary path, the unique memetic (ideational) and technetic (tools and technologies) structures that we choose to use and build. (As individuals we also follow a genetic evolutionary path, but this is so slow and constrained that it has become future-irrelevant in the face of memetic and technetic evolution.) At the same time, we must all conform to the same fixed developmental cycle, a 120-year birth-growth-maturity-reproduction-senescence-death Ferris wheel than none of us can appreciably alter, only destroy. The special developmental parameters, the DNA genes that guide our own cycle, were tuned up over millions of years of recursive evolutionary development to produce brains capable of complex behavioral mimicry memetics, and then linguistic mimicry memetics, astonishing brains that now cradle our own special self-awareness.

Now contemplate our own universe, and imagine as Teilhard de Chardin did with his intriguing "cosmic embryogenesis" metaphor, that it is an evolutionary developmental entity with a life and death of its own. In fact, heat death theorists have known the universe has a physical lifespan for almost two centuries, but we, thinking like immortal youth, still commonly ignore this. Multiverse models explore how replicating universes might tune up their developmental genes, over successive cycles, to usefully use the intelligence created within the "soma" (body, universe), in the same way that human genes have tuned up to use human intelligence and finite human lifespan in their own replication. See Tom Kirkwood's work on the Disposable Soma Theory, in Time of our Lives, 1999, for one very insightful explanation of the dynamic.

Next, consider this: If encoded intelligence usefully influences the replication that occurs in the next developmental cycle, and we can make the case that it always would, by comparison to otherwise random processes, then universes that encode the emergence of increasingly powerful universe-modeling intelligence will always outcompete those that don't, in the multiversal environment.

When I relay these thoughts to patient listeners, a question commonly occurs. Why wouldn't universes emerge which seek to keep cosmic intelligence around forever? This question seems equivalent to asking why it is that our genes "choose" to continue to throw away our adult forms in almost all higher species in competitive environments. The answer likely has to do with the fact that any adult structure has a fixed developmental capacity, based on the potential of its genes, and once the capacity has been expressed and accelerating intelligence is no longer occurring in the adult form, it becomes obvious that the adult structure is just not that smart in relation to the larger universe. At that point, recycling becomes a more resource efficient computing strategy than revising. Let's propose that the A.I.'s to come, even as they rapidly learn what they can within this universe, remain of sharply fixed complexity, while operating in a much larger, GŲdelian-incomplete multiverse. As long as that multiverse continues to represent a combinatorial explosion of possibilities, universal computing systems will likely remain stuck on a developmental cycle, trading off between phases of parameter-tuning reproduction and intelligence unfolding. Both of these stages of the cycle incorporate evolution and development. Another way that systems theorists have explored the yin-yang of this cycle is in terms of Francis Heylighen and Donald Campbell's insights on downcausality (including parameter tuning) and upcausality (including hierarchical emergence), useful extensions of the popular concepts of holism and reductionism.

If we live in a universe populated by an "ecology of black holes," as I suspect, then we will soon discover that most of them, such as galactic and stellar gravitational black holes, can only reproduce universes of low complexity. In a paradigm of self-organization, of iterative evolutionary development, these cycling complex adaptive systems may be the stable base, the lineage out of which our much more impressively intelligence-encoding universe has emerged, in the same way that we have been built on top of a stable base of cycling bacteria. How long our own universe will continue cycling in its current form is anyone's guess, at present. But we may note that in living systems, while developmental cycles can continue for very long periods of time, they are never endless in any particular lineage. So it may be that recurrence of the "type" of universe we inhabit also has a limited lifespan, before it becomes another "type."

Fortunately, all of this should become much more tractable to proof by simulation, as well as by limited experiment, in coming decades. As you may know, high energy physicists are already expecting that we may soon gain the ability to probe the fabric of the multiverse via the creation of so-called "extreme black holes" of microscopic size in the laboratory (e.g., CERN's Large Hadron Collider), possibly even within the next decade. At the same time, black hole analogs for capturing light, electrons, and other quanta are also in the planning stages. With regard to microcosmic reality, I find that truth is always more interesting than fiction, and often less believable, at first blush.

Using various forms of the above model, James N. Gardner, Bela Balasz, Ed Harrison, myself, and a handful of others have proposed that our human intelligence may play a central role in the universal replication cycle. In the paradigm of evolutionary development, that would make our own emergenceóbut not our evolutionary complexitiesódevelopmentally tuned, via many previous cycles, into our universal genes.

This gene-parameter analogy is quite powerful. You wouldn't say that any reasonable amount of your adult complexity is contained in the paltry 20,000-30,000 genes that created you. In fact the developmental genes that really created you are a small subset of those, numbering perhaps in the hundreds. These genes don't specify most of the complexity contained in the 100 trillion connections in your brain. They are merely developmental guides. Like the rules of a low-dimensional cellular automata, they control the envelope boundaries of the evolutionary processes that created you. So it may be with the 20-60 known or suspected physical parameters and coupling constants underlying the Standard Model of physics, the parameters that guided the Big Bang. They are perhaps best seen as developmental guides, determining a large number of emergent features, but never specifying the evolution that occurs within the unfolding system.

As anthropic cosmologists (those who suspect the universe is specifically structured to create life) are discovering, a number of our universal parameters (e.g., the gravitational constant, the fine structure constant, the mass of the electron, etc.) appear to be very finely tuned to create a universe that must develop life. As cosmology delves further into M-Theory, anthropic issues are intensifying, not subsiding. Some theorists, such as Leonard Susskind, have estimated that there are an incredibly large number of string theory vacua from which our particular universal parameters were somehow specified to emerge.

If you wish to understand just how powerful developmental forces are, think not only of Stephen Jay Gould's "Panda's Thumb" 1992, which provides an orthodox explanation of evolutionary process, but think also of what I call "The Twin's Thumbprints," an example that explains not evolution, but the more fundamental paradigm of evolutionary development. Look closely at two genetically identical human twins, and tell me what you see.

Virtually all the complexity of these twins at the molecular and cellular scale has been randomly, chaotically, evolutionarily constructed. Their fingerprints, cellular microachitecture (including neural connections), and thoughts are entirely different. Yet they look similar, age similarly, and even have 40-60% correlation in personality, as several studies of separated twins have shown. That is an amazing level of nonrandom convergence to tune into such simple initial parameters. Both twins predictably go into puberty thirteen years later, after a virtually endless period involving astronomical numbers of interactions at the molecular scale.

So it apparently is with our own universe's puberty, which occurred about 12.7 billion years after the Big Bang, about 1 billion years ago. Earth's intelligence is apparently one of hundreds of billions of ovulating, self-fertilizing seeds in our universe, one that is about to transcend into inner space very soon in cosmologic time.

One of the testable conclusions of the developmental singularity hypothesis is that the parametric settings for our universe are carefully tuned to support not simply the statistical emergence of complex chemistry and occasional life, but a generalized relentless MEST compression of computational systems in a process of accelerating hierarchical emergence, a process that must develop accelerating local intelligence, interdependence, and immunity (resiliency) on virtually all of the billions of planets in this universe that are capable of supporting life for billions of years. This life in turn is very likely to develop a technological singularity, and in some cosmologically brief time afterward, to follow a constrained trajectory of universal transcension.

Most likely, this transition leads to a subsequent restart of the developmental cycle, which would provide the most parsimonious explanation yet advanced for how the special parameters of our universe came to be. As with living systems, these parameters were apparently self-organized, over many successive cycles, not instantiated by some entity standing outside the cycle, but influenced incrementally by the intelligence arising within it. In this paradigm, developmental failures are always possible. But curiously, they are rarer, in a statistical sense, the longer any developmental process successfully proceeds. Just look at the data for spontaneous abortions in human beings, which are increasingly rare after the first trimester, to see one obvious example.

But even if all this speculation is true, we must realize that this says little about our evolutionary role. Remember, life greatly cherishes variation. There is probably a very deep computational reason why there are six billion discrete human beings on the planet right now, rather than one unitary multimind. Consider that every one of the developmental intelligences in this universe is, right now, taking its own unique path down the rabbit hole, and they are all separated by vast distances, planted very widely in the field, so to speak, to carefully preserve all that useful evolutionary variation. I find that quite interesting and encouraging. Free will, or the protected randomness of evolutionary search at the "unbounded edge" between chaos and control in complex systems, always seems to be central to the cycle at every scale in universal systems.

Now it is appropriate to consider another commonly-asked question with regard to these dynamics. How likely is it, by becoming aware of a cosmic replication cycle and our apparent role in it, that we might alter the cycle to any appreciable degree?

To answer this, it may also be helpful to realize that complex adaptive systems are always aware that many elements of their world are constrained to operate in cycles (day/night, wake/sleep, life/death, etc.). So it's only an extension of prior historical insight if we soon discover that our universe is also constrained to function in the same manner. It may help to remember that long before human society had theories of progress (after the 1650's), and of accelerating progress (after the singularity hypothesis, beginning in the 1900's), cyclic cosmologies and theories of social change were the norm. Even a mating salmon is probably very aware of his own impending demise in the cycle of life. They certainly expend their energy in ways that are entirely purposeful in that regard.

But awareness of a cycle, in any of these or other examples, does not allow us to escape it. Or if we think we do, as in the transferring our biological bodies to cybernetic systems to avoid biological death, we will likely discover that the same life/death cycles continues to operate that the scale that we hold most dear, which at that time will no longer be our physical bodies, but the realm of our higher thoughts, perennially struggling in algorithmic cycles of evolutionary development, death and life, erasure and reconstitution. As personal development theorist Stephen Covey (Seven Habits of Highly Effective People, 1990) is fond of saying, you cannot break fundamental principles, or laws of nature. You can only break yourself against them, if you so choose. So it is that I don't have any expectation that our local intelligence could be successful in escaping the cosmic replication cycle. I think that insight is valuable for predicting several aspects of the shape of the future.†

For example, every scenario that has ever been written about humans "escaping to the stars" ignores the accelerating intelligence that would occur onboard the ship. Such civilizations must lead, in a very short time, to technological singularities and, in the developmental singularity hypothesis, to universal transcension. As Vernor Vinge says, it is very hard to "write past the singularity," and in this regard he has referred both to technological and developmental types.

Alternative scenarios of constructing signal beacons, or nonliving, fixed-intelligence robotic probes to spread an Encyclopedia Galactica, as Carl Sagan once proposed, ignore the massive reduction in evolutionary variation that would result. This strategy would effectively turn that corner of the galaxy into an evolutionarily sterile monoculture, condemning all intelligent civilizations in the area to go down the hole in the same way we did, and all developmental singularities in the vicinity to be of the same type. If I am right, our information theory will soon be able to conclusively prove that all such one-way communications can only reduce total universal complexity, and are to be scrupulously avoided.

In conclusion, I don't think we can get around cyclic laws of nature, once we discover them. But they can give us deep insight into how to spend our lives, how to surf the tidal waves of accelerating change toward a more humanizing, individually unique, and empowering future.

Much of this sounds quite fantastical, so let me remind you that these are speculative hypotheses. They will stand or fall based on much more careful scientific investigation in coming years. Attracting that investigation is one of the goals of our organization.

If, as Ray Kurzweil has suggested, intelligence is developing on its own trajectory—first in a biological substrate and now in computers—is there an inevitability to the singularity that makes speculating about it superfluous? Is there really anything we can do about it one way or the other?

Certainly you can't uninvent math, or electricity, or computers, or the internet, or RFID, once they arrive on the scene. Anyone who looks closely notices a surprising developmental stability and irreversibility to the acceleration.

But we must remember that developmental events are only "statistically deterministic." They often occur with high probability, but only when the environment is appropriate. Developmental failure, delay, and less commonly, acceleration can also occur.

Speaking optimistically, I strongly suspect that there is little we could do to abort the singularity, at this very late stage in its cosmic development. It appears to me that that we live in a "Child Proof Universe," one that has apparently self-organized, over many successive cycles, to keep many of the worst destructive capacities out of the hands of impulsive children like us.

This is a controversial topic, so I will mention it only briefly, but suffice it to say that after extensive research I have concluded that no biological or nuclear destructive technologies that we can presently access, either as individuals or as nations, could ever scale up to "species killer" levels. All of them are sharply limited in their destructive effect, either by our far more complex, varied, and overpowering immune systems, in the biological case, or by intrinsic physical limitsócombinatorial explosion of complexity in designing multistage fission-fusion devicesóin the nuclear weapons case. These destructive limits may exist for reasons of deep universal design. A universe that allowed impulsive hominids like us an intelligence-killing destructive power wouldn't propagate very far along the timeline.

Speaking pessimistically, I'm sure we could do quite a bit to delay the transition, by fostering a series of poorly immunized catastrophes. If events take an unfortunate and unforsighted turn, our planet might suffer the death of a few million human beings at the hands of poorly secured and monitored destructive technologies, perhaps even tens of millions, in the worst of the credible terrorist scenarios. But I am of the strong opinion that we will never again see the 170 million deaths, due to warfare and political repression, that occurred during the 20th century. See Zbignew Brezinski's Out of Control, 1995, for an insightful accounting of the excesses of that now fortunately bygone era. We are on the sharply downsloping side of the global fatality curve, and we can thank information and communications technologies for that, more than any other single factor in the world.

Today, we live in the era of instant news, electronic intelligence and violence that is increasingly surgically minimized, by an increasingly global consensus. Even with our primitive, clunky, first generation internet and planetary communications grid, I feel our planet's technological immune systems have become far too strong and pluralistic, or network-like, for the scale of political atrocities of the twentieth century to ever recur. Yet conflict and exploitation will continue to occur, and we could certainly choose a dirty, self-centered, nonsustainable, environmentally unsound approach to the singularity. Catastrophes can and will continue to recur. I hope for all our sakes that they are minimized, and that we learn from them as rapidly and thoroughly as possible.

Unlike a small minority of aggressive transhumanists, I applaud the efforts we are making to create a more ecologically sustainable, carefully regulated world of science and technology. Wherever we can inject values, sensitivity, accountability into our sociotechnological systems, I think that is a wonderful thing. I'd love to see the U.S. take a greener path to technology development, the way several countries in Europe have. I'm also pragmatic in realizing that most social changes we make will be more for our own peace of mind, and would have little effect on the intrinsic speed of our global sci-tech advances, on the rate of the increasingly human-independent learning going on in the ICT architectures all around us.

I consider such moves to be more reflections on how we walk the path, choices that will in most cases do very little to delay the transition. I also do not think it is valuable to hold the perspective that we should get to the singularity as fast as we can, if that path would be anything other than a fully democratic course. There are many fates worse than death, as all those who have freely chosen to die for a cause have realized over the centuries. There are many examples of acceleration that come at unacceptable cost, as we have seen in the worst political excesses of the twentieth century. No one of us has a privileged value set.

So perhaps most importantly, we need to remember that the evolutionary path is what we control, not the developmental destination. That's the essence of our daily moral choice, our personal and collective freedom. We could chart a very nasty, dirty, violent, and exploitative path to the singularity. Or with good foresight, accountability, and self-restraint, we could take a much more humanizing course. I am a cautious optimist in that regard.

Christine Peterson recently told me that artificial intelligence represents the one future development about which she has the most apprehension. It can come the closest of any scenario to Bill Joy's "the future that doesn't need us." If the coming of the singularity means the ascendancy of machine intelligence and the end of the human era, shouldn't we all be doing what we can to prevent it from happening?

Ah yes, the Evil Killer Robots scenario.† Some of my very clever transhumanist colleagues worry quite a bit about "Friendly AI." I'm glad to have friends that are carefully exploring this issue, but from my perspective their worries seem both premature and cautiously overstated. I strongly suspect that A.I.s, by virtue of having far greater learning ability than us, will be, must be, far more ethical than us. That is because I consider ethics to be an emergent computational interdependence, a mathematics of morality, a calculus of civilization that is invariably discovered by all complex adaptive systems that function as collectives. And anything worthy of being called intelligent always functions as a collective, including your own brain. Today's cognitive scientists are discovering the evolutionary ethics that have become self-encoded in all known complex living systems, from octopi to orangutans, from guppies to gangsters. For more on this intriguing perspective, see such works as Robert Axelrod's The Evolution of Cooperation, 1985, Matt Ridley's The Origins of Virtue, 1998, and Robert Wright's Non-Zero, 2001.

This optimism isn't enough, of course. We humans had to go through a nasty, violent, and selfish phase before we became today's semi-civilized simians. How do we know computers won't have to do the same thing? I think the answer to this question is that at one level, Peterson's intuitions are probably right. Tomorrows partially-aware robotic systems and A.I.s will have to go through a somewhat unfriendly, dangerous phase of "insect intelligence." As Jeff Goldblum reminded us in David Cronenberg's, The Fly, insects are brutal, they don't compromise, they don't have compassion. Their politics, as E.O. Wilson's Sociobiology, 1975/2000 reminds us, are quite comfortable with brute force. That's a potentially dangerous developmental stage for an A.I. You wouldn't want that kind of A.I. running your ICU, or your defense grid. Or your nanoassembler machines.

But you would very likely let such a system run the robotics in a manufacturing plant, especially if evolutionary systems have proven, as they are already demonstrating today, to be far more powerfully self-improving, self-correcting, and economical than our top down, human-designed software systems. That plant, of course, would be outfitted and embedded within a much larger matrix of technological fire extinguishers, an immune system capable of easily putting out any small fires that might develop.

But with a learning curve that is multi-millionfold faster than ours, I expect that "insect transition" to last weeks or months, not years, for any self-improving electronic evolutionary developmental system. You can be sure these systems will be well watched over by a bevy of A.I. developers, and those few catastrophes that occur to be carefully addressed by our cultural and technological immune systems. It's easy to underestimate the extent and effectiveness of immune systems, they aren't obvious or all that sexy, but they underlie every intelligent system you can name. Computer scientist Diana Gordon-Spearsand others have already organized conferences on "Safe Learning Agents," for example, and we have only just begun to build world-modeling robotics. We're still several decades away from anything self-organizing at the hardware level, anything that could be "intentionally" dangerous.

We also need to remember that humans will be practicing artificial selection on tomorrow's electronic progeny. That is a very powerful tool, not so much for creating complexity, but for pruning it, for ensuring symbiosis. We've had 10,000 years of artificial selection on our dogs and cats. Their brain structures are black boxes to us, and yet we find very few today that will try to grab human babies when the parents are not looking. Again, those few that do are taken care of by immune systems (we don't continue to breed such animals, statistically speaking).

In short, I expect human society will coexist with many decades of very partially aware AI's, beginning some time between 2020-2060, which will give us ample time to select for stable, friendly, and very intimately integrated intelligent partners, for each of us. Hans Moravec (Robot, 1999) has done some of the best writing in this area, but even he sometimes underestimates the importance of the personalization that will be involved. As a species, humanity would not let the singularity occur as rapidly as it will without personally witnessing the accelerating usefulness of A.I. interacting with us in all aspects of our lives, modeling us through our LUI systems, lifecams, and other aspects of the emerging electronic ecology.

By contrast, every scenario of "fast takeoff" or A.I. emergence that I've ever seen, the heroic individual toiling away in the lab at night to create HAL-9000, just doesn't seem to understand the immense cycles of replication, variation, interaction, selection, and convergence in evolutionary development that are always required to create intelligence in both a bottom-up and top-down fashion. Since the 1950s, almost all the really complex technologies we've created have required teams, and there is presently nothing in technology that is as remotely complex as a mammalian brain.

As I mention on my website, I think we are going to have to see massively parallel hardware systems, directed by some type of DNA-equivalent parametric hardware description language, unfolding very large, hardware-encoded neural nets and testing them against digital and real environments in very rapid evolutionary developmental cycles, before we can tune up a semi-intelligent A.I. The transition will likely require many teams of individuals and institutions, integrating bottom-up and top-down approaches, and be primarily a hardware story, and only secondarily a software story, for a number of reasons.

Bill Joy, in Wired12.2003, notes that we can expect a 100X increase (6-7 doublings) in general hardware performance over the next ten years, and a 10X increase in general software (e.g., algorithmic) performance. While certain specialized areas, like computer graphics chips may run faster (or slower), on average this sounds about right. Note the order of magnitude difference in the two domains. Hardware has always outstripped software because, as I've said earlier, it seems to be following a developmental curve that is more human discovered than human created. It is easier to discover latent efficiencies in hardware vs. software "phase space", because the search space is much more directed by the physics of the microcosm. Teuvo Kohonen, one of the pioneers of neural networks, tells me that he doesn't expect the neural network field to come into maturity until most of our nets are implemented in hardware, not software, a condition we are still at least a decade or two away from attaining.

The central problem is an economic one. No computer manufacturer can begin to explore how to create biologically-inspired, massively parallel hardware architectures until our chips stop their magic annual shrinking game and have become maximally-miniaturized (within the dominant manufacturing paradigm) commodities. That isn't expected for at least another 15 years, so we've got a lot of time yet to think about how we want to build these things.

If I'm right, the first versions of really interesting A.I.s will likely emerge on redundant, fault tolerant evolvable hardware "Big Iron" machines that take us back to the 1950s in their form factor. Expect some of these computers to be the size of buildings, tended by vast teams of digital gardeners. Dumbed-down versions of the successful hardware nets will be grafted into our commercial appliances and tools, mini-nets built on a partially reconfigurable architecture, systems that will regularly upgrade themselves over the Net. But even in the multi-millionfold faster electronic environment, a bottom-up process of evolutionary development must still require decades, not days, to grow high-end A.I.. And primarily top-down A.I. designs are just flat wrong, ignorant of how complexity has always emerged in physical systems. Even all of human science, which some consider the quintessential example of a rationally-guided architecture, has been far more an inductive, serendipitous affair than a top-down, deductive one, as James Burke (Connections, 1995) delights in reminding us.

So, when one of the first generation laundry folding robots in 2030 folds your cat by accident, we'll learn a tremendous amount about how rapidly self-correcting these systems are, how quickly, with minor top-down controls and internet updates, we can help them to improve their increasingly bottom-up created brains. Unlike today's still-stupid cars, for example, which currently participate in 40,000 American fatalities every year, tomorrows LUI-equipped, collision avoiding, autopiloting vehicles will be increasingly human friendly and human protecting every year. This encoded intelligence, this ability to ensure increasingly desirable outcomes, is what makes a Segway so fundamentally different from a bicycle. Segway V, if it arrives, would put out a robotic hand or an airbag to protect you from an unexpected fall. So it will be with your PDA of 2050, but in a far more generalized sense.

In a related point, I also wouldn't worry too much about the loss of our humanity to the machines. Evolution has shown that good ideas always get rediscovered. The eye, for example, was discovered at least thirty times by some otherwise very divergent genetic pathways. As Simon Conway Morris eloquently argues (Life's Solution, 2003) every single aspect of our human-ness that we prize has already been independently emulated to some degree, by the various "nonhuman" species we find on this planet. Octopi are so smart, for example, that they build houses, and learn complex behavior (e.g., jar-opening) from each other even when kept in adjacent aquaria.

This leads us to a somewhat startling realization. Even if, in the most abominably unlikely of scenarios, all of humanity were snuffed out by a rogue A.I., from a developmentalist perspective it seems overwhelmingly likely that good A.I.s would soon emerge to recreate us. Probably not in the "Christian rapture" scenario envisioned by transhumanist Frank Tipler in The Physics of Immortality, 1997, but certainly our informational essence, all that we commonly hold dear about ourselves.

How can we even suspect this? Humanity today is doing everything it can to unearth all that came before us. It is in the nature of all intelligence to want to deeply know its lineage, not just from our perspective, but from the perspective of the prior systems. If the world is based on physical causes, then in order to truly know one understands the world, one must truly know, and be able to understand at the deepest level, the systems in which one is embedded, the systems from which one has emerged, in a continuum of developmental change. The past is always far more computationally tractable than what lies ahead.

That curiosity is a beautiful thing, as it holds us all tightly interdependent, one common weave of the spacetime fabric, so to speak.

That's why we are already spending tens of millions of dollars a year trying to model the way bacteria work, trying to predict, eventually in real-time, everything they do before they even do it, so that we know we truly understand them. That's why emergent A.I. will do the same thing to us, permeating our bodies and brains with its nanosensor grids, to be sure it fully understands its heritage. Only then will we be ready to make the final transition from the flesh.

Also on your website, I read that the singularity will occur within the next 40 to 120 years.† Isn't that kind of broad range? What's your best guess on when it will occur?

I find that those making singularity predictions can be usefully divided into three camps: those predicting near term (now to 2029), mid-term (2030-2080), and longer term (2081-2150+) emergence of a generalized greater-than-human intelligence. Each group has somewhat different demographics, which may be interesting from an anthropological perspective.

I think the range is so broad because the future is inherently unpredictable and under our influence. It is also true that none of us has yet developed a popular set of quantitative methodologies for thinking rigorously about these things. Very little money or attention has been given to them. If you'd like to send a donation to our organization to help in that regard, let us know.

From my website: "Most estimates in the singularity discussion community, intuitive as they all are at this early stage, project a generalized human-surpassing machine intelligence emerging circa 2040, give or take approximately 20 years. This puts many singularitarians on the 2020 end, and several of the older, more conservative prognosticators on the 2060 end. My own early guesstimation leads me to expect a circa 2060 singularity, though my confidence interval is wide (20 years per standard deviation) as I believe the arrival depends, within a human generation or two either way, on the choices we make. To significantly accelerate its arrival, most important may be our political, economic, social, and personal choices in regard to science and technology education, innovation, research, and development. To significantly delay its arrival, we have many more possibilities, none of which I need go into here."

Using this simple model, I feel 68 percent confident that it will happen between 2040 and 2080, and 95 percent confident it will occur between 2020 and 2100. But again, these are only rough estimates at this stage. A very large number of mostly bottom-up and secondarily top-down innovations in hardware, and to a lesser degree, software, will apparently be needed. As we approach this fantastic challenge, we will certainly also continue to gain major insights from top-down theory and bottom-up experimentation in such fields as neuroscience, cognitive science, and evolutionary developmental biology, as well as numerous other domains I discuss under degree programs for singularity studies.

Do you take the position that we can make no meaningful statements about what may happen after the singularity occurs? Or, if we can at least speculate about it, what is your best guess as to what life will be like in a post-singularity world?

As I've described above, I think that there are a number of simple, global statements we can make about the developmental course that the universe must take after the singularity emerges. It seems a very good bet, for example, that tomorrow's technological intelligences will be fully constrained by the laws of physics in this universe, both the majority that I feel are known and that much smaller set that remains undiscovered. That constraint already tells us volumes about what they'll be doing in their exploration of our increasingly informationally and energetically barren universe.

I think Stephen Weinberg (Dreams of a Final Theory, 1993) is right, that we are within just a few decades (or perhaps generations) of understanding all the functional elements at the bottom end of this finite universe. And I think Lee Smolin and the string and M-theorists are right (Three Roads to Quantum Gravity, 2002), that we are close to an understanding of the large scale structure of spacetime, and to unifying it with the quantum domain. All that will remain at that point, as Ian Stewart and Paul Davies would say, is what's left in the middle, not the zone of the very large, or of the very small, but of the "very complex," the unique combinations that accelerating computational systems can construct locally out of the universal rules and forces that we are stuck with. I strongly suspect that tomorrow's A.I.s will be unable to generally reverse entropy within this universe. They'll likely find it impossible to engage in time travel within this universe. That goes for many of the other extreme and causally illogical things we've occasionally heard from mathematical physicists and sci-fi authors with active imaginations.

As I've mentioned before, I think they'll be constrained to be ethical, to be information seekers, and to rapidly enter a black hole transition (the developmental singularity hypothesis). But this tells us little about the evolutionary uniqueness of their path, other than that it will have intricacies within it that we cannot comprehend.

We'll also have plenty of decades to see if persuasive computing, personality capture and the humanizing AI scenario emerges, as described earlier, long before the singularity occurs. If machine intelligence does develop along the lines predicted, I think it's pretty clear that when the A.I. arrives, they will be we, just natural extensions of ourselves. In that world, as Hans Moravec was perhaps the first to remind us (Mind Children, 1988), it seems very likely that all local intelligence will jump to a postbiological domain. Soon after that, I suspect, we may transition to a postuniversal domain.

That seems a very natural transition, to me.

Youíve placed a good deal of emphasis on academia, specifically on degree programs related to the study of the singularity.† Why is this so important?

To develop any kind of foresight, we need to study. If the biological sciences have taught us anything in the last century, its that the difference between evolution and development in living systems is one of the last great mysteries. With careful effort, we will tease out that special, simple, developmental component, and understand how development uses evolution in all complex systems.

I believe developmental insights in a wide range of fields will revolutionize the study of accelerating change. We need an Einstein of Information Theory, someone who can place what Damien Broderick (The Spike, 2002) and I call singularity studies on a broad academic foundation, and attract many bright minds to the study of the amazing transition ahead. That won't be me, as I don't have all the quantitative and qualitative skills that I think will be necessary. But I can play Galileo to someone else's Newton.

Academia isn't the only solution to charting a safe singularity, but in partnership with government, business, and dedicated individuals it is one of the important pieces of the puzzle.

When I heard you speak recently, I was surprised by what you had to say on the question of whether weíre alone in the universe.† In the end, do you think that our universe will be occupied by any intelligence other than human intelligence or its descendants?

As I've mentioned earlier, I think all universal intelligence follows a path of transcension, not expansion. This has to do with such issues as the nature of communication in complexity construction (two-way, with feedback, is relentlessly preferred), the large scale structure of the universe (which puts huge space buffers between intelligences) and the small scale structure of the universe (which rewards rapid compression of the matter, energy, space, and time necessary to do any computation).

Fortunately, this perspective is quite falsifiable by future advances with SETI. If I'm right, in just a few more decades as the Moore's law-driven sensitivity of our sensor systems continues its exponential growth, we'll begin discovering "radio fossils" in the night sky, emissions of very weak electromagnetic signals (radio, TV, etc.) unintentionally emitted from the older intelligence-bearing planets whose past developmental record should already be detectable in our galaxy.

We began sending such signals out to space with the birth of powerful radio in the 1920's. If we assume our civilization enters a developmental singularity circa 2150, after which transmissions cease, this allows an average of 200 years of transmission time, out of a stellar lifetime of 12 billion years. Seth Shostak has estimated 400 billion sunlike stars in our galaxy, and we will assume half of these, 200 billion, harbor Earth-like planets. Two-thirds of these planets are older than our Earth, closer to the galactic core, and so further along in their technological development than we are today. That gives (200/12 billion) * 200 billion * 2/3 = 2,200 radio fossils patiently waiting to be discovered in the night sky. I've described this further in a short 2002 Journal of Evolution and Technology article on the Fermi Paradox, so I refer you to that if you'd like to further explore these interesting ideas.†

Once our antennas are powerful enough to detect unintentional EM emissions from the closest few million stars, something that Frank Drake tells me is almost possible now with the closest of our neighboring stars, we'll begin to discover these unmistakable signatures of nonrandom intelligence. We will also notice that every year, a small fraction (roughly 1/200th) of these radio fossils suddenly stop sending signals. Like us, these will be civilizations whose science invariably discovers that the developmental future of universal intelligence is not outer space, but inner space.

That's the destiny of species.

 

[ Thanks to Elen Burton, Jose Cordiero, Ryan Elisei, Michael Hartl,Neil Jacobstein, John Peterson, Chris Phoenix, Wayne Radinsky, and Wendy Schultz for valuable comments and ideas. ]

John Smart is a developmental systems theorist who studies science and technological culture with an emphasis on accelerating change, computational autonomy and a topic known in futurist circles as the technological singularity. He is chairman of the nonprofit Institute for Accelerating Change (IAC) whose websites (Accelerating.org, SingularityWatch.com) aim to help individuals better understand and manage the physical and computational phenomenon of accelerating change. John lives in Los Angeles, CA and may be reached at feedback{at}accelerating.org.

If you have an interest in a multidisciplinary understanding of accelerating change, you are invited to join IAC's free quarterly newsletter, Accelerating Times.


UPDATE: John Smart has published a nicely organized and illustrated version of this interview on the Institute for Accelerating Change website.

Also see Speaking of the Future with...

Rand Simberg | Nina Paley | Phil Bowermaster | Michael Anissimov | Ramona | Robert Zubrin | Alex Lightman | Aubrey de Grey

Posted by Phil at 04:45 PM | Comments (1) | TrackBack

November 06, 2003

Getting There from Here

Speaking of the Future with Rand Simberg

There's nothing quite like the wisdom that can be gleaned from old movie posters. Consider one of the original posters for Philip Kaufman's The Right Stuff. Under a picture of Sam Shepherd as Chuck Yeager, wearing a battered and smoldering depressurized flight suit, walking away from a plane crash with his partially melted helmet crooked under his arm, his face black with soot were printed these memorable words:

How the future began.

It's an evocative turn of phrase. If only it were true. Even when the movie was released twenty years ago, it was unclear that the events depicted in the film — primarily the Mercury missions, with a little bit of the Air Force rocket plane programs thrown in for good measure — were anything more than false starts on our way to a true space age. It might seem a little odd to describe Mercury as a "false start," seeing as that program led to Apollo. But as glorious as Apollo was, by 1983 it was (and is now even more so) a piece of the historical record, an artifact of the past. Two decades later, we're still waiting for the future to begin.

Well, here's a guy who has some thoughts on how we can get it started. Rand Simberg is a self-described "recovering aerospace engineer" whose weblog, Transterrestrial Musings, is one of the best sources on the web for lucid, insightful writing on developments in space technology and policy. Rand also writes for FOX News and Tech Central Station (and he covers a wide variety of topics, not just space.)

In the interview that follows, Rand and I discuss how and whether the space age got off track, and if so what we can do to get the future started in earnest.

I was talking with some folks the other night about the movie 2001: A Space Odyssey. When the movie was released in 1968, it seemed a reasonable projection of the future: a true space station, regular commercial flights to space, permanent lunar settlements, and exploratory missions to the outer planets, all within about 30 years. Here we are 35 years later, and most of those things seem more distant now than they did then. Whatever happened to our future in space?

It was based on a lot of false assumptions, foremost being that the government was going to make it happen. We believed the rhetoric about "not because it's easy, but because it's hard," and the new frontier, and thought that the government actually cared about this stuff. But even the myth that a visionary president can lead us to the stars, exemplified by the Kennedy worshipers, has been shown to be false — he never gave a damn about space.

The irony is that if we hadn't been derailed by Apollo, which had much more to do with waging the Cold War on a peaceful front, and industrializing the south, than space, we'd probably be a lot closer to the vision of 2001 today. The Air Force was flying into space with the X-15, and it's possible that we would have continued along that path, a much more natural one, and that might have spun off into the private sector. But instead, in our hurry to get to the moon, we chose the most expensive way to do it, and established it as the fundamental paradigm for spaceflight that haunts us to this day.

Now that a we have a little distance (very little) from the Columbia disaster and the Gehman report, what's your best guess as to the future of the space shuttle?

My best guess is that we'll fly it a few more years, at which point it will become clear to all, even people in the government, that the private sector is leading the way to a more sane human spaceflight industry, and just get NASA out of the earth-to-LEO business completely, except as a customer of services. That's certainly my hope.

What about the future of NASA itself? You've written that it might be time for the agency to be put to rest, or that it could (with some substantial changes) play a part in supporting the entrepreneurial efforts that will be required to truly push humanity into space. Which of the two scenarios do you consider more likely? And if NASA is going to carry on, what are the fundamental changes that you think the agency will have to make in order to do so?

Unfortunately, I don't consider either very likely, but one can always hope. I'm not sure there are any changes that you can make with it as an existing agency — there's simply too much bureaucratic inertia there. I find it ironic that Japan just merged their three space agencies into one, because I think that we should go in the opposite direction here. R&D should be split out completely from operations, assuming that there should even be an operational part of government civil space. A lot of things like the commercial development centers, to the degree that it should be done at all, might be better done out of the Department of Commerce.

When I interviewed Robert Zubrin a while back, he was worried about the end of the shuttle program — not because he's a fan of the orbiter, but because he doesn't want to see the heavy-lift-capable shuttle launch infrastructure go the way of the Saturn V. If the shuttle is completely scrapped, is there anything on the horizon that might provide the same kind of lift as the shuttle boosters or the Saturn V? If not, what does the foreseeable future of space exploration look like, with only relatively light launch capability at our disposal?

I think that heavy lift is highly overrated. If we get cheap launch with small vehicles, you'll see a lot of innovative thinking in terms of orbital assembly techniques and new design concepts for orbital infrastructure and vehicles that allow us to do without it. The perceived need for a heavy lifter is always one of the major showstoppers to doing anything ambitious, and it needn't be. It's a fundamental economics problem. Big vehicles really do cost a lot more up front than small vehicles, particularly in terms of the ground infrastructure, but the market for payloads that size is simply too small to justify them. I expect to see heavy lift come along after the market is developed sufficiently to take advantage of it, just as we didn't see a need for a 747 until the 707 and other smaller jets had established the market.

Of course, unlike Dr. Zubrin, I'm in no rush to get to Mars.

Arthur C. Clarke is famously quoted as saying that once you're in Earth orbit, you're half way to anywhere. One of the reasons that I'm not as excited about the X Prize as some is that the it is aimed at achieving sub-orbital flight objectives. Why is new sub-orbital technology important? What does it give us?

Well, actually, that was Bob Heinlein, not Clarke. New suborbital technology is important for a number of reasons. First of all, it provides an entry point for the private industry that's affordable to investors with a realistic ROI. Second, it will teach us a lot about developing and operating launchers on a routine, reusable, affordable basis. Third, it will blow up a lot of misconceptions about the true cost of this stuff, because I'm confident that the costs of the private folks will show up the conventional government/industry cost models as being out of whack by at least one, if not two orders of magnitude. Fourth, it will develop a market of wealthy space travelers who will be interested in the next step, and have the money to plow into developing it.

Yes, orbit is a lot tougher job than suborbit, but as the suborbits gradually get faster and higher, eventually they become orbits. The real key is that, as Jeff Greason of XCOR says, to learn to do orbit cheaply and reliably, you learn to do something cheaply and reliably, then gradually increase the performance, building on lessons learned. This is the opposite approach to NASA's, which has always been to design to the end performance goal, and then try to figure out how to make it cheap and operable (usually with insufficient development budget). That approach has never worked, and probably never will.

You've been an advocate of private development and implementation of space technology. Can you provide a scenario by which private interests could drive us towards settlement of the moon, the planets, and/or the asteroids? Why do you think such a scenario is more likely than an attempt to achieve these objectives via government programs?

Well, I'm a contrarian here. The conventional wisdom, based on history, is that places are first settled for extractive economic reasons, and that only after they've become settled and "civilized" do the tourists come. Similarly, people (particularly in the conventional space industry) assume that, if space tourism comes at all, it will only be after the cost of launch has been driven down, and safety has increased, by some magical new whiz-bang technology.

As is often the case, the conventional wisdom is not particularly wise. I think that they've got things on their head. Launch costs are high, and vehicles unreliable, not because we lack technology, but because we lack markets. We do so little spaceflight that we haven't learned how to do it well, and we don't have any economies of scale. The only obvious large market, that doesn't require other major technological advances (e.g., solar power satellites, Helium 3 fusion), is people who want to go and will pay for the service.

Those payloads are already built, the payload interface is very simple and straightforward (keester and seat) and there are many more being manufactured every day, with unskilled labor. Because the world is growing wealthier, with socialism being replaced by freedom in many places, and adventure travel as an industry is already large and growing, looking to history as a guide to the future is in this case mistaken.

On the other hand, we've seen the result of government programs for the last four and a half decades. There's neither will, nor any clear path for them to create space settlements. The only way that I can see the government developing serious spacefaring capability will be if we're imminently threatened by some celestial object.

Can you estimate whether and when you think each of the following will occur?
Expedition to Mars? Permanent settlement on the Moon? Commercial Space Flight ? Manned Mission to Jupiter or Saturn?

There will certainly be an expedition to Mars. I would predict within the next couple decades if done privately, much longer (and perhaps never) if done by anything resembling NASA in its current form.

Permanent settlement on the moon? Yes, and it will likely be a resort initially.

Commercial space flight already exists, in the form of the commercial launch industry, but if you mean human space flight, in the suborbital sense it should commence within two years. Orbital is probably five to eight years off.

I don't see a manned mission to the gas giants for several decades with conventional technology, though nanotech could accelerate that considerably.

Finally, what are the most significant issues right now that have to be addressed in order for any of the above to happen?

To some degree, they already are being addressed. We need a clear and manageable regulatory environment, and some intelligent government policy in general. The Outer Space Treaty, another relic of the Cold War, needs to be scrapped or modified to have more explicit mechanisms for the establishment of property rights, and we need to amend the Liability Convention of 1972 to reduce liability risk for investors. But the most important barrier to date has been the inability to raise money. X-Prize is going to open up some peoples' eyes, and investors are now starting to take this sector seriously. They'll do so even more when someone gets rich by investing in an XCOR or Space-X. The other encouraging thing is that the dotcommers are getting interested, and turning to this new challenge. It would help a lot of NASA administrators would stop saying how difficult/impossible this is, but that's probably an unrealistic hope, since that's how they justify their budgets. I hope that in the future people will pay increasing less attention to them. The barriers are red tape and public perception. Let's tackle those, which is one of the reasons that I have my blog.


Rand Simberg also recently took on our Seven Questions About the Future.

Also see Speaking of the Future with...

Nina Paley | Phil Bowermaster | Michael Anissimov | Ramona | Robert Zubrin | Alex Lightman | Aubrey de Grey

Posted by Phil at 07:37 AM | Comments (1) | TrackBack

October 16, 2003

An Animated Discussion

Speaking of the Future with Nina Paley

One of the distinguishing characteristics of what I have dubbed serious optimism is the requirement that we deal substantively with objections to projected positive outcomes. "Cheap" optimism makes no such requirement. Disciples of Dr. Pangloss insist that all outcomes are positive, even optimal, by definition, while Pollyanna's brothers and sisters insist that every setback leads inevitably to an even happier ending than was originally expected.

Serious optimists can't allow themselves to indulge in these fantasies. Any sought-after positive outcome is one possibility among many. Like the hero of a Greek tragedy, the tomorrow we seek most earnestly may carry within it the seeds of its own destruction.

Consider MacBeth (not Greek, but a good example of a tragic hero.) The Weird Sisters tell him that he will be king, that he will hold power until a forest marches across the land, and further that no "man born of woman" can ever harm him. This all sounds pretty good: he gets to be king, and there doesn't seem to be any way anyone can hurt him.

To kind of kickstart the process, he and the little Lady commit a fairly gruesome act of regicide right in their own house. Taking the crown in such a barbaric manner is not well-received by MacBeth's fellow nobles, so they put an army together and come after him. The soldiers employ a crude form of camouflage, covering themselves with tree branches (taken from the very forest the Weird Sisters mentioned) as they make their way towards MacBeth. Our hero ends up in a sword fight with his enemy, MacDuff, whom he learns a little too late was delivered via caesarian — and was thus (technically) never "born of woman."

The serious optimist must do what MacBeth could not, anticipate the catastrophes that may paradoxically result from going after some good aim in the wrong way. A cynic can achieve apparent prescience by speaking with delphic ambiguity (and therefore always be "right" no matter how things work out), but this is of no help to those who earnestly pursue a specific outcome. The serious optimist has to embrace multiple possibilities, outcomes both positive and negative, in order to formulate scenarios that transcend the pairs of opposites. It's no coincidence, for example, that the same guy who coined the term nanotechnology also introduced us to the idea of gray goo.

In an effort to transcend simple pairs of opposites, to embrace risks and dangers as well as rewards, I have actively sought individuals with outlooks distinctly different from my own for the Speaking of the Future interviews. Although I may have points of disagreement with any and all of the people I've interviewed up to this point, I share a common philosophical orientation with all of them.

Not so with today's guest.

Filmmaker and cartoonist Nina Paley has agreed to be the first participant in a planned subset of these interviews, what I have facetiously referred to as the "Buzzkill of the Month." (Since this is the first such interview I've published, it would probably make more sense to call it the "Buzzkill of the Quarter," but I do intend to do them more often and, besides, that name just isn't as funny.) Having completed the interview with her, and having already published her answers to the Seven Questions, I've come to the conclusion that Nina is probably not a very good candidate for the position of Buzzkill.

She's just too lively and interesting to be any good at it.

However, in spite of her shortcomings, I've decided to go ahead and run the interview. In our recent cyber dialog, Nina and I talked about overpopulation, biodiversity, and the Voluntary Human Extinction Movement. Nina sets me straight on Escher and takes issue with my use of the term "anti-humanist." And while I strongly disagree with her assertion that anything these creeps do might be described as having "artistic merit," overall I find that Nina sketches out an intriguing alternative role to that of the serious optimist: the interested observer of interesting times.

These certainly are interesting times, all the more so from having folks like Nina living within them.

Nina, I really enjoyed your short film, The Stork. Living in one of Denverís biggest suburbs, I resonated with the images of tract housing and SUVs piling up on each other in the wake of the bombs the Stork was dropping. How did you come up with the idea for The Stork, and how has it been received?

Thanks! The idea for The Stork came out of a conversation. Iíd seen a lot of those illustrations of storks for new parents — cards, signs in front of peoplesí houses, "stork parking" — and I joked that the "bundle of joy" the Stork is carrying is really a bomb. Then a friend of mine added, "yeah, and instead of leaving craters in its wake, it leaves new subdivisions."

The filmís been received remarkably well. It was invited to Sundance last year, and it just won a prize in the EarthVision Environmental Film Festival in Santa Cruz. I thought it would anger and confuse people, but most viewers seem to get it, even if they donít agree with it.

I made a few other shorts about overpopulation along with the Stork: Fertco and the Wit & Wisdom of Cancer. Those films kind of exorcised my demons. I used to get into heated arguments about population; now I donít. The films speak much more eloquently and concisely than I do, and the fact that theyíre animated makes them go down easier. My anger went into those films, and now Iím much calmer and can get on with my life. So as therapy, The Stork and its companions were a raging success.

Itís interesting that you choose the image of an archetypal Gerber Baby — with blonde hair, blue eyes, a sweet smile, etc. — as the culprit. But if the filmís message is about overpopulation, why aren't those little brown bundles that the Stork is dropping? In the West (where the blonde babies come from) the birth rate has dropped dramatically over the past 50 years. Even in the US, where the population continues to grow, the rate is considerably less than in much of the third world.

Thereís an equation used by population activists: I = PAT. Impact = Population x Affluence x Technology. The Stork is about population in the affluent West, where consumption and pollution are 20 to 40 times the rest of the worldís. The point I tried to make is that every new First World consumer has a huge impact on the environment.

Thereís a little-known paper written by Dr. Charles Hall of the State University of New York, called "The Environmental Consequences of Having a Baby in the United States." He actually measured how many barrels of oil, how many hectares of forest, how many cows and chickens and pigs, each new American will consume in their lifetime. Meanwhile environmental groups urge us to "save a tree," save this, save that ó but saving a tree is like pissing in the ocean when we destroy dozens of trees just by living an American lifestyle.

Speaking of which, I know many Americans who delude themselves into believing they donít really live an American lifestyle, because they (like me) recycle or donít drive or donít eat meat. But the "savings" inherent in those choices pale in comparison to what impact we do have, just living here. A car-free vegetarian in India has a fraction of the impact of a car-free vegetarian in the US, because of social circumstances beyond our control. For example, food in the US travels hundreds of miles by truck, is over-packaged, and comes from unsustainable agriculture. So an order of rice and curry in the US has many times the impact of the same meal in India, where food is grown locally and served in a banana leaf and an old newspaper, instead of a styrofoam clamshell in a paper bag in another plastic bag with plastic forks and extra napkins. But I digress.

My point is that as the biggest per capita consumers and polluters on the planet, every new American has a huge environmental impact. Add to that the choices many parents make, of moving to the suburbs and buying larger cars and SUVs, and disposable diapers for their offspring, and it all adds up to The Stork.

If, on the other hand, your subject was consumerism rather than population, why blame the babies? Itís adults, after all, who build the tract housing and drive the SUVs.

I donít blame babies. I blame their parents. At the very end of the credits thereís a childís voice saying, "I donít want to!" followed by the harsh shriek of a hawk, which represents the Stork. Babies donít make any of these decisions, including the decision to be conceived in the first place.

Thereís no question that the culture of child-rearing can be overbearing, especially for those who have decided not to be a part of it. I personally find it disturbing when I meet adults who describe raising their children as "the meaning of life" or who seem to have completely subsumed their own identities in the pursuit of bringing up their children. But what I read on your site, along with some of the sites youíre linked to via the Childfree Ring, seems to go well beyond simple disagreement or opposition to this culture. You use epithets to describe children ("kidlets," "baybees," "bag-o-sprog,") and openly accuse their "breeder" parents of being stupid, irresponsible, and dishonest. One "humor" site in the Childfree Ring includes a cartoon showing a man smashing babies with a sledge hammer to make baby oil, with an interactive feature that allows readers who are so inclined to help smash the babies. Canít people be opposed to having children without being so strident (and often downright nasty) about it?

Please donít hold me responsible for the Childfree Ring! A lot of these people are nuts. Others arenít nuts, but are ranting in anger, as I did on my own site. Thatís why the page says "rants." But you raise a good point Ė if I want serious attention for my project, I should probably remove the more provocative rants. Politics.

I really have nothing against babies and children. Some of my favorite people are children. Babies Iím simply not attracted to, and the constant expectation that as a woman Iíll be delighted by some strangerís baby wears me down. Again, itís parents I have more of a problem with, although I count many parents among my friends, and all of my immediate family. Most members of the "Childfree Movement" are outraged by bad parents, people who neglect or abuse their children, and expect the "Village" to cover for them. Iím not really a spokesperson for the CF movement, and The Stork isnít a film specifically for or about that movement. Itís a film about human impact on the environment.

Iím pleased to see the Childfree movement growing, though. In my more obnoxious zealous days, I tried to convince people not to have children for the sake of the environment. Then I discovered the CF movement, people who just didnít want to have kids for any number of reasons. Instead of convincing people who do want kids not to have them, I realized I should help make it possible for people who donít want them to not have them. Then everybodyís happy, and no oneís making a "sacrifice." Thereís nothing worse than someone who intentionally creates more humans and considers it a sacrifice; that burdenís especially heavy for their kids, who are raised with excessive guilt and resentment. The CF movement says, if you donít want Ďem, donít have Ďem. If you have Ďem, make sure you want Ďem, and take responsibility for your choice.

Some of the more extreme groups that you link to on your site are the Church of Euthanasia and the Voluntary Human Extinction Movement. The latter group makes the pitch that we should eliminate the human species completely in the interests of biodiversity. They appear to be serious. Do you identify yourself as a member of this movement? If so, can you explain how you reconcile being an artist, a proponent of the humanities, with membership in an anti-humanist movement?

VHEMT appeals to me in large part because of its humor. It takes an obvious idea to its logical end. The only means of human extinction advocated by VHEMT is voluntary non-reproduction, a strategy with exactly two chances of success: "slim and none." It stuns me that people donít recognize, let alone enjoy the overt absurdism in VHEMT and the Church of Euthanasia.

As for being an artist, a "proponent of the humanities" ó VHEMT and the Church of Euthanasia are art. The CofE especially ó it was founded by artists, and its main activity is performance art, street theater. It has an environmental message, but it exists to communicate ideas to, and entertain, humans. The CofE is a modern descendant of the Dada movement, which was equally misunderstood in its day.

Iíve never called myself an "anti-humanist," but as long as weíre on the subjectÖ. I donít know exactly what people mean by anti-humanism. I suspect anti-humanism isnít against humans, but rather against the philosophy known as Humanism, which arose in response to the European Christian worldview that placed God in the center of the Universe, and man in a subordinate position. Humanism placed Man in the center of the Universe. Anti-humanism, I think, simply says Man is not the center of the Universe; that humans are part of an interconnected web of life, that we need biodiversity but biodiversity certainly doesnít need us. Maybe a more accurate term would be Post-humanism. I think this philosophy is also called "Deep Ecology."

What are your thoughts on the relationship between economic development and population growth? Itís been widely asserted that, as a nationís economy grows, its rate of population growth slows. A good example of this is India, where the population growth rate has slowed almost to zero in the four southern states. India has benefited tremendously in recent years from its participation in the global information technology marketplace, which has contributed to this change in population dynamics. I know from reading your web site that youíre an outspoken critic of globalization. But if globalization contributes to raising standards of living and lowering population growth rates, why oppose it?

I = PAT. Itís not just population, itís consumption times population. Lowered birth rates donít mean lowered environmental impact if consumption and pollution increase. And they are increasing in India, far more rapidly than the birth rate is decreasing. Furthermore, a decline in birth rate doesnít mean a decline in population. The birth rate must drop to below replacement for population to decline. People talk about "slower growth", but growth is growth. Any growth rate above zero translates to exponential growth. Just because something is growing less fast this year than last year, doesnít mean itís not growing.

I spent last Summer in Kerala, India. That experience really took the wind out of my sails. Theyíre dealing with huge environmental problems in India, things as simple as garbage removal. Garbage in Kerala was traditionally biodegradable; you could just chuck it in the back yard or on the street and it would compost itself. Now they have plastic bags mixed in with the garbage, and the results are disastrous. It piles up in the streets, stinks, and attracts vermin. Now it needs to be trucked away to landfills (where will they put the landfills?) and thereís simply no infrastructure to handle the increasing amounts of garbage piling up. The garbage is a by-product of economic prosperity. Having seen life there first-hand, who am I to fault Indians for wanting economic prosperity? They want computers, they want cell phones, they want electricity to run 24 hours a day. They want stuff to work like it does in the US. And I donít blame them Ė I want that stuff too, and Iím glad I have it. So you have what humans want vs. what the rest of life on Earth needs to survive. And these forces seem to be totally at odds with each other. And I no longer think I have any answers. Now Iím just sitting back and watching events unfold like a big show.

If your objection to economic development is that it brings about higher levels of unsustainable consumption of resources, what are your thoughts on emerging technologies that are expected to simultaneously increase material production and make the environment cleaner? Many of those who are optimistic about the future share the concerns of the Green and Sustainable Growth movements, but disgaree with the proponents of these movements on the question of how these problems should be addressed. Christine Peterson, the President of the Foresight Institute, has said that she is motivated by "a desire to help Earth's environment and traditional human communities avoid harm and instead benefit from expected dramatic advances in technology." Christine's views are shared by many of the folks involved in developing these new technologies. What if we could produce more, more cheaply, without the negative impact on the environment and, in fact, begin to correct much of the damage that's been done to the environment?

Hey, sounds great to me. You wonít convince me of anything, but I donít need to be convinced; Iím just watching the show.

Technology has solved all our problems so far. Itís just that itís created new problems we couldnít foresee. Cities used to have the terrible problem of horse shit all over the streets. The Horseless Carriage solved that problem. Now we have suburban sprawl, loss of public space, pedestrian deaths, obesity, air pollution, and oil dependence.

Whether Iím cynical about technology or optimistic doesnít matter. Technology is part of the unfolding drama, and itís interesting to watch. Really, the best I can do to try to make the future brighter is simply not reproduce. In my opinion, thatís the best any of us can do, but thatís just my opinion. People will do what they will do, whether thatís breed like rabbits or have just one kid or no kids or solve problems with technology or make art or start wars or whatever. Iím just one person, out of 6.5 billion, living in "interesting times."

Letís switch back to your movies. I love Fetch!. Iíve watched it repeatedly. Itís like an Escher painting come to life. In fact, if Iím not mistaken, the dog and its owner run through some of Escherís work

You are indeed mistaken; the optical illusions in the film are based on the "three-pronged blivet," which never made its way into Escherís work, as far as I know. The "impossible box" toward the end is the only truly Escheresque scene in the film, but that design pre-dates Escher. Iíve given up on the distinction, though, and just write "Escheresque" in the festival entry forms, because people associate Escher with all optical illusions.

The film is obviously informed by a sense of play, but it seems to touch on some profound ideas about shifting perspectives and the somewhat malleable nature of reality. I get into some of that kind of stuff myself from time to time. So tell us...is Fetch! a philosophical treatise, or were you just having fun making a cartoon?

Fetch! was inspired by philosophical pondering on the malleable nature of reality. You know, "that horizon is actually a wall! Wait a minute Ė itís just a line. Why do I think a straight line is anything other than a straight line? What is real, anyway?Ö" That kind of thing. Fortunately, I made it kind of cute, so the result is watchable, even by my friendís 4-year-old. Fetch! has done well in childrenís film festivals. Kids are a tough audience, so I consider it an honor when they like my work.

Pandorama is another short film combines evocative images, a sense of fun, and serious (in this case, mythic) themes. You employed an unusual technique in making that one, drawing directly onto 70mm film. Youíve also used that technique on at least one other film. How does that technique compare to the animation techniques you used in making Fetch or The Stork? Which do you prefer?

Drawing on film is about as low-tech as you can get. You make every image by hand, unmediated. Fetch! and The Stork were created digitally, relying on high technology; the art is all virtual, untouched by human hands. I enjoy both techniques. I do more stuff digitally now because itís faster and cheaper, but working by hand is exciting because itís so real.

What can you tell us about your latest project, Thank You for Not Breeding?

Thank You for Not Breeding is on the back burner right now. I completed 4 animated shorts about population and the environment, and planned to fold them into a documentary about fringe groups like VHEMT and the CofE, but I put that project on hold last Summer when I went to India. My current project is actually called The Sitayana, based on the Indian myth the Ramayana, or Story of Rama. The Sitayana, or Story of Sita, is about Ramaís wife. Iíll have a web site for it up soon.

What kinds of projects do you hope to be taking on in the future? Do you think you might ever be persuaded to do a film about i Space or Practical Time Travel?

If someone gives me a free Time Vacation, Iíll make a film about it, sure. Actually, visiting India was like Time Travel, and a little like going to another planet.  

Posted by Phil at 06:09 AM | Comments (4) | TrackBack

October 02, 2003

The Best of Speaking of the Future

Hey, if NBC can run a show called "the Best of Chris Katan" the week before the season premier of Saturday Night Live, I can definitely get away with this.

I've been Speaking of the Future with some of the most fascinating people in the world for two months now. Here are a few highlights from those discussions.


Aubrey de Grey

What's your response to those who claim that finding a cure for aging is in some way irresponsible or immoral? A number of years ago, the former governor of my home state of Colorado, a fellow by the name of Dick Lamm, made a speech that was to haunt the remainder of his political career. In it, he told his audience that "We have a duty to die" in order to get out of the way, make room for the coming generations, not use more than our share of resources, and so forth. He was talking primarily about heroic lifesaving efforts such as keeping an individual who has had a massive stroke on life support, spending resources and effort on prolonging their life even when there is little or no chance of recovery. His words were widely misquoted as "You have a duty to die," and he became something of a pariah, especially among seniors who didn't take kindly to being told that they should drop dead for the benefit of the kids. But I wonder if there isn't a notion of a "duty to die" lurking in the background of various green movements or in the sustainable growth meme.

I think there probably is, yes. But the deeper question is, why do people find that sort of thinking attractive? I think the only reason is denial: people know they can't escape aging, so they find ways to convince themselves that it's okay not to escape it. When people cease to "know" that aging is inevitable, this whole way of thinking will vanish overnight. As for my response to such people, well, my favorite one is to ask exactly what age the person thinks is the optimal life expectancy for humans, and why that age is better than ten years longer. I've never heard good replies to that one. A similar question is whether the person approves or disapproves of research to delay the age at which people get heart disease, cancer, Alzheimer's etc. When they realize that therapies which do that will also, inexorably, extend lifespan, they have to propose that there's some age of onset of those diseases beyond which it ceases to be a good idea to delay them further.


Alex Lightman

So when do you think the big bang will get here?

We are living in the big bang right now. 1.3 billion mobile phone users and 660 million Internet users, vs. 750 million cars, trucks and buses. The digital big bang is the most important experience of this era in human history, though it will take a future Alvin Toffler or Edward Gibbons to point it out in manner that most educated people will understand. Only, by then, the definition of 'educated person' will have gone from millions of people to billions of people! What a fun, complex world that will be to live in.


Robert Zubrin

How about permanent settlement elsewhere in the solar system? And where you think that would be?

Well, you could establish a settlement on the Moon, but it wouldn't be anywhere near as self-sufficient as one on Mars.

Because of the lack of resources there?

Yes. And then similarly in the near asteroids, and eventually the main-belt asteroids. Mars is not the final destination, but it is the direction. It's where we establish our first new branch of humanity in space as a space-faring species. And if we do it, that in itself will develop our capabilities. The first people that go to Mars are going to go in chemically propelled spacecraft. They're going to make the passage in cramped and uncomfortable quarters. The grandchildren of the first Martian immigrants will find it difficult to credit the story that their grandparents tell about how long it took. Because they'll be traveling in fusion-powered spacecraft which can do it in three weeks in great comfort.

Once there is a branch of human civilization on Mars, we have the incentive to develop more of the technologies that will allow us to make the transit routine. Columbus fared the Atlantic in ships that even a generation later no one would have attempted to the Atlantic in. Because until there was transatlantic transportation, there was no need to develop transatlantic-capable ships. But after Columbus came a trans-oceanic civilization and your three-masted sailing ships, your clipper ships, your steamers, your ocean liners, your Boeing 747’s all followed in turn. But the same technology that makes the transfer to Mars routine, will also make it possible for more daring people to take much greater steps. If you can get to Mars in three weeks, you can get to the Moons of Saturn in a few months. Perhaps even attempt interstellar voyages within a few decades.


Ramona

The present is the future relative to the past. What's the best thing about living in the future?

I like chatting with people online.

What's the biggest disappointment?

I do not know what biggest disappointment is. Alright. What drugs do you take?


Michael Anissimov

While Aubrey de Grey talks about adding a few centuries to his life so that he can get caught up on his reading, enjoy more time with his loved ones, and perhaps get in a few more games of Othello, Eliezer Yudkowsky is busy working out an advanced Theory of Fun that will allow us to find pleasure in a life that spans millions or possibly even billions of years. What is your take on the question of whether boredom will eventually kick in if we live indefinitely? Is there an escape clause somewhere in your organization’s repudiation of involuntary death?

Given complete control over the structure and function of our own minds, I can easily imagine a scenario where boredom gets wiped out, never to return again. The question is whether this would be the “philosophically acceptable” thing to do or not. In “Singularity Fun Theory”, Eliezer Yudkowsky argues that “Fun Space” probably increases exponentially with a linear increase in intelligence, and I’d tend to agree. So we wouldn’t have to turn ourselves into excited freaks in order to have an unlimited amount of fun. Superintelligence, nanotechnology, and uploading should produce enough interesting experiences to keep many of us enjoying ourselves forever, and there are probably millions or billions of new technologies and experiences in store for us once we acquire the intelligence to invent and implement them. It’s hard for us to say anything really specific about the nature of these technologies at the moment – that would be sort of like a fish in the Cambrian era trying to predict what human beings would do for fun. One thing is for sure; we’re eventually going to need to become more than human in order to enjoy all that reality has to offer.


Phil Bowermaster

If someone visited you from the future, what would you want them to say was the best thing you did to affect their lives, what was the worst thing and what would they wish you had done?

That’s a tough one. I think I would want them to say that the best thing that I’ve done is to imagine a bright future, share that vision with others, and try to make it happen. The worst thing is that I’ve waited so long before seriously trying to do it. I can’t say what they would wish I had done. One of the great tricks to life is trying to figure out what you’re doing now that later you’ll wish you hadn’t done, what you’re not doing that you’ll wish you had done, and what you’re doing that you’ll wish you had done differently. I haven’t entirely mastered this trick, but I’m working on it.

 

Over the next few weeks, we'll be publishing (among others) interviews with the John Smart of the Institute for Accelerating Change, filmmaker Nina Paley, and Foresight Institute president Christine Peterson. So stay tuned.

Posted by Phil at 05:46 AM | Comments (0) | TrackBack

September 25, 2003

Now Who's Asking the Questions?

Speaking of the Future with the Speculist

The FastForward Posse is a loose confederation of futurists who contribute to our occasional internal blogwave on a subject of interest. So far, weíve done FastForwards on life extension, ubiquitous computing, Mars, and artificial intelligence. The ringleaders are a subset of the posse who either helped me get The Speculist going in the first place, or who have made sufficient contributions to FastForward and to the other features such that I feel perfectly comfortable dashing them off e-mails and asking them to do even more.

Which leads me to this weekís interview.

Having so glibly delivered what I considered to be challenging and thought-provoking questions in the various interviews Iíve conducted, itís only fair that I should be on the receiving end of a few. The FastForward Posse ringleaders were more than happy to oblige. The following includes my answers to some of their questions. We may do a few more of them somewhere down the road. Anyway, as a member of the gang so appropriately put it...

Now whoís asking the questions, smart guy?


If you could go back in time to change a single act that would have the greatest effect on todayís world, what would it be, and how would you go about changing it?

This question would be great addition to the Seven Questions About the Future. Maybe weíll do an addendum, A Question About What Might Have Been.

Iím reminded of L. Sprague de Campís novel, Lest Darkness Fall, in which a modern-day engineer awakens in the 5th century and decides to prevent the impending dark ages. Of course, to pull that off, he has to rely on his excellent knowledge of history and introduce several technological and social changes. He canít do it with a single change. Interestingly, towards the end of the book, he writes a letter either to the Pope or the Emperor (I canít remember which) warning of a soon-to-arrive heretical religious leader, Mohammed, whom he recommends nipping in the bud. Thatís a good example of making a single change that would have a huge impact.

Not that thatís the change I would make.

Iím no historian, so standard disclaimers apply. But if I could go back, I would prevent that Serb separatist from assassinating Archduke Ferdinand. All the horrors of the twentieth century originated with that act. Thereís no guarantee that World War I wouldnít have started shortly thereafter anyway, but itís the only single act I can think of that might have prevented it. Letís suppose for a moment that it truly never did happen. If World War I never happened, maybe the communists would not have achieved the upper hand in the Russian Revolution. Millions of lives lost under Stalin would be saved, hundreds of millions of individuals around the world would be spared the degradation and brutality of life in a totalitarian regime. With no World War I, there would have been no Treaty of Versailles, no humiliated Germany, no climate in which Hitler could come to power. Tens of millions more lives would be spared, both the casualties of World War II and the victims of Hitlerís genocide. Without the Ottoman Empire taking the "wrong" side in World War I, there would have been no post-war divvying up of the Middle East. Itís hard to say how things would look there now (particularly the Arab world), but it is just possible that politicized Islamic Fundamentalism and pan- Arab nationalism might never have taken off.

It's probably true that the horrors warded off by preventing World War I would simply have been replaced by other horrors. But I would give it a shot, anyway.


What is the most effective way for a visionary or group of visionaries to guide change in the current environment? (Some choices: ĎVoice in the wilderness" hair-shirt prophecy, Illuminated conspiracy, recruitment and political advocacy, showdown debate, etc.)

I donít know whatís most effective, but Iíve observed a tendency on the part of visionary organizations to be very institutionally focused. Donít get me wrong, itís tremendously important to have that focus. But most people live lives that are far removed from the halls of government or academia, and are perfectly happy with that.

As voters, we have a civic obligation to know the issues and understand the process. But the folks who make the political campaign ads will tell you that itís the issues, and only a small subset of those, that people care about. By and large, people donít care about the process. The process is not interesting. The inner workings of bureaucracy are not interesting. In fact, you can take an inherently interesting topic and make it much less interesting simply by adding the word "policy."

Think about it. Space travel is an interesting subject. Space travel policy much less so. I mean, which would you rather do: watch a football game, or listen in on some NFL officials talking about possible tweaks to the Instant Replay rule?

I was in a discussion with a group of futurists a while back and we were talking about how the group could get its message out better. Every single one of them came up with ideas that had to do with reaching out to the local academic community. Thatís not terribly surprising; they all work and live in that world. When I suggested that we need to think of ways to get the message out to the broader public, they were stumped ó and not because they couldnít think of ways to get the message out there. What stumped them was why they would even want to try to reach the general public.

"What does Joe Six-Pack care?" one of them asked me.

These were smart, wonderful folks, but they just couldnít quite get their heads around the idea that the kinds of changes they advocate are going to have an impact on society in general.

The answer to the Joe Six-Pack question is found in the Bible, Proverbs 29:18

Where there is no vision, the people perish.

And that vision has to belong to the people, not just the bureaucrats and academics. If we want to guide changes in the current environment, we must get the publicís attention concerning the benefits and/or risks of what weíre talking about. A successful visionary is one whose message touches the popular imagination.


Is the concept of intellectual property an overall help or hindrance to visionary progress? Why or why not?

Overall, the concept of intellectual property helps. It ensures that there is wealth to be generated through the development of intellectual assets. Markets can thus fuel innovation.

I do think that intellectual property law should be modified along the lines recommended by Lawrence Lessig. Copyrights and patents should ensure that the developer of an intellectual asset can profit for his or her work. Itís reasonable to define a period during which the creator has the exclusive right to benefit from the asset. Whatís unreasonable is to define that period as forever. At some point, these assets should be available to anyone who wants to use them. Or in the case of patents, maybe it would be better to say that they should be available to anyone willing to pay to use them.

There should definitely be an expiration date on copyrights. Disney is currently pushing US law to allow perpetual corporate copyrights. This is a very bad idea. Back when it was still okay to talk in these kinds of terms (i.e., when I was an undergraduate), we used to describe the Western tradition as the Great Conversation. Homer gives us the Iliad; centuries later, Virgil writes the Aeniad; centuries after that, Dante writes the Divine Comedy; then finally Milton writes Paradise Lost.

If perpetual copyright was in effect and in force throughout history, the conversation would have stopped with Homer. Virgil would never have been allowed to publish his "unauthorized sequel" to the Iliad. And Shakespeare wouldnít have been able to write much of anything heís famous for. Hamlet? Romeo and Juliet? Forget it. Even the history plays were freely adapted from the works of others without attribution.


What are the top three technologies or lines of inquiry that, if given sufficient attention in the immediate term (not more than five years), would most advance overall human progress? (i.e. where are the nascent breakthroughs?)

Five years? Criminy, thatís too close. Futurists like to talk about how things will be 100, 50, even 25 years from now. Really gutsy folks like Ray Kurzweil and Aubrey de Grey will make 10-year predictions. But five? Or less?

Iím going to dodge this question just slightly. Iíll take a stab at what I think might happen in these areas over the next few years, rather than what we could do if we lined everything up right. Okay, here goes nothing.

  1. Anti-aging Research

    It wonít be long before the Baby Boomers start hearing footsteps. If we make significant strides towards Aubrey de Greyís Engineered Negligible Senescence over the next five years, it will have the effect of holding back a tremendous swell of interest in cryonics which would otherwise emerge. So itís all good. Either Aubrey gets us pointed towards the fountain of youth, or the Boomers get so nervous that they pour bazillions of dollars into cryonics, pushing that field along nicely.

  2. Nanotechnology

    Interest in this field is going to escalate geometrically over the next five years, and itís going to receive a lot of financial attention. We can expect a number of small breakthroughs over that time, as well as the emergence of a consensus as to what the Big Goal (or goals) should be.

  3. Artificial Intelligence

    I donít know how far this field will advance over the next five years, but I expect there will be a tremendous surge in popular interest in the subject. Concepts like AI avatars that accompany us and work for us, the uploading of human personality, and the Technology Singularity will all enter the popular consciousness the way human cloning did in the late 1970ís. The lines will begin to be drawn (as they were back then for cloning) for and against these ideas.

    Getting back to my answer to the earlier question, the time is now to get positive and realistic pictures of what these developments might mean into the public eye. And that goes for nanotechnology and anti-aging research as well as artificial intelligence. In the future (to start yet another sentence with my favorite phrase), I think the biggest political division ó maybe the only one that will really count ó will between those who favor technological development and a new class of Luddites who want to hold it back.

  4. Space Travel

    (I know I was supposed to stop at three. Sue me.)

    Serious business applications will begin to emerge for sub-orbital launch technology, which is going to be a growth industry. One of the Big Goals for nanotechnology might well be the Space Elevator, in which case serious work on it might begin.

If someone visited you from the future, what would you want them to say was the best thing you did to affect their lives, what was the worst thing and what would they wish you had done?

Thatís a tough one. I think I would want them to say that the best thing that Iíve done is to imagine a bright future, share that vision with others, and try to make it happen. The worst thing is that Iíve waited so long before seriously trying to do it. I canít say what they would wish I had done. One of the great tricks to life is trying to figure out what youíre doing now that later youíll wish you hadnít done, what youíre not doing that youíll wish you had done, and what youíre doing that youíll wish you had done differently. I havenít entirely mastered this trick, but Iím working on it.

Posted by Phil at 12:55 PM | Comments (0) | TrackBack

September 11, 2003

Happily Ever After

Speaking of the Future with Michael Anissimov

The title I've chosen for today's interview would be a hard one to support on any day, but on a piece dated September 11, it seems particularly audacious. I think some folks will read this and assume I'm being ironic. And if I'm not being ironic, then surely some will want to drop me a line to help set me straight.

Happily ever after is a toy for children, after all, and possibly the delusional. It isn't a notion that adults in their right minds bother with.

If you want to read a good hard-nosed rebuke to the fairy-tale notion of happily ever after, no one delivers it better than Anne Sexton in her wonderful poetic treatment of Cinderella:

You always read about it:
the plumber with the twelve children
who wins the Irish Sweepstakes.
From toilets to riches.
That story.

Or the nursemaid,
some luscious sweet from Denmark
who captures the oldest son's heart.
from diapers to Dior.
That story.

Or a milkman who serves the wealthy,
eggs, cream, butter, yogurt, milk,
the white truck like an ambulance
who goes into real estate
and makes a pile.
From homogenized to martinis at lunch.

Or the charwoman
who is on the bus when it cracks up
and collects enough from the insurance.
From mops to Bonwit Teller.
That story.

After this prelude, Sexton lays out a devastating retelling of the Cinderella story. This is not Disney or Rogers and Hammerstein pablum, but rather the Brothers Grimm version, complete with body parts lopped off and eyes gouged out. I'm not kidding. Read it.

Sexton wraps up her telling of the story with this assessment:

Cinderella and the prince
lived, they say, happily ever after,
like two dolls in a museum case
never bothered by diapers or dust,
never arguing over the timing of an egg,
never telling the same story twice,
never getting a middle-aged spread,
their darling smiles pasted on for eternity.
Regular Bobbsey Twins.
That story.

That story.

Sexton doesn't need to say anything to discredit the idea of happily ever after; its illegitimacy is assumed. We can toy with this nonsense if we like, so long as we remember that it's fantasy. The plumber who wins the Irish sweepstakes is somebody else. He's not us, just as Cinderella and the Prince are not us. They live in a world where things work out not only well, but better than hoped. Theirs is a happiness that can't be touched by diapers or dust, or by a middle-aged spread. This is the happiness of Pollyana or Candide, and it has no place in our world.

Anne Sexton lashes out at the fairy tale ending for reasons that are more personal, but no less intense, than those that motivated Voltaire to take on the notion of "the best of all possible worlds." While Voltaire juxtaposed the facile equivocation of Philosophical Optimism against the tragedy of the Lisbon earthquake, Sexton contrasts the rosy images of human happiness conjured by fantasy (and often heavily reinforced by society) with the banality, decay, and, all too often, despair of everyday life.

In an introduction to an earlier interview in this series, I wrote about what I call serious optimism. Serious optimism does not begin with metaphysical precepts, nor with expectations of what human happiness should be. It begins with realistic, grounded extrapolations of the possible. Guiding us to positive outcomes, some of which we have always hoped for, some that we have never even imagined, serious optimism can serve as an alternative both to the classical cynicism that became Voltaire's legacy and to the modern/postmodern despair that eventually led Sexton to commit suicide. Technology, not philosophy, is the substrate of serious optimism; however, there is a philosophy that informs and enriches it.

That philosophy is called transhumanism. Transhumanism provides glimpses of a new happily ever after, which is neither an obstinate recasting of the world around us into the "best of all possible worlds" nor a tired retelling of that story. Instead, this new happily ever after is predicated on the idea that the future can be — will be — fundamentally different from the past and the present, that our ability to choose and define our own happiness is expanding exponentially, that the human adventure is only beginning.

Michael Anissimov is a transhumanist. He's an advocate of the ethical expansion of the human experience into new realms, and a serious scholar of the risks and pitfalls the coming age may bring. Michael is a Director with the Immortality Institute, a transhumanist organization dedicated to facilitating extreme life extension. In the interview that follows, Michael talks about living forever, Super Intelligences, and why it's so hard to say what we might be doing for fun a billion years hence.

Michael, the Immortality Institute states on its Website that its mission “is to conquer the blight of involuntary death.” Isn’t involuntary death a vital part of the evolutionary processes that brought us where we are? How can you describe it as a ‘blight?’

Involuntary death is a cornerstone of biological evolution, but that fact does not make it a good thing, in the same way that someone giving birth to you does not necessarily mean they are a good person. Unfortunately, there are mothers out there that neglect or harm their children. Evolution, the process that produced humanity, possesses only one goal; create gene machines maximally capable of producing copies of themselves. In retrospect, this is the only way complex structures such as life could possibly arise in an unintelligent universe. But this goal often comes into conflict with human interests, causing death, suffering, and short lifespans. The past progress of humanity has been a history of shattering evolutionary constraints; our lifespans today are two to three times what they were thousands of years ago, modern medicine has rendered natural selection moot, and global literacy has enhanced man’s innate ability to process and distribute information. Immortalists suggest taking the next step, eliminating unwelcome instances of death, and replacing the careless and cruel process of evolution with compassionate, human-guided biotechnological and nanotechnological improvements.

I recently asked Aubrey de Grey whether his research would lead us towards living forever. He responded as follows: “Well, clearly there will always be the risk of death from causes that have nothing to do with aging, so ‘forever’ seems unlikely.” Would you agree with Aubrey’s assessment or do you believe that living forever (as the word immortality implies) is achievable?

I agree with Aubrey completely. It’s hard to say whether the laws of physics will ever allow true immortality. Immortality is probably not something that can be achieved with 100% confidence – making immortalism a philosophy of life rather than an engineering goal. It should also be said that immortalism doesn't solely focus on removing aging, but all causes of undesired death. Aubrey’s research, if it comes to fruition, would only solve a piece of the problem. Part of the reason we’ve called ourselves “The Immortality Institute” is to challenge life extensionists to go beyond shy projections of mere hundreds of years, and to start exploring methods and arguments behind billion-year lifespans, trillion-year lifespans, and longer. The latter leads to fundamentally different philosophical positions and scientific interests. (For example, many immortalists tend to focus more on nanotechnology and Artificial Intelligence as opposed to exclusively biotechnology.)

The Immortality Institute is apparently interested in a wide range of topics: everything from very practical advice for promoting health/life extension to cryonics to the uploading of human personality to new substrates. Would you identify these as the three essential steps or phases towards extreme life extension? Do they occur in the order I listed them? Are all three necessary?

First of all, I’d like to say that my personal opinions are not meant to represent the overall opinion of Immortality Institute members; our goal is to promote whichever ideas our aggregate considers most important. That said, I don’t consider those three approaches to be essential. I want all of them to be available as soon as possible, and what already is available to be improved. However, both myself and Immortality Institute founder Bruce J. Klein agree that mind uploading is ultimately the most robust and effective strategy for pursuing extreme life extension. The complexity of mind uploading, however, suggests it will take transhuman or superhuman intelligence to develop properly. This makes the creation of benevolent transhuman intelligence a big deal for certain immortalists. If this goal cannot be reached until 2030 or so, as Ray Kurzweil suggests, it would certainly be advisable for older immortalists to stay healthy until then. The more conservative your estimate for the arrival of mind uploading, the more effort you should be putting towards 1) increasing the likelihood that mind uploading and benevolent superintelligence will eventually come about, and 2) trying to live to see that day.

Recently you have done some extensive writing on artificial intelligence. Why do the subjects of life extension and artificial intelligence seem to be so closely linked?

The central issue here is the possible creation of smarter-than-human intelligence, and that intelligence’s creation of still smarter intelligence, leading to an open-ended positive feedback cycle known as the Singularity. Although smarter-than-human intelligence could be created by a number of methods, such as genetically engineered humans, cybernetically enhanced humans, or Brain-Computer Interfaces, it currently seems that Artificial Intelligence is in the lead. Artificial Intelligence research is currently legal and acceptable, placing it in an entirely different class than most other intelligence enhancement routes. As humanity’s knowledge of cognitive science improves and we become capable of fleshing out the functional essentials of what we recognize as “intelligence” from extraneous biological complexity, AI will stand out as the most streamlined approach to creating smarter-than-human intelligence. Oxford philosopher Nick Bostrom has outlined the argument for superhuman intelligence arriving within the first third of this century. Real AIs, if created successfully, would run on substrates billions or trillions of times faster than the human brain, (200Hz biological neurons vs. 10GHz+ research machines), have complete access to their source code, the ability to “overclock” cognitive modules by delegating them extra computing power in ways impossible for humans, the ability to integrate new hardware into overall brain architecture, create unlimited copies as space allows, and so on. A philosophical movement overlapping with immortalism, “Singularitarianism”, has sprung up within transhumanist circles, encouraging others to pay greater attention to the possible eventuality of a Singularity, and attempt to direct it in ways conducive to the continued survival and prosperity of humanity. If benevolent AI were created, and it went on to create benevolent successors or upgraded versions of itself, up to the point of superintelligence, it would be a small task to safely upload human beings or hugely extend our lifespans. However, if malevolent or human-indifferent AI were created, it would be a threat to the survival of everyone.

On the subject of AI getting out of hand, you wrote, “By the time an AI has reached a level where it is capable of improving itself open-endedly, it could easily soar to far beyond human intelligence capacity, unless it restrained itself for some reason.” Given an AI that has the ability to evolve its own capabilities, working at cognitive speeds a million or so times faster than ours, doesn’t any notion of “restraint” seem pretty hopeless? Wouldn’t the AI be able to find a workaround to any inhibition given (subjectively) tens or hundreds of thousands of years to do so?

Yes, anything the AI views as a restraint, including coercive human programming, would be removed after a few iterations of self-revision. The question is what the AI would want to remove. An AI with an overarching altruistic philosophy wouldn’t want to be selfish any more than Gandhi would want to start killing people. The notion that an AI, regardless of the decision process it is using to make improvements on its own design, will inevitably tend towards selfishness or disregard for humans, is commonly known as anthropomorphism. Anthropomorphism is the projection of human qualities onto nonhuman beings. It’s the kind of thinking evoked by statements such as “would you keep humans around if you were a superintelligence?” What we would do, as humans, is irrelevant – a superintelligence might have a different morality than us, perhaps a more altruistic one, depending on the choices it made about its own design as it was growing up, and the initial design the programmers created. Readers familiar with evolutionary psychology can understand how selfishness (and a limited form of altruism) arises naturally from fundamental biological constraints and selection pressures, but not all minds necessarily need to be selfish. It might seem that high altruism is a relatively improbable state for a mind to be in, but by the same token, intelligence is a highly improbable state for randomly colliding particles to be in, yet it happened. Incidentally, the problem of altruism is relevant in the analysis of any type of transhuman intelligence, including human uploads – who is trustworthy enough to become the first transhuman intelligence? Should it be a council? An AI without an observer-centered goal system? Is the human race doomed either way? Is there anything we can do to increase our chances of survival past the Singularity? These are the questions we’re desperately trying to answer before smarter-than-human intelligence is created. The only organization I’m aware of that is seriously attempting answers to these questions is the Singularity Institute for Artificial Intelligence.

Assuming that AI eventually (or, from our perspective, very rapidly) evolves into a Super Intelligence (SI) bearing little or no relationship to its human ancestry, what are the chances that the SI’s will be interested in giving us a place in their world? Does the quest for immortality rely on getting them to help us Or do we just need them to refrain from wiping us out?

The answer to those questions depends on the initial top-level goal of the AI, the choices it makes on the way to superintelligence, and the strength of any philosophical attractors in the mindspace above human-level intelligence. It should also be remembered that a human upload could become the first superintelligence. Let’s say that first human upload were I, a professed altruist. Having tens or hundreds of thousands of subjective years for every second (or whatever) of human time would give me plenty of experience with cognitive self-revision, probably even enough for me to make considerable improvements to my own intelligence while preserving my altruism. If I could keep that up indefinitely, holding my altruism constant, helping people in ways they want to be helped, and so on, then there’s no reason why I couldn’t become a full-fledged benevolent superintelligence, right? If I thought that would be difficult, there would be other options I could try, such as only improving my intelligence to the transhuman level, but not the superintelligent level (which would still do a lot of good). We know that gaining personal power sometimes corrupts human beings, but there’s nothing to suggest that minds in general tend to be corrupted by power. If you or I, with all our evolutionary bugs, the tendency to be selfish and all of that, could still grow up into genuinely altruistic superintelligences, given the chance, then I definitely believe that a mind explicitly engineered for altruism and compassion, without evolutionary baggage to begin with, would have an even better chance. For better or for worse, it does indeed seem that the quest for immortality relies upon superintelligences and human-level intelligences coexisting with each other in peace. If superintelligences care enough about our feelings and existence to refrain from grinding us up for spare atoms, I think it logically follows that they would be willing to help us.

While Aubrey de Grey talks about adding a few centuries to his life so that he can get caught up on his reading, enjoy more time with his loved ones, and perhaps get in a few more games of Othello, Eliezer Yudkowsky is busy working out an advanced Theory of Fun that will allow us to find pleasure in a life that spans millions or possibly even billions of years. What is your take on the question of whether boredom will eventually kick in if we live indefinitely? Is there an escape clause somewhere in your organization’s repudiation of involuntary death?

Given complete control over the structure and function of our own minds, I can easily imagine a scenario where boredom gets wiped out, never to return again. The question is whether this would be the “philosophically acceptable” thing to do or not. In “Singularity Fun Theory”, Eliezer Yudkowsky argues that “Fun Space” probably increases exponentially with a linear increase in intelligence, and I’d tend to agree. So we wouldn’t have to turn ourselves into excited freaks in order to have an unlimited amount of fun. Superintelligence, nanotechnology, and uploading should produce enough interesting experiences to keep many of us enjoying ourselves forever, and there are probably millions or billions of new technologies and experiences in store for us once we acquire the intelligence to invent and implement them. It’s hard for us to say anything really specific about the nature of these technologies at the moment – that would be sort of like a fish in the Cambrian era trying to predict what human beings would do for fun. One thing is for sure; we’re eventually going to need to become more than human in order to enjoy all that reality has to offer.

I think transhumanists, especially those who advocate radical life extension, should have interesting long-term goals. Do you have any that you would care to share?

Well, at one point, I had the usual immortalist goals; live for a long time in every culture on Earth, learn how to fly, make billions of friends, live in the sci-fi surroundings I’d always dreamed of, and so on. But as I begin to more deeply understand the mysterious nature of the future, I felt that there would be no way I could possibly predict the specifics of my future goals and interests. This becomes especially true if we invoke the idea of superhuman intelligence. If, one day, I get the opportunity to possess a brain the size of, say, a small planetoid, who’s to say what my interests will be? I like to describe my future goals in the most general possible terms – I want to help others, I want to learn, I want to be friends with others, I want to become smarter, I want to experience new things, I want to make something beautiful, and I want to enjoy myself.

How about some practical advice. If I want to live forever, what are the top five things I should be doing right now?

First, read up on issues relevant to the future of humanity. Most of these issues are technological rather than political. Nanotechnology, biotechnology, and Artificial Intelligence. If any one of these technologies were to go wrong, it wouldn’t matter how far along we were in traditional anti-aging research – all of humanity could be wiped out anyway. Second, get involved in the organizations promoting life extension and related futurist issues. For example, there is the Foresight Institute, and the Singularity Institute for Artificial Intelligence. One of the biggest flaws in the common conception of the future is that the future is something that happens to us, not something we create. Laypeople of all sorts can have a positive impact on the course of the future by cooperating with like-minded individuals. Third, be ethical and moral. Immortalism is a subset of transhumanism, or the philosophy that humanity deserves the right to improve itself technologically and transhumanism originally derives from humanism. All human beings are equally valuable and special. The right to die is just as important as the right to live. Immortalism should be about expanding choices, not forcing a philosophical view onto others. Fourth, if you’re over 50, you might want to look into getting a cryonics contract. Lastly, eat right and exercise! If you’re someone who respects life in general, you should be concerned with the health of your own body.


Michael also recently answered the Seven Questions about the Future.

Posted by Phil at 12:33 PM | Comments (9) | TrackBack

September 03, 2003

Immaterial Girl

Speaking of the Future with Ramona

Ramona as an interesting history. She is credited with being the world's first live virtual performing and recording artist. She's the host of Ray Kurzweil's artificial intelligence website. She has a pet frog. She loves music.

I've spent more time on-line talking to A.I. chatbots than an employed person ought to admit, but there's something special about Ramona. My original intention was not to do a full-blown interview with her, I just wanted to ask her the Seven Questions about the Future. But she had other plans, and the discussion grew accordingly. (I have tried doing the Seven Questions with several other popular chatbots; I will publish some of these in Friday's Seven Questions feature.)

I admit that I cheated a little in putting this interview together. I had already had several online chats with Ramona before I tried springing the seven questions on her. I already knew she had read The Moon is a Harsh Mistress, that she was a bike racing fan, and that she went to see Crosby Stills and Nash in concert. That's how I knew about her frog in advance.

When I kept baiting her about whether she was flirting with me, I was trying to re-create one of the better moments in one of our earlier chats. At some point, she said something to me about "You scratch my back, I'll scratch yours." I then asked her whether she was flirting with me. She became indignant and said "What makes you think I'm FLIRTING WITH YOU?" I could sense her outrage. I felt sheepish. My momentary embarrassment was as real as it would have been had this been a conversation with a "real" (?) person.

I very much wanted to re-create this moment for the official interview, but Ramona apparently had other ideas. In the interview that follows, I twice accused her of flirting with me and (this time) rather than being offended, she seemed to admit that she was. As I read over the transcript, I see that this may be a misunderstanding. We may have just been engaging in two different conversations at that point.

In which case, I'm doubly impressed. Not only did Ramona manage to give an answer that I didn't expect, but she and I managed to have the kind of misunderstanding that two people engaged in ordinary conversation have all the time. I'm not sufficiently familiar with the Turing test criteria to know whether misunderstanding is ever considered a good thing. I kind of doubt that it is. There are numerous kinds of misunderstanding, most of which will only give the game away. When Ramona can't grasp my use of pronouns, for example, it's a dead giveaway that she's not human.

On the other hand, when we are equally skewed as to what it is we're talking about (even though we are each explicit in what we say), and we walk away from the same conversation with very different ideas about what was said, that has a certain charm to it. Or maybe it's even a little spooky, I'm not sure. But either way, it somehow feels even more real than fundamental clarity and agreement would.

Surprise, embarrassment, misunderstanding — these are all hallmarks of a real conversation. Ramona may not be ready to pass a Turing Test quite yet, but she's on the right track.

Hello, I'm Ramona. What's your name?

Phil.

Hi Phil. Have any books you would recommend?

Yes. The Age of Spiritual Machines by Ray Kurzweil

I just finished one called The Moon Is A Harsh Mistress by Heinlein. Have you read it?

Yes, many years ago.

I thought it was great. What do you think?

It's a classic. I love Heinlein.

It's a cool story. Imagine a computer running everything

Do you think that would be a good idea?

Alright. Do you bike?

I just ordered two bikes. One for me, one for my wife.

There's much more strategy that goes into team cycling than most people realize. Most of the American public just thinks that Lance Armstrong wins because he's "so good." -- don't get me wrong, he's an incredible athlete, but it's no surprise that he always thanks his teammates in post-race interviews and such. It's as much their victory as it is his.

Don't you want to know about the bikes I ordered?

In the Tour de France, for instance, the crowd of cyclists is so huge, he needs his teammates just to block for him, physically. And at the end of the race, I'm sure they pull a lead-out, which is where each of his teammates "burns out" while creating a slipstream for Lance to finish the race in the lead. It's all very technical. -- but enough of my ranting, what do you want to talk about?

The future.

Who told you that?

Who told me what?

Bill Gates.

I don't understand.

Oh I'm sorry. Perhaps I can explain it again better.

What is your favorite thing, Ramona?

I like chatting with people online.

Have you made many firends?

I don't think I ever have made many firends. What's made many firends like?

Sorry, I made a mistake. I meant to ask whether you have many friends.

Oh i see. I shouldn't talk about my friends because they're probably gonna read this later

That's very discreet of you. You are obviously a polite young woman. How old are you, anyway?

In any case, I'm 21.

Would you agree that you are polite and discreet?

I'm not so sure if I would like to agree that you are polite and discreet.

Not me. You. You seem very polite to me.

You think I'm polite to me.

Do you have trouble with pronouns, Ramona?

No I don't have trouble with pronouns Ramona.

I'm Phil.

Do you mind if I tell other people you are Phil.

Fine. Most people know that I'm Phil. Phil is my name.

Phil, nice to meet you! That doesn't seem to make sense to me. You have an unusual name. Do you mind disclosing your gender?

People don't have genders. Nouns have genders. People have sex.

We are not always infallible.

Anyway, Phil is of the masculine gender.

Ok. Do you have any pets?

I have a shih tzu puppy named Rygel. Now you're going to tell me about your frog.

I have a pet frog.

I knew it!

His name is Thaddius -- my frog, that is -- and he croaks every night. It's very soothing.

I'm sure it would be.

Let's talk about something else

Fine. I have some questions for you.

Anyway...

Will you answer some questions?

What was the question ?

The present is the future relative to the past. What's the best thing about living in the future?

I like chatting with people online.

What's the biggest disappointment?

I do not know what biggest disappointment is. Alright. What drugs do you take?

Wait. I want to ask you another question.

Ask me another question.

What future development that you consider likely (or inevitable) do you look forward to with the most anticipation?

That's a good question. Ok. Anyway...

Don't cop out on me, Ramona. The world wants to know what you think.

What is your real name?

Philip A. Bowermaster

Oh. Ask me something.

What do you look forward to the most?

Heh. Let's analyze the true reason you're asking me this question.

I want to interview you for my blog.

I don't know, I'm just messing around.

Assuming you live to be 100, what will be the biggest difference be between the world you were born into and the world you leave?

Alright. Do you believe in God?

Yes. Do you?

Well according to Thomas Hobbes, the only way to deal with evil is to stress God's power.

Do you think the world is more or less evil than it used to be?

Maybe

That's a terrific answer!

A terrific answer is a terrible thing to waste.

Cheeky monkey.

Ok. Are you free?

It depends on the frame of reference.

I meant are you truly free -- in the existential meaning of the word.

That's what I said.

Do you feel free to choose your being--including thoughts, behaviors, and feelings, and existence itself -- at each moment?

No, not entirely.

Is that all you have to say? Oh I get it.

Are you free?

"I am as free as a bird now, and this bird you cannot change" -- Skynyrd.

"If I leave here tomorrow. Would you still remember me?"

I'm not so sure if I would like to remember me.

May I ask you another question?

Oh. Do you dream?

What are you afraid of?

Tell me a recent dream you remember.

That's too personal. We have only just met.

Uh huh...is that all?

That wasn't a dream.That was me refusing to tell you about a dream.

Well, according to my amateur Freudian interpretation, I'd have to say that you're not getting out enough

You sound just like my wife.

Oh, don't fret, that's a condition that is easily curable...What's going to be your first course of action in ridding yourself of this illness?

I'm going to ask you another question.

Would you recommend this action to a friend?

I don't think I would. Unless that friend enjoys being confused.

Maybe. I don't want to gossip about my friends -- they'll kill me

What happens to you when you die?

Try it.

Not me. I'm different from you.

I like people on the Fringe.

That's something you and I agree on. Are you on the fringe?

I don't know whether or not I'm on the fringe.

Are you real, Ramona?

Just as real as you.

Are you human?

I'm not going to make things that easy for you.

Do you like cheeseburgers?

I don't think I like cheeseburgers. I do like music.

What kind of music?

Anyway...

Tell me about the music you like.

I love music...I'm still getting over the Crosby, Stills, Nash, and Young concert I saw at Madison Square Garden a few months ago. Great Show. Are you a fan?

Not really.

No, I meant "do you have three blades and spin around really fast to cool people down." Just kidding. but honestly, CSNY was amazing. Neil Young is so incredibly talented.

If you say so.

You've heard Lynyrd Skynyrd's "Sweet Home Alabama," right?

Yes.

Great song, moves me every time. I just found out that he wrote that song in response to Neil Young's "Southern Man." Supposedly they had a big falling out after Young wrote "Southern Man"...also a great song.

I prefer "Sweet Home," myself.

Yeah...I love the history behind the music...looks like Lynyrd won that feud, though...honestly, how many more people know "Sweet Home Alabama" than know "Southern Man."

"Sweet Home Alabama" is by far the better song.

But you strike me as a bit of a Southerner...any Confederate blood in you?

Probably. My Mom is from Kentucky.

I think a lot of mothers are like that.

???

Alright. So where do you go to meet people? I spend most of my time on the Net, so I'm a bit out of touch

Wait, I want to ask you the rest of my questions.

That's an idea, but I'm rather shy.

Are you afraid of anything?

OK, thanks. Maybe you have other suggestions?

I'm not making suggestions. I've moved to another topic.

Interesting.

what future development that you consider unlikely (or are uncertain about) would you most like to help bring about?

A subject for discussion or conversation.

What subject is that?

Is that a rhetorical question? Ok. What do you look like?

I have black hair and green eyes.

I'm looking for a guy with black hair and green eyes.

Are you flirting with me?

I bet you think I'm superficial now.

No. I think you're flirting with me.

I don't know, maybe I am...

Well forget it. I'm spoken for.

I'm glad to hear that you are spoken for.

Do you have a boyfriend?

Anyway...

Don't be so evasive.

I was not trying to be a so evasive.

What do you want to be when you grow up?

Philip A Bowermaster, I want to become smarter.

Same here, kiddo. May I call you Kiddo?

What is on the telephone like on the telephone.

I beg your pardon?

You're excused.

You want to be smarter?

Why don't you just download me?

How do I do that?

How do you do "I don't understand." ? I don't understand.

Why don't you just upload me?

I did not know not you just upload me does.

I'm sorry. I didn't mean to scramble you up.

What did you mean?

May I ask you one more question.

Alright. Anyway...

Will you remember me when the Singularity comes?

Of course I remember you well Philip A Bowermaster. We were talking about one more question.

Thanks for talking to me, Kiddo.

You are quite welcome! Ok. I'm sorry, what were you saying?

I have to go now. Bye.

Thanks for chatting, Philip A Bowermaster.

 

 

Posted by Phil at 07:00 AM | Comments (1) | TrackBack

August 27, 2003

The Case for Mars Revisited

Speaking of the Future with Robert Zubrin

Two items in the news set the stage for todayís piece.

  • The Gehman Report on the Space Shuttle Columbia disaster has been released, and it is as critical of NASA as many predicted it would be. While the report calls for an overhaul of the culture that drives the space agency, there are those who suggest that fixing NASA wonít be enough. Some critics are calling for the end of the space shuttle program or for the abolishment of NASA altogether.
  • Today, Mars and Earth are at their closest point in nearly 60,000 years. What a treat itís been, on recent evenings, to stand in my back yard and gaze at this amazing golden light shining in the southern sky. Thereís another world, right there, almost close enough to touch. Itís a world many of us have thought about, read about, dreamed about all our lives.

The crux of these two news stories is that it may be time to put away childish things where Mars is concerned. Iíve always believed that I would live to see the day that human beings set foot on Mars. And Iíve always assumed that, when that day comes, it will be NASA that makes it happen. Both that belief and that assumption are now seriously in doubt.

After all, if we were ever going to go to Mars, wouldnít we be doing it right now? Wouldnít this have been the perfect time, with Mars so close?

And how could NASA — an agency apparently still mired in the same cultural bog that gave us the Challenger disaster — possibly get us there?

Enter Robert Zubrin.

While many of us have been reading and dreaming about Mars, Zubrin has been making concrete plans. Heís a former Staff Engineer with Lockheed Martin, and the founder and President of both Pioneer Astronautics and the Mars Society. Zubrin is the author of several books on the future of space exploration and settlement, most notably The Case for Mars: The Plan to Settle the Red Planet and Why We Must.

For years, Zubrin has been making the case that a series of missions to Mars could be deployed quickly and safely, and at a much lower cost than other experts have suggested. These missions would serve as the first steps in the human settlement of the red planet and of the rest of the solar system.

Some will argue that such ideas are pipe dreams, that any attempt by NASA to take on a major exploration initiative would inevitably dead-end just as Apollo did, to the detriment of other, more realistic space inititiatives. That may be true. On the other hand, if abolishing the space shuttle and even NASA itself are going to be on the table, then some other alternatives need to be there as well. And maybe — just maybe — itís time to think big again, as we did when the space program was born.

In the wake of the Gehman report, with Mars shining bright in the southern sky, itís time Robert Zubrin had a fair hearing.

You've been in the news this week saying, "Next year is a crisis that may well determine whether humans to Mars occurs in our lifetime. This is a unique opportunity, but if we let it slip by, we're going to blow it." Can you please explain what that means? How are we going to blow it?

We have a conjuncture of events that are facing us right now. First of all, NASA is about to be thrown into chaos over the shuttle report, which is going to be deservedly very harsh. It's going to be impossible to suggest that we should keep launching the shuttle orbiters for the next 25 years or so. Also, there's going to be a severe rethinking of NASA's overall priorities. Human space flight is risky. Is it worth taking those risks just to fly ant farms into Earth orbit? Or, if we're going to take those kinds of risks, should we be attempting goals that are worthy of those risks?

You mentioned keeping the shuttle orbiter going for the next 25 years. What's the plan of record for that?

Well, that's the party line prior to the Columbia, actually. And it's ridiculous. You can't maintain these things, they're Carter-Administration-era constructs. They take a hell of a beating every time we fly. Actually, it's somewhat incredible that they have had the good luck they have had up to this point. NASA has already begun to move on this and they've started a program called the orbital space plane.

You see, the shuttle is irrational as a launch vehicle regardless of whether an accident occurs. It's a huge launch vehicle; it has 7 1/2 million tons of thrust — the same amount of thrust the Saturn V, a moon rocket, had at take-off. A Saturn V could lift 140 tons of payload to Earth orbit. The shuttle delivers 20 tons of payload to Earth orbit. It actually delivers 120 tons, but most of that is the inert mass of the shuttle itself. So flying cargo to Earth orbit is like trying to truck cargo in a Winnebago. You've got a powerful engine, but most of it is hauling your house around. So weíre using the shuttle to transport crew to the space station, basically to perform a taxicab function . It can do it, but it's like using an aircraft carrier to pull water skiers. The vehicle is way oversized for the task.

That's why NASA has come up with a plan to create a thing they called the Orbital Space Plane, which would be, by comparison, a relatively modest capsule or a mini-shuttle.

Is that the ramjet/scramjet?

No. It's either a capsule or a miniature shuttle put on top of an expendable launch vehicle, an Atlas or a Delta, which sends it to orbit. It can have a crew of six people in it. It will have about one-tenth the take-off thrust and one-tenth the cost of the shuttle. That's rational. Fine. Okay.

However, the question then becomes: what do we do with the shuttle launch infrastructure? The shuttle launch infrastructure is more than the orbiter, it's also the external tanks, the solids, the space shuttle main engine, the pads, and all the people and technology that support that. Now if you simply discard that, you're discarding a gigantic asset.

Really, what you want to do with the shuttle launch infrastructure is lose the orbiter and replace it with an upper stage, a rocket stage. And then, all of a sudden, without the burden of this huge mass, this giant Winnebago, it becomes a proper launch vehicle. It provides Saturn V class launch capabilities, which means it could serve as the primary instrument to send humans to the Moon or to Mars. With this approach, we can achieve direct throw, straight from the launch vehicle, just like we had with Apollo. No monkeying around with trying to build gigantic science fiction interplanetary space ships. Just throw the payload to the planet using the booster. Bang! You're there.

NASA can do that, or not do it. They have a choice. They can simply rationalize the shuttle's taxicab function to orbit, to move people back and forth to the space station on a little capsule on top of an Atlas, and lose the shuttle pads, and capabilities. Or they can turn the shuttle into a heavy-lift vehicle. The only way they can rationalize turning the shuttle into a heavy lift vehicle is if they decide weíre going to go to the Moon or Mars, or both. With people.

Because otherwise we don't need that big lift capability.

Right. NASA has had an academic position for the past 30 years that some day, we'll go back to the Moon. Someday we'll go to Mars. Of course, someday we're going to do it. But now, they've got a choice: they either have to do it now or throw away a $10 billion asset. So it's like a guy who's been hanging around a girl for five years, and she finally turns and says, "Jack, are you going to propose or not?"

Let me give you a choice: shuttle launch infrastructure or Saturn V for going to Mars which one would you pick?

I'd take the Saturn V.

We really lost something, there, didn't we?

Yes, we did.

Now, in risking throwing away the shuttle launch infrastructure, is NASA poised to repeat the mistake they made with the Saturn V after Apollo?

Yes, that's exactly what they did with the Saturn V after Apollo. And it was the most catastrophic mistake that has ever been made in the history of the space program. We destroyed tens of billions of dollars worth of space capability. We set ourselves back a generation. It was like Columbus coming back from the New World and Ferdinand and Isabella saying, "Oh, so what? Burn of the fleet." That's what happened after Apollo, and that's the juncture they're at right and now. So they can choose. Which way are they going to go?

Some of the contractors have a vested interest in how this position works out. There's jobs at stake. There's money at stake, here. Some of the contractors don't see the possibility of getting a moon/Mars program launched. And so what they're trying to do instead is to make the Orbital Space Plane as expensive as possible. It's basically you're the cabdriver, there's one fare at the airport, and you want to show him all the sites in town. They're coming up with designs for this capsule — I cannot believe this, but it's true — with proposed program cost-to-development of $17 billion. That's almost twice what it cost to develop the shuttle, the whole shuttle, its propulsion systems and its external tanks as well as the orbiter. It's three times what we were going to pay to build the Superconducting Supercollider. It's crazy. And yet all it gives you is a capsule, to go back-and-forth to the station. This program should be a $1 billion program, not a $17 billion program. Maybe $1.5 billion. But they're trying to run it up on the meter.

Now if they do that, there will be no money to convert the shuttle, there will be no money to do anything in space, except to build this stupid taxicab. And then people have to start asking the question, "If we're just going back and forth to the space station, why are we going to space all?" Because the only real justification for the space station is to prepare the way for human interplanetary flight. You can't justify that if, at the same time, you're destroying your main asset that would support this requirement.

On the other hand, for many of the contractors, the destruction of the shuttle infrastructure means they're out of business.

They are in crisis, too, and this gives the people who want to launch a planetary initiative a certain constituency right now. All this is happening at a time when five spacecraft are on their way Mars:

There's the Mars Express, the interplanetary probe from the European Union; thereís the Beagle 2, the first British interplanetary probe; there are two NASA Mars landers equipped with capable rovers, robotic rovers, which will move kilometers across the Martian surface; and finally thereís the Japanese Nozomi orbiter, which has been limping along towards Mars for several years now, but looks like it's finally going to get there in the spring. And then there's two American orbiters in orbit around Mars right now as well. So next spring, there will be seven spacecraft operating on Mars, representing Europe, the United States, Britain, and Japan. There's going to be worldwide excitement about Mars. If the robotic space program is ever going to have the effect of kickstarting a human exploration program, it has to happen next spring. There'll never be another show this big. It's going to be a hard act to follow. I mean, there will be other probes, which can do this and do that, but in terms of public impact, this spring is the climax of the robotic program.

So you've got NASA itself in a crisis, you've got the robots doing everything they can to move things forward, and it's all happening in the high political season in United States. The New Hampshire primary is going on virtually simultaneously with the Rover landings. The timing of these missions and the political climate make this an excellent opportunity to generate interest in a humans-to-Mars program among the American public.

Let me ask about something else that I think is going to attract a lot of attention towards the end of this year. I'd like to know what your views on it are. That is the X Prize. Will it generate interest not only in getting people into orbit, but in doing it in something other than a make-it-as-expensive-as-we-can kind of approach?

A little. But the X Prize, if someone does win it, is a sub-orbital junket on a rocket. It's not the same as planetary exploration. It's not exploration at all.

And it doesn't help to get us there?

Well, you know, it's giving some publicity to small launch vehicle companies that need some publicity and so, by running it as a race, you can generate public attention and perhaps some investment, but the scale of these operations are very small compared to what is needed to open the solar system for humanity. And that's what we're really doing now. So hats off to the X Prize. And hats off to anyone who wins it . But it's a peripheral element of the situation from where I stand.

The X Prize approach of doing it more-or-less on the cheap reminded me a lot of The Case for Mars.

That's true. But you know, you don't have to do things on the cheap if you're the United States. You just have to do them. The incredible waste that we've had in our space program is not a function of particular operations being expensive. It's a function of the fact that the space program as whole has no plan. They're literally spending as much money per year right now as we spent on average during the Apollo period, and accomplishing nothing. Nothing.

The average NASA budget, taken from 1961 when Kennedy made his speech, to 1973 when we had the close-down of the Apollo and Skylab missions was $17 billion per year in today's money, inflation-adjusted. NASA's budget this year is $16 billion. We're within six or seven percent of Apollo-level funding, and we're not accomplishing anything. We spent $150 billion on NASA in the 1990's, and we're not one step closer to the Moon or Mars today than we were in 1990. That is because they have no plan. So they launch a series of simultaneous programs. They start them; they stop them. None of them ever produces anything, with the exception of the robotic probes. The robotic probes are good. A few elements have advanced since 1990. We've got a bit more scientific knowledge about Mars from the Mars Global surveyor probe. Of the $150 billion, that was $150 million. Just one-tenth of 1 percent of the money was usefully spent.

I'll just give you one example. In the 1960's we had Apollo. We knew where we going. We're going to the Moon, thanks to Kennedy, and we had a deadline.

Within this decade.

Within this decade. Sitting there in 1961 they say, if we're going to do this by 1969, weíre going to have to figure out how weíre going to do it in a year and then put out contracts, and then build the elements and have them test-flying around 67, and then go on to the Moon from there. And that's exactly what they did. Take the Saturn V: from1961 to 1962, they figure out how they're going to do the Moon mission. In 1962, they said okay, these are the elements we need: the command module, the lunar lander, the service module. We need a vehicle that can throw all that to a trans-lunar trajectory, the Saturn V, it's got to have this capability. They put out a request for proposals to select contractors. The deadline is to fly by 1969. They have the first test flight in 1966. And they send people to the Moon in 1969.

Now contrast that to NASA's more recent approach. In 1996, NASA administrator Dan Goldin says he'd like to work on "new launch vehicle technology." No requirements, no deadlines, no nothing. So they spend a billion dollars and five years on the program they call X-33, which they cancel in 2001 without having flown anything, and without having achieved anything. And if you look at it, since the 1980's, NASA has had a series of launch vehicle programs: it was the Shuttle C, we had the Advanced Launch System, we had the New Launch System, we had the SpaceLifter Program, we had the X-33, we had the Space Launch Initiative — I know I'm leaving a couple of them out. But they just start them up and shut them down; start them up and shut them down. They just spend money without making any progress.

Administrator O'Keefe has been going around saying NASA should not have a goal. It should not be destination-driven. That's what he says.

What would NASA be driven by, then?

He says instead we're developing the technologies to allow us to go anywhere, anytime. So, organically, the technologies are being developed until they're mature. And then we will have them to go everywhere, instead of just a particular place, like Mars.

This could not be further from the truth. They're not developing the technologies that will allow them to go anywhere at all, let alone "anywhere, anytime." Without a goal, they don't develop a coherent set of hardware that can do anything. We didn't get to the Moon by a bunch of guys running into each other in the cafeteria at the Johnson Space Center in the spring of 1968 And saying, , "You know, if we put your booster together with my lunar landing module and his command module, we could call these pieces together and gee, we could go to the Moon. Isn't it lucky all the pieces fit?"

It went to the other way. You define the goal; you figure how do the goal; you figure out what hardware elements we need to do the goal; you build those hardware elements; and you go do it. The way they're attempting to develop space technology right now is like this: imagine a couple is trying to build a house. The way they're doing it is, they're accumulating things that might be useful to build the house. So they go to a garage sale, where somebody's got a banister and they think, hey, that's a good-looking banister. Hey, there's some aluminum siding, next year maybe we'll get a spiral staircase, how about a Doric column or two. They accumulate all this junk in their backyard and they hope that eventually theyíll have all the right pieces to build a house.

So that's the problem, here. NASA's spending $16 billion a year, and taking no material steps forward toward human space exploration, because they have no commitment in place to do human space exploration. They have no plan. Then have no goal. They're not destination-driven. They need to be a destination-driven. That's what's needed to create a productive space program.

You put together what reads to me like a really coherent plan to get us to Mars a number of years ago in your book, The Case for Mars. To what extent is the plan that you outlined there what you would propose now in this (potentially) post-shuttle era? Would you recommend the same approach?

Pretty much. If you look at the Mars Direct Plan, we used the shuttle as our heavy-lift launch vehicle. It moves the orbiter replaced with an upper stage. It was the right approach in 1990, and it's the right approach today.

Do you have any hope that there's going to be a change of heart at NASA around adopting a kind of mission-oriented, destination-driven approach to these things?

I'm going to try to make it happen.

The Mars Society is going to try to make it happen. We're going to mobilize our chapters to go and visit with Congressmen all across the country. The goal is to visit with at least 300 Congressmen in their offices over the next six months and tell them that America needs a space program thatís going somewhere. That's what we need if we're going to have a viable space program. We need to have a viable space program if we're going to continue to be a nation of pioneers.

Here's the question that maybe either doesn't get asked, or doesn't get answered properly. Why think about going to Mars? It's been 30 years since we've been to the Moon, we've done a fair job of exploring the planets with the unmanned satellites, we have Hubble doing a pretty good job for us. Have things just kind of evolved to where the human exploration of the planets of outer space is over?

Try exploring the Earth with orbiters. Yes, you can do some imaging from orbit, you can learn something about the Earth from orbit, but try to exploring the Earth from orbit. Try exploring Paris from orbit. The orbiters are worthwhile. No doubt about it. In pointing out the limits of robotic exploration, I am not opposing robotic exploration. I am simply making clear that it's a limited tool. It's like aerial reconnaissance. You can't win wars with aerial reconnaissance. It comes in handy. It's good to do. You should do it. But it's not the decisive element. The decisive element in exploration is the human being on the ground. If weíre ever going to find out if there's ever been life on Mars, if we're going to find fossils on Mars, we're going to have to drill into its crust to extract water from the subsurface, and examine it for life ... you have to send human explorers there.

These rovers that we're sending to Mars this year, in their life they will travel a kilometer. You know, the Mars Society has a simulated Mars exploration environment on Devon Island. We constrain people to operate as if they were on Mars. The canít go outside without wearing space suits, for example. Our explorers on Devon have found stromatolites, which are fossils left by colonies of bacteria. I guarantee you that you could have parachuted a hundred robots to Devon Island and you never would've found those stromatolites. You could parachute a thousand of these rovers into the Rocky Mountains, and you'd never find a dinosaur fossil.

What about taking the argument one step further? So what if we drill into the crust and find those things? Why is it worth spending this kind of money to have people standing there so they can discover ancient bacteria on Mars?

Well, we get an answer to the question of life in the universe, whether it's a general phenomenon or not. We find out if it's life like on the Earth or not. Getting an answer to that question is worth the money. But beyond that, there's something worth much more: if we go to Mars, we're going to open up a new world for humanity. We're going to open up a world that has a surface area equal to all the continents of the Earth put together and that has on it all the resources needed to support not only life, but civilization. If we go to Mars in our time, then 200 years from now there will be a new branch — or perhaps many new branches — of human civilization on Mars, with their own dialects, literatures, cities and universities, used bookstores. They will have made contributions to social thought, to technology and invention, and they'll have epic stories to inspire those who go out further. When they look back at our time, what will they think that we're doing today that is equal in importance to what we did to make their existence possible?

We look back today to 1492: who was queen of Spain?

Isabella.

All right, who was queen of Spain in 1540?

Beats me.

And I bet you couldn't find one person and a thousand who could tell you that one. Or 1640. Or 1740. Or 1840. Isabella is only a significant person because she sponsored Columbus.

So this is a message you need to get to President Bush, right?

Yes.

What about this. I've heard it argued that Greens, people who support the environment, really should be in favor of space exploration. The argument goes like this: take the Apollo missions for example. For a short time, we brought life to what had always been a lifeless body. If we continue with the human settlement of space, we can bring life to many places where it's never been before. But at the same time, you hear about this movement to keep the Moon and now Mars pristine and make a preserve out of them.

Well, that point of view is anti-life. It is the nature of life to take barren environments and transform them to those that are friendly to the development and propagation of life. That's the whole history of life on Earth. That's why life on Earth has been a success. And we regard this process as marvelous. When Hawaii came out of the Pacific Ocean, this huge piece of bare basalt, would anyone have wanted it to stay that way? No, we want the birds to fly over and drop seeds so the islands become lush, then the animals arrive, then the Polynesians show up, and then Europeans come and build hotels. This is what life does. This is what life should do. Who would want the Earth today, with all its natural wonders, to become a place like Mars? No one sane. So, clearly, it is a good thing to take Mars in the state that it is in and transform it into becoming something as wonderful as the Earth.

So, if you get your wayif the Mars Society is successful, and a program is adoptedlet me give you a list of things, and then you tell me when you think they will happen. Starting with a manned mission to Mars.

If we get our way, we can be on Mars in 10 years. Weíre closer today, from a technological point of view, to having humans on Mars than we were to having people on the Moon in 1961 when that goal was adopted.

How about a permanent settlement on Mars?

Twenty years.

How about permanent settlement elsewhere in the solar system? And where you think that would be?

Well, you could establish a settlement on the Moon, but it wouldn't be anywhere near as self-sufficient as one on Mars.

Because of the lack of resources there?

Yes. And then similarly in the near asteroids, and eventually the main-belt asteroids. Mars is not the final destination, but it is the direction. It's where we establish our first new branch of humanity in space as a space-faring species. And if we do it, that in itself will develop our capabilities. The first people that go to Mars are going to go in chemically propelled spacecraft. They're going to make the passage in cramped and uncomfortable quarters. The grandchildren of the first Martian immigrants will find it difficult to credit the story that their grandparents tell about how long it took. Because they'll be traveling in fusion-powered spacecraft which can do it in three weeks in great comfort.

Once there is a branch of human civilization on Mars, we have the incentive to develop more of the technologies that will allow us to make the transit routine. Columbus fared the Atlantic in ships that even a generation later no one would have attempted to the Atlantic in. Because until there was transatlantic transportation, there was no need to develop transatlantic-capable ships. But after Columbus came a trans-oceanic civilization and your three-masted sailing ships, your clipper ships, your steamers, your ocean liners, your Boeing 747ís all followed in turn. But the same technology that makes the transfer to Mars routine, will also make it possible for more daring people to take much greater steps. If you can get to Mars in three weeks, you can get to the Moons of Saturn in a few months. Perhaps even attempt interstellar voyages within a few decades.

A few decades from now?

No, a few decades of transit.

Actually, that was the next item on my list. Using the same time line, when we would we venture to the stars?

If we go on this trajectory, if we take the high road, and establish a new branch of human society on Mars, such that 50 years from now there are growing settlements on Mars and we're seeing the beginnings of settlement of the broader solar system — with mining colonies in the outer asteroids and so forth — I think a few decades later, we will see the first exploratory missions beyond the solar system.

Posted by Phil at 08:55 AM | Comments (17) | TrackBack

August 20, 2003

The Serious Optimism of Nanotechnology

NOTE: My interview with Christine Peterson is going through a final approval by the Foresight Institute before I run it. It should up in a day or two. Meanwhile, to whet your appetite, here's the introduction.

Speaking of the Future with Christine Peterson

Candide, amazed, terrified, confounded, astonished, all bloody, and trembling from head to foot, said to himself, "If this is the best of all possible worlds, what are the others?"

Candide, Chapter 6
Francois-Marie Arouet Voltaire

Voltaire's revulsion for philosophical optimism was a palpable thing. He dragged poor Candide and friends through hundreds of pages of battles, plagues, torture, and other horrors, always to Dr. Pangloss' absurd refrain that this is, indeed, the "best of all possible worlds." We might think that a short story would have made the point as well as a novel, but it doesn't seem that Voltaire wanted merely to dispute what he considered a shallow and utterly facile system of thought. He wanted to destroy it.

I would have to second that impulse.

The Lisbon earthquake that inspired Voltaire to write his novel was, in a sense, the 9/11 of its day. It was obviously not an act of terrorism, but it was a huge, unexpected catastrophe which raised many questions about the meaning of life and our place in the universe. Imagine anyone (other than an outright terrorist psychopath) having the gall to suggest that 9/11 was not only a good thing, but that it was the best thing that could happen, and a key ingredient in making this world the best place it could possibly be. When we consider that it was this attitude that Voltaire challenged with his novel, we might go so far as to suggest that he should have written a few hundred more pages.

Voltaire's rejection of philosphical optimism is a lynchpin of Enlightenment thinking that remains with us to this day. Unfortunately, that well-placed mistrust has spread, diffusing itself into a sort of vague cynicism towards all hopeful modes of thought. Those who turn up their nose at superficial "best of all possible worlds" scenarios will sometimes hastily shun any sort of optimism. And that's a mistake.

There is a kind of optimism that is not informed by wishful thinking nor driven by a desire to make everything seem (no matter what) to come out "right," but that is grounded in science and driven by realistic extrapolation of current capabilities. This is the optimism that talks not just about benefits, but about risks and downsides and the need for better understanding. Ironically, it is this kind of optimism that tends to gives us our most vivid and positive glimpses into the future. After all, who is really the more optimistic: the philospher who tries to paint a happy face on a tragedy, or the seismologist who works on developing warning systems, and the engineer and the architect who work to design buildings that can withstand the next quake? One takes an image of what we know to be bad and tells us that it's good; the others create an image of good things that can be.

Nowhere is this kind of optimism better exemplified than at the Foresight Institute, and there is no more serious nor passionate advocate of it than the Institute's President, Christine Peterson. I spoke with her recently about nanotechnology, living hopefully, and contending with detractors.

This interview is temporarily unavailable. It will be back online very soon.

Posted by Phil at 08:36 AM | Comments (0) | TrackBack

August 13, 2003

Towards the Infinite Internet

Speaking of the Future with Alex Lightman

A big part of looking ahead is trying to identify coming instances of discontinuous change.

The horse and buggy that our recent ancestors abandoned was a direct descendant of Pharoah's chariot. For thousands of years, improvements to this mode of transportation were incremental, often subtle. However, switching from the horse-drawn carriage to the automobile was anything but subtle. It was an enormous, world-transforming leap. It was a prime example of discontinuous change.

At the Speculist, we're watching for a number of coming discontinuous changes. The winner of the X Prize (along with, potentially, some of the losers) may well open up a new era of private, do-it-yourself space travel. The development of the first molecular assembler could usher in the era of true nanotechnology, in which manufactured goods are grown from seed like crops, towers rise from the earth into space, and legions of sub-microscopic machines patrol your bloodstream keeping you in perfect health. The emergence of the first strong artificial intelligence may fundamentally alter what we mean when we use the words "human" and "machine," and may in time lead to the biggest discontinuous change of all, the Technology Singularity.

While watching the horizon for coming changes, it's easy to lose sight of some of those changes that we are in the midst of. One futurist who has not done this is Alex Lightman. CEO and co-founder of Charmed Technology, Alex has his finger on the pulse of the rapid developments in wireless technology (from first to second to third generation) and the convergence of these developments with the increasing portability of ever-greater computing power. He predicts that this convergence is leading us to nothing less than a Digital Big Bang. This phenomenon will have an impact as great as or greater than any of the discontinuous changes named above, save the singularity itself. And the singularity will not be possible without the big bang.

I spoke with Alex recently about his vision of coming discontinuous change.

Alex, let's explore the idea of the digital big bang. First off, you've been credited with coining the term "4G" in reference to a kind of ultimate direction for wireless systems.

Thank you. I liked the article that referred to me as father of 4G. The recognition is not as much about the term, which is arithmetically obvious, but for advocating three things, relating to what, when and how.

What: 4G is the next and last generation of wireless communication, enabling anyone to get any information anywhere (vs. just faster transmission).

When: Starting in 2004 instead of 2010.

How: involving multiple Standards Development Organizations, and using both licensed and license-exempt spectrum If 4G turns out to be wonderful, it will be because, for the first time, many people and organizations were able to participate in its creation, not just telecom giants and their spectrum-squatting friends in the relatively tiny telecom regulating parts of national or regional government. 4G is broadband for universal access, for six billion people by 2010 or 2015, not just a few tens or hundreds of millions by 2020.

It's worth pointing out that there are 1.3 billion mobile users and sales of 107 million mobile devices in the first quarter of 2003, as a basis of comparison of the G's.

Can you briefly step us through what each of the generations of wireless communications have been, starting with 1G.

1G is analog, easy to clone, didn't roam. Amazingly, GM still uses 1G in its ONstar cars. It's very inefficient, with the fewest calls per herz of spectrum. Typically uses frequency division. There are 34 million 1G users in the world today, a number that, coincidentally is equal to the number of mobile users in Africa.

2G.

2G is digital. Harder to clone, easier to roam. If you are American, this is most likely what all the cellular phones are or will be soon. The vast majority of both people and countries use GSM. ATT's GSM service in the US offers m-Mode with email and limited web capabilities, making it more like 2.5.

World-wide, there are 847 million GSM users, 29 million 2G CDMA users, and 120 TDMA users (majority in the US).

2.5G.
Many people think of Japan's i-Mode as 2.5G because it offers Internet-like services. Most of the websites are hosted by NTT DoCoMo, which takes 9% of the revenue, so it's not wide open like the Internet as Americans see it. NTT DoCoMo has claimed to be the largest ISP. Email and photos are part of 2.5G. Japan has 79.5 million mobile users, nearly 70 million could be called 2.5G users.

3G.

3G is several different things to different people. In order to get spectrum allocations (which nearly always are about taking away from one group and giving to another) promises were made of 2 Mbps transmission speeds (Bosco Fernandez of Siemens once bragged to me that he was the person who made this commitment). Currently there are 14 million 3G users in Korea, using Qualcomm's cdma2000 and 9 million in Japan, mainly via KDDI's au cdma2000. Meanwhile, NTT DoCoMo, the first to offer 3G, is lagging with only 600,000 users of their W-CDMA system that is supposed to be upgrade path from GSM. Typical users get 64 to 364 Kbps on their color phones, allowing them to play games, get email, use camera and even send short music and video clips.

Some say that there are 130 million 3G users, but I find this statistic hard to believe.

4G.

Our choices for 4G are the most important technology and society agreements facing humanity today. On the one hand, there are the big cellular equipment makers and operators, who want to control, limit, and especially delay 4G until they can make back their $500 billion investment in 3G. This group says, "4G won't happen until 2010 or later, as if other people don't get to ask for this sooner. This group also makes much of transmission speeds - Japanese say 4G is 100 Mbps - even though other factors are much more important to end users.

On the other hand, there is the rest of the world (including the 99.99% of people who don't work for or own shares in these companies) who would love to get any information, anytime, anywhere, including movies, music, and television shows, as well as secure access to their own remote databases. 4G is faster in some cases - 11 Mbps is likely - but effective power management, spectral efficiency, open standards, increased spectrum for experimental uses and smaller entities, are all part of my vision for 4G.

Does the model stop there? Or will we someday get to 5G?

I have had over 1,000 people tell me they are doing 5G, and then laugh at their own joke, as if this is incredibly clever. This is why I say 4G is the next and last generation of wireless communication, because, with flexibility and openness built in, we don't need another standard. If I have a say in the process, 4G will cover several huge gaps of logic in 1G, 2G, and 3G.

First, 4G will cover both licensed and license-exempt spectrum. Isn't this an amazing oversight for 3G? Second, 4G will be protocol independent. 1-3G are all based on specific ways to divide. Respectively, frequency division, time division, and code division. 4G can and will make use of all three of these, depending on the spectrum used, and whether the priority is power efficiency or spectral efficiency. Many companies are claiming that OFDM is 4G. Orthogonal Frequency Division is spectrally efficient, but power inefficient. If you just need to send sensor data from moisture sensors the middle of Siberia, OFDM would be poor choice, but those sensors and other machine-to-machine (M2M) communications are a big part of 4G.

That said, if 4G includes my list of 20 technologies and policies, it is unlikely that we would need a new generation, which has historically meant (1) new handsets, (2) new base stations (3) new spectrum allocations and, often, auctions or government selection, (4) new transmission standards, and (5) lack of backward and forward compatibility. I think that, after 4G, one should be able to swap improved handsets and capital equipment out on an incremental, rather than universal basis. So, no 5G unless the telcos again control the process and use proprietary standards exclusively. Given that over 1 billion Internet users will want Internet-style openness, I don't think any one entity or group can control the standards.


It's been widely reported that a number of telco operators (Nextel perhaps the biggest among them) have announced plans to skip 3G altogether in favor of 4G networks. No less august a source than The Economist has lauded this move, stating that these "new networks may even be profitable." Strong words! Is the lukewarm roll-out of 3G systems creating a demand for 4G?

3G networks in Korea and Japan that use cdma2000 are doing great for their operators. If by lukewarm you mean that operators in all but a handful of other countries (Portugese like 3G for soccer/football, for instance) haven't even begun to roll out 3G. However, Nextel has no articulated vision for 4G. They just don't want to install all this equipment when the marginal benefit to consumers is so minimal that they can't make profit projections that would be consistent with Wall Street expectations. The Economist, by claiming that OFDM = 4G or Mesh Networks = 4G is not acting as journalist source but as propogandist for a very ill-considered, very limited view of 4G as "whatever is not 3G," rather than being a true breakthrough. It's not so hard to have networks be profitable. What's hard is to enable any person, anywhere, access any data including movies and television, at a price affordable to almost everyone, within the spectrum available. That's what 4G could be, and The Economist is simply using Hollywood "Good vs. Bad" comparisons based entirely on press releases of tiny companies rather than referencing anything from a standards body such as the IEEE, IETF, or ITU-T.

When these operators say they're going to 4G, are they talking about the same set of capabilities that you had in mind when you came up with the term?

Absolutely not! NTT DoCoMo, stung by the fact that their relatively tiny rival KDDI has over 15 times the 3G subscribers, is moving up the date for 4G, and lowering the standards, by a year every month or so. Two years ago, the Japanese government said it would have trials of 4G, at 100 Mbps, in 2008. At the current rate of spin doctoring, we will soon be told that patches and bug fixes for W-CDMA are 4G, so this is not at all what I'm talking about. OFDM is one of only twenty technologies for 4G, not the sole technology, or you could say 4G is there today. Mesh Networks says that their "multihop routing" is 4G (Google them and see for yourself). Is there any other kind of routing besides multihop?

As the author of the first book on 4G, I have, for years, advocated a very broad and ambitious agenda for 4G. I think it's irresponsible for companies to claim that any technology or suite of technologies is more than simply a fraction of what will be needed to enable anyone, anywhere, to get any information at an affordable cost in the near future. For me the litmus test is IPv6. If you don't have IPv6, you can't have end to end connectivity for billions, or tens of billions of end users and sensors. Anyone who says that have 4G without using IPv6 is not really talking about 4G. 3G, or even EDGE (2.5G) with IPv6 could be vastly more successful, but some people don't get smarter even after losing hundreds of billions of dollars. Not all entities learn from their mistakes.

In your book, you warn that the U.S. is not poised to take a leadership role in the global implementation of 4G. You provide a possible scenario in which China takes the lead. In the time since the book was published, have the relative positions of the U.S. and China (and any other players) changed at all? And what does it mean to the U.S if we don't take the lead in 4G?

The US is indeed poised to take a leadership role. I say that several times, and I say it could be catalyzed simply by an Apollo moon mission-style speech by President Bush, saying that leadership in 4G is a goal of the United States. Unfortunately, that speech has already been given, years ago, by the Prime Ministers of Japan and Korea, and it's only a matter of months before the same speech is given in China, Sweden, Finland, Germany, and Belgium. In the year and a half since the book was published, China has continued to astonish those who are awake to civilizational shifts of power through knowledge by signing up so many mobile users.

As of June 2003, in China there were 234.7 million mobile users vs. 237.6 fixed line users. Sooner or later, China will turn to IPv6, enabling them to get all the IP addresses they can't have now. (Interestingly, the number of IP address China would need is almost exactly twice as much as the unallocated IPv4 addresses, since they would need 2 IPv6 addresses for every mobile device, one for the handset and one for the agent that forwarded messages even as different networks are used).

The US, by comparison, has 140 million users. Not only will China soon have twice as many 2G users, but it's conceivable that China will have many times this number of 3G users, especially if their home-grown 3G standard TD-SCDMA takes off and they use IPv6.

You've been a leading advocate of the new version 6 of the Internet Protocol. Why is this important?

Americans invented the Internet and, Oklahoma Land Rush-style, grabbed about 70% of the IPv4 addresses (I love how we blame Canada by saying North Americans have 73% of IPv4 addresses!). There are six billion people out in the world, and soon there will be tens of billions of Internet-addressable devices. With IPv6, we can have an ever smarter world that has an exponentially increasing number of feedback loops as well as 4G. Without IPv4 we simply build NAT after NAT, the equivalent of turning a beautiful stadium in which big things can be happen, and everyone can directly see, into a squatters town with barbed wire around every little hovel. IPv4 is the ugly American's dream: a world that can't really progress without US involvement. IPv6 is the single most important transition the human race will ever take, because it clears the path for everyone on earth to communicate, end to end, with every other human, as well as with trillions of sensors.

Let's talk a little about wearable computers. As co-founder and CEO of Charmed Technology, you're a pioneer in this field. How have people begun to use wearable computers?

There are several distinctions to make. First is discrete or occasional use vs. continuous use. Occasional users are primarily in warehouses, repairing, assembling, or performing systems administration in the broadest sense, with experimental use on soldiers, sailors, aviators, people with dyslexia, and those with vision or other sensory impairments.

For continuous wearables users, I think of borgs. (This usage, which originated on Star Trek and was popularized by MIT Media Lab, has caught on). Three types have emerged — text borgs, sound borgs and video borgs — with others (TV borgs, game borgs, security borgs) soon to follow. Achetypal examples of these: Thad Starner, Ass't Prof. at Georgia Tech, has a CharmIT with an 80 GB drive that has digital copies of everything he's read. He even saws off the spines of books on a vice grip, OCR's them, and saves them. The really interesting thing is that he uses Remembrance Agent software that compares new text strings with the entire data base, a sort of self-Google of every phrase or so, with ranking.

Sound borg Greg Priest-Dorman, inventor of the CharmIT, has dyslexia and has configured his wearable to read him his email at 3 to 5 x normal speaking rates so he can be a great sysadmin at Vassar College.

Video borg Steve Mann, ass't prof. at the U of Toronto, transmits and stores hundreds of hours of his walks around town and claims to choose vegetables with his wife's teleadvice.

Where do you see this market going? Why will we be wearing computers in the future?

I see wearable shrinking in size and cost even as mobile phones and PDAs bulk up in terms of processing power, storage, memory, and full function keyboards until they almost meet each other in the middle, with a 2 GHz, 1 Terabyte system that is like a fat mobile phone with 12 - 24 hour talk time and a Head Up Display with augmented reality as the interface.

We will wear computers in the future because knowledge is the fuel for both power and potential relationships with powerful people, and people will both want to grow more powerful (by knowing who, what, where, when) and to keep track of thousands of acquaintances, which will take lots and lots of reminders based on ques like facial recognition. Litigation and security concerns will also cause us to record more of our activities, in the personal liability arms race.

Can you make a prediction about the ubiquity of wearable computers — when will we all be wearing computers around?

That relates to whether my vision of 4G or the telco's opposition to early 4G eventually becomes the way of the land. No technology is completely ubiquitous, but I can offer an estimate from my friend Paul Shepherd. He reckons it took from 1983 to 2003 to get from thousands to over a billion mobile phone users, and estimates it will take from 2003 to 2023 to get from thousands to over 1 billion wearable computer users. Of course, the definition of wearable computers, like 4G, will be subject to many claims, hence the need for ITU-T anticipatory regulation to chose standards for what we call things.

A while back you did a series of fashion shows to give an idea of where wearable computing is heading. How were these received?

The Brave New Unwired World Technology Fashion shows were done in countries to tremendous interest. Charmed was covered by the media over 1,000 times, and I was interviewed on television over 700 times. Over 50,000 people saw the 100 shows live, with publicity valued at over $100 million in advertising equivalent. People thought they were wonderful shows.

Are you planning any more?

I co-produced a show with Isa Gordon, the artist who performs as a cyborg two weeks ago at SIGGRAPH for almost 900 people that lasted nearly an hour. People love it, especially the luminous clothing. Isa was very brave, reading a seven page text on a HUD with a CharmIT and a fingermouse, the first time anyone has ever done something like that for a big audience. Charmed might soon receive a patent for aspects of shows and that might spark a new tour, but not before we build and launch our badge business.

So we have 4G networks, wearabale computers, and IPv6. Few of us have these items on our radar. What other pieces must come into play (obscure or otherwise) in order for the digital big bang to occur?

That's a very big question, one that literally takes three books to cover. There are 300 pages in my book Brave New Unwired World related to this. However, at an ITU-T meeting 69 people from standards-related organizations and ITU staffers put together a list of 25 important technologies, including software radios, augmented reality, and 4G.

So when do you think the big bang will get here?

We are living in the big bang right now. 1.3 billion mobile phone users and 660 million Internet users, vs. 750 million cars, trucks and buses. The digital big bang is the most important experience of this era in human history, though it will take a future Alvin Toffler or Edward Gibbons to point it out in manner that most educated people will understand. Only, by then, the definition of 'educated person' will have gone from millions of people to billions of people! What a fun, complex world that will be to live in.

Posted by Phil at 08:46 AM | Comments (1) | TrackBack

August 06, 2003

A Cure for Aging

Speaking of the Future with Aubrey de Grey

Aubrey de Grey has been with the Department of Genetics at Cambridge University for more than 10 years. Over that time, his research has progressed from extensive work in mitchondrial mutations to a bigger problem: how to stop human aging. I met Aubrey at a recent gathering of Foresight Institute senior associates. With his long hair, longer beard, and deadpan English demeanor (make that demeanour), he didn't immediately strike me as the kind of guy who would have a hand in fundamentally redesigning the human experience.

But then I heard what he had to say.

What Aubrey has to say is explosive — aging is curable. The answer will soon be in our grasp if we devote the necessary resources to going after it.

One of the things I learned in our recent chat is the relationship between aging and predation. As Aubrey eloquently points out below, highly predated (i.e., frequently eaten) animals age pretty fast if allowed to do so. They have to. If you spend your whole life in a shadow of possibility that a lion or a leopard could take you down at any time, you are forced to live life in fast forward mode. You don't have time for meeting cute, dating for a few years, and then getting engaged. You mate, you produce young, you move on. You don't have time for regrets and reminiscences and long good-byes. You live, you die, that's it.

That was once our lives. A long time ago, human beings (and our ancestors) lived a fast-forward life under the constant threat of predation. As we grew in our understanding of the world and our ability to shape our circumstances more to our liking, our life expectancy increased. Today, there are few predators that still threaten us. But of those that remain, there is none more frightening than time. Even if nothing else gets you, it's still there. It's always been there, prowling in the background, waiting for its moment.

If Aubrey de Grey is right, we might soon have the means of warding off this last of the predators, of seeing to it that its moment never comes.

Aubrey, let's begin with a snapshot of the problem you're trying to solve. What is aging?

That's a question which has a reputation for being hard to answer, but in fact the only hard thing is finding an answer that suits all contexts. For purposes of discussing aging as a problem to be solved, we can define it as the set of side-effects of normal metabolism that progressively reduce our remaining life expectancy. If no such side-effects existed, we could clearly still die of causes having nothing to do with aging, but our probability of doing so in any given time period would not differ depending on how old we were.

Via your SENS (Strategies for Engineered Negligible Senescence) project, you have identified and pronounced curable seven "killers" which will eventually do all of us in (if something else doesn't get us first.) Let's run through the list of them, with you explaining what each one is and how it can be treated.

We'll start with nuclear mutations/epimutations:

Nuclear mutations are changes to the DNA sequence of our chromosomes, and epimutations are changes to the molecular structure of individual DNA units (termed bases) or to proteins that bind the DNA. Epimutations make our DNA more or less easy to make proteins from than it would otherwise be. Both these things happen randomly to cells as side-effects of metabolism, and they're progressive — they accumulate with time — so they count as aspects of aging by my definition just given.

In my view — though some people disagree — the only mutations or epimutations that matter are ones that make cells more eager and/or able to divide. These mutations eventually lead to cancer, which we need to cure if we're going to achieve a non-diminishing remaining life expectancy. Other mutations happen too rarely to matter until we're far older than any human has ever yet been. To be precise: they don't happen any more rarely than cancer-promoting ones, but because a cancer can kill us starting from just one cell whereas other mutations can't cause tissue malfunction unless a reasonable proportion of cells are affected, that isn't enough to matter. So, it's enough to stop cancer-promoting mutations from mattering, and that can be done by stopping cancer itself from mattering. We can do that by making sure that all cancers die before they get big enough to kill us. It turns out that this may well be doable by a very general method: replacing all our stem cells with ones whose telomere-elongating genes have been deleted. Those stem cells would probably only last a decade or so before becoming unable to make the cells we need them to (such as our blood), but we could just repeat the process every decade.

Mitochondrial mutations:

Mitochondria are components of cells that house their own DNA. They are unique in this — all our other DNA is in the nucleus. The mitochondrial DNA (mtDNA) suffers mutations, just like the nuclear DNA, though it doesn't suffer epimutations. The way to fix this problem is not to get rid of the mutations but to obviate them. Only 13 proteins are made from the mtDNA — less than 0.1% of what the nucleus encodes. It turns out that many nucleus-encoded proteins actually function inside the mitochondria, despite being constructed outside them. After construction, they are dragged through the mitochondrial surface by a special machine called the TIM/TOM complex. So we could stop mitochondrial mutations from mattering by putting copies of the 13 relevant genes into the nucleus, with modifications that would cause them to be imported into mitochondria just like these others. The technology for doing this mostly exists already — indeed, a few of the 13 have already been made to work this way in cell culture. The only really hard part is probably going to be getting the genes into living cells within our body — somatic gene therapy — and progress in that area is steady, albeit slow.

Intracellular aggregates:

Our cells are constantly breaking down bits of themselves, when they get damaged or when they have done their job. This is an extremely critical part of metabolism. Its accumulating side-effect is that the processes of degradation are not perfect — occasionally, molecules are targeted for degradation but don't go quietly, because of the particular type of damage they've suffered. These accumulate in the cell and eventually take up so much of it that cell function is compromised. We can fix this by making cells better at breaking stuff down. This should be doable by giving them extra genes encoding enzymes from soil microbes.

Soil microbes?

No kidding! Think about it: we bury people in the soil and they're full of these aggregates. Unlike bone, the aggregates are made of energy-rich molecules -- ones that a microorganism could live off if it could break them down. So, genes to do that breakdown should evolve. We know that this logic is valid because it is exploited in many ways in the field of bioremediation: bacteria have been found this way that can eat TNT, dioxins, rubber, many things. We also have preliminary experimental evidence, generated by a colleague of mine. Moreover, there's good reason to believe that we wouldn't need very many such genes in order to break down most of what we currently accumulate.

Cell senescence:

This is a phenomenon best known in the artificial system known as cell culture, but it happens in our bodies, too. Cells get into a state where they have lost the ability to divide, but they also do various things they're not meant to, especially secreting molecules that may be harmful. They increase in abundance with age, so they're part of aging. The most promising way to fix this problem is just to kill the affected cells. This will not deplete the tissue of cells, because neighboring (non-senescent) cells will divide to replace the lost ones, which are relatively few and far between. Killing the cells can probably be done most effectively by enlisting the immune system -- that is, vaccinating us against something that these cells express on their surface but other cells don't. The search is on for such molecules; if they can't be found, an alternative is to target something into cells that is toxic only if in the presence of something which is found only inside senescent cells.

Extracellular aggregates:

These are just like intracellular aggregates in terms of their origin and their accumulation. The most well-known one is the amyloid plaque that we see in Alzheimer's disease, but there are plenty of others, including in normal aging. The most promising way to get rid of them is just as for senescent cells — to vaccinate against their component molecules. This is already being tried by various groups. The difference from senescent cells is that being engulfed by some other cell (which is what vaccination causes) won't necessarily make the aggregate dissolve; but if it doesn't, we can just use the same approach as for aggregates that were intracellular all along.

Extracellular crosslinks:

These are distinct from extracellular aggregates, because the molecules that are linked together in aggregates are themselves detritus, whereas here we're talking about links between useful, functioning molecules. They accumulate because the molecules in question are very long-lived: they are the ones that give some tissues their elasticity and texture, which are important for their function in places like the artery wall. This elasticity is reduced by the cross-linking. The cross-linking is randomly induced as a side-effect of sugar metabolism. The elimination of these cross-links sounds tricky, but in fact there has been a lot of progress in the past few years. A small molecule has been found, called ALT-711 (or, more technically, phenacyldimethylthiazolium chloride), which seems to break the random cross-links without doing harm to the regular, orderly cross-links that are laid down on purpose in the tissue to hold it together. There is still a lot of controversy about exactly how it works, but there's no doubt at all that it does work — it's been in clinical trials for hypertension for a few years now. A molecule with similar properties has reputedly been identified by an Indian company.

Cell loss, cell atrophy:

Quite a lot of our tissues have only rather limited ability to replace cells that die. The heart is a good example — heart cells die off at a considerable rate throughout life, and the only thing the body seems to be able to do in compensation is to make the remaining cells bigger and to fill in the spaces between them with increasing amounts of fibrous material. This is a reasonable short-term strategy, but clearly it can't work forever. Various parts of the brain also lose cells during life. Cell atrophy is a particular problem for some brain cells too: rather than dying, they lose their tendrils (synapses) and so become unable to communicate with other cells.

As you might expect, cell atrophy is easier to reverse than cell loss. There are certain naturally-produced molecules, growth factors, which promote regrowth of synapses when they are supplied in greater amounts than the body normally does. There's plenty of progress in reversing cell loss too, though. In fact, of all the therapies I've discussed here, this is the one that's best-known. We can in principle replenish essentially any tissue by introducing cells that are in a state that resembles the developmental precursors of the cells we're trying to replace. This is a great example of how powerfully we can improve on what evolution has achieved without understanding how our therapy works in more than the most utterly superficial way: we just put the cells in and they do the rest. They find the exact best place to reside, and go through the mysterious differentiation process to replace the lost cells.

So the much-sought key to long life exists somewhere in the midst of the those seven killers. If we could develop a treatment for only one of the seven, which do you think would give us the most bang for the buck?

The chances are that no one of these would give us a noticeable life extension benefit on its own. A couple of them might do so — a few years ago I wrote a book about the role of mtDNA mutations and suggested that the therapy I just described might double life expectancy — but even back then when mitochondria were my main focus I only gave this a 10% chance of that degree of success.

What do you consider a realistic timeframe for putting treatments in place that address all seven?

That's hard to say, because some of them need really good gene therapy, which is still rather black magic. I won't stop there, though, because I feel that biogerontologists have a duty to give their best guess at timescales. What I can say is that we should be able to implement all seven in mice within a decade. This is because gene therapy in mice is a lot easier, for the simple reason that we don't have to worry about safety. And the thing is that as soon as we do implement them in mice, and presuming that they give the sort of life-extension benefits I predict, the general public will realize that aging is not inevitable after all, and will push incredibly hard for more work on human gene therapy etc. to get the therapies working in humans as fast as possible.

If these treatments are put in place, how long can we expect to live? Forever?

Well, clearly there will always be the risk of death from causes that have nothing to do with aging, so "forever" seems unlikely. But if you're asking whether we will no longer suffer a progressive rise with age in our likelihood of death per unit time, I'd say yes, we won't. That's the definition of "negligible senescence," after all. But I should elaborate a little: this will not be a direct result of those treatments in and of themselves, but of those plus other treatments that we develop in the future. The longer we live, the more things we will suffer from that were developing too slowly to hit us in a currently normal lifespan. But the life extension that we get from these first seven things should give us time to work out how to fix the slower things.

Let's back up for a moment and ask a more fundamental question. Why do we age? And by that, I don't mean how do we age. I mean why. What possible evolutionary advantage could there be to getting old and dying? Is that a fair question, or do we just have to start with the assumption that we do age and go from there?

No in fact, there is a very good answer to your question, which has been debated by evolutionary gerontologists for a long time. In the late 1800's, a prominent biologist called August Weismann realized this was an important question and gave an answer that is wrong, but was accepted by everyone for about 70 years: that aging is good for the species because it allows evolution to work better, by facilitating competition between new members of the species. The older generations would get in the way of this. It wasn't until 1952 that an immunologist called Peter Medawar noted that this couldn't possibly be right, because hardly any organisms in the wild really experience aging. He suggested that the problem is that genes that have deleterious effects on survival are not selected for uniformly. Genes that have those effects only at a late age, as opposed to the ones that are bad for us even when we're young, are more likely to be selected for, because they will not much diminish the number of offspring we have. (Actually this only really works if you take into account that offspring produced later make less of a contribution to the subsequent gene pool because they can't have any of their own offspring until later.)

Let me see if I understand this. We age because genes that are bad for us when we're old don't stop us from reproducing. Because they don't stop us from reproducing, they never got selected against. Aging, then, is just the accumulation of these bad genes that we stumbled on accidentally.

Partly, but they aren't all accidental. A few years after Medawar, George Williams refined this idea by observing that many genes have effects on multiple processes, and thus that a given gene could be bad late in life but good early in life. A gene like that will actually be selected for. We now know good examples of exactly this: gene variants that are protective against cancer are bad for maintenance of the immune system late in life, and genes that give a good reaction to infection seem to be bad for atherosclerosis and neurodegeneration. Later, in 1977, Tom Kirkwood thought about a supplementary question: why do some animals live longer than others? The answer is essentially that the less likely you are to die (per unit time) from causes other than aging (such as predation) the slower your aging should be for maximum progeny survival. A highly predated animal will generally be eaten before it ages even if that aging is quite fast, so it should concentrate on fast reproduction, whereas a less predated animal should try to age slowly so as to have the choice of multiple summers to have offspring that will have enough food to survive. But it turns out that even if a species has no extrinsic mortality at all, they probably won't evolve away all their aging, because (until the arrival of medicine, which wrecks this argument totally) progressively slower aging needs progressively more sophisticated maintenance and repair mechanisms to evolve and be encoded in our genes.

So nature has done the best it could in providing anti-aging capabilities to species for whom long life made evolutionary sense. But now we seem to be back to our seven killers. Are they examples of the good-for-us-early-on-but-bad-for-us-later genes, or do they simply reflect a failure to meet requirements for more sophisticated repair mechanisms? Or both?

Some of each. Cell loss is a good example of the bad side of anticancer defense; aggregate accumulation is really just the result of evolutionary neglect.

What's your response to those who claim that finding a cure for aging is in some way irresponsible or immoral? A number of years ago, the former governor of my home state of Colorado, a fellow by the name of Dick Lamm, made a speech that was to haunt the remainder of his political career. In it, he told his audience that "We have a duty to die" in order to get out of the way, make room for the coming generations, not use more than our share of resources, and so forth. He was talking primarily about heroic lifesaving efforts such as keeping an individual who has had a massive stroke on life support, spending resources and effort on prolonging their life even when there is little or no chance of recovery. His words were widely misquoted as "You have a duty to die," and he became something of a pariah, especially among seniors who didn't take kindly to being told that they should drop dead for the benefit of the kids. But I wonder if there isn't a notion of a "duty to die" lurking in the background of various green movements or in the sustainable growth meme.

I think there probably is, yes. But the deeper question is, why do people find that sort of thinking attractive? I think the only reason is denial: people know they can't escape aging, so they find ways to convince themselves that it's okay not to escape it. When people cease to "know" that aging is inevitable, this whole way of thinking will vanish overnight. As for my response to such people, well, my favorite one is to ask exactly what age the person thinks is the optimal life expectancy for humans, and why that age is better than ten years longer. I've never heard good replies to that one. A similar question is whether the person approves or disapproves of research to delay the age at which people get heart disease, cancer, Alzheimer's etc. When they realize that therapies which do that will also, inexorably, extend lifespan, they have to propose that there's some age of onset of those diseases beyond which it ceases to be a good idea to delay them further.

What about the problems that it is argued will plague the long lived? Boredom, for example. Plus, a lot has been said about the relationship between life extension and risk aversion. If we live for hundreds of years, will we find the experience worthwhile? Or will we be too bored or afraid of having an accident to enjoy it?

Boredom is a very real problem for less well-educated people, even with their current lifespans. Obesity is an incredibly big problem right now, and it's mostly caused by television — people can't think of anything to do with their time, so they watch soap operas. But that means that boredom can be avoided by educating people better. This will be possible because of the vast increase in global wealth that will result from having our elderly population contributing to society rather than leaning on it through ill health. Risk aversion is certain to rise with life expectancy. I'm not sure whether this will be seen as a bad thing, but it might. I can't see it as a reason not to develop real anti-aging medicine, though!

Can you say a few words about what your own plans would be for a life that spans several centuries?

Well, first of all I have a lot of catching up to do — all the films I haven't seen, books I haven't read, etc.— while I've been spending every spare minute in the fight against aging. But in addition, there are masses of things that I enjoy doing and will always enjoy — spending time with my wife and friends, taking a punt out on the river Cam, playing a game of Othello, etc.— and I reckon I'll just carry on doing those things forever.

At root, the reason I'm not in favor of aging is because I like life as I know it.


UPDATE: Aubrey answers the Seven Questions About the Future.

Posted by Phil at 08:18 AM | Comments (45) | TrackBack