AboutAI

Over the last 60 years, ever-smaller generations of transistors have driven exponential growth in computing power. Could molecules, each turned into miniscule computer components, trigger even greater growth in computing over the next 60?

Atomic-scale computing, in which computer processes are carried out in a single molecule or using a surface atomic-scale circuit, holds vast promise for the microelectronics industry. It allows computers to continue to increase in processing power through the development of components in the nano- and pico scale. In theory, atomic-scale computing could put computers more powerful than today’s supercomputers in everyone’s pocket.

“Atomic-scale computing researchers today are in much the same position as transistor inventors were before 1947. No one knows where this will lead,” says Christian Joachim of the French National Scientific Research Centre’s (CNRS) Centre for Material Elaboration & Structural Studies (CEMES) in Toulouse, France.

Joachim, the head of the CEMES Nanoscience and Picotechnology Group (GNS), is currently coordinating a team of researchers from 15 academic and industrial research institutes in Europe whose groundbreaking work on developing a molecular replacement for transistors has brought the vision of atomic-scale computing a step closer to reality. Their efforts, a continuation of work that began in the 1990s, are today being funded by the European Union in the Pico-Inside project.

In a conventional microprocessor – the “motor” of a modern computer – transistors are the essential building blocks of digital circuits, creating logic gates that process true or false signals. A few transistors are needed to create a single logic gate and modern microprocessors contain billions of them, each measuring around 100 nanometres.

Transistors have continued to shrink in size since Intel co-founder Gordon E. Moore famously predicted in 1965 that the number that can be placed on a processor would double roughly every two years. But there will inevitably come a time when the laws of quantum physics prevent any further shrinkage using conventional methods. That is where atomic-scale computing comes into play with a fundamentally different approach to the problem.

“Nanotechnology is about taking something and shrinking it to its smallest possible scale. It’s a top-down approach,” Joachim says. He and the Pico-Inside team are turning that upside down, starting from the atom, the molecule, and exploring if such a tiny bit of matter can be a logic gate, memory source, or more. “It is a bottom-up or, as we call it, ‘bottom-bottom’ approach because we do not want to reach the material scale,” he explains.

Joachim’s team has focused on taking one individual molecule and building up computer components, with the ultimate goal of hosting a logic gate in a single molecule.

How many atoms to build a computer?

“The question we have asked ourselves is how many atoms does it take to build a computer?” Joachim says. “That is something we cannot answer at present, but we are getting a better idea about it.”

The team has managed to design a simple logic gate with 30 atoms that perform the same task as 14 transistors, while also exploring the architecture, technology and chemistry needed to achieve computing inside a single molecule and to interconnect molecules.

They are focusing on two architectures: one that mimics the classical design of a logic gate but in atomic form, including nodes, loops, meshes etc., and another, more complex, process that relies on changes to the molecule’s conformation to carry out the logic gate inputs and quantum mechanics to perform the computation.

The logic gates are interconnected using scanning-tunnelling microscopes and atomic-force microscopes – devices that can measure and move individual atoms with resolutions down to 1/100 of a nanometre (that is one hundred millionth of a millimetre!). As a side project, partly for fun but partly to stimulate new lines of research, Joachim and his team have used the technique to build tiny nano-machines, such as wheels, gears, motors and nano-vehicles each consisting of a single molecule.

“Put logic gates on it and it could decide where to go,” Joachim notes, pointing to what would be one of the world’s first implementations of atomic-scale robotics.

The importance of the Pico-Inside team’s work has been widely recognised in the scientific community, though Joachim cautions that it is still very much fundamental research. It will be some time before commercial applications emerge from it. However, emerge they all but certainly will.

“Microelectronics needs us if logic gates – and as a consequence microprocessors – are to continue to get smaller,” Joachim says.

The Pico-Inside researchers, who received funding under the ICT strand of the EU’s Sixth Framework Programme, are currently drafting a roadmap to ensure computing power continues to increase in the future.

Popularity: 4% [?]

You’re following a gloomy corridor into a large boiler room, dimly lit by a flickering fluorescent lamp and echoing with the rhythms of unseen machinery. Three enemy soldiers suddenly appear on a catwalk high above the floor. They split up, one of them laying down suppressive fire, which forces you to take cover. Although you shoot back, the attackers still manage to creep forward behind a curtain of smoke and flying debris.

Moments later, a machine gun rings out, and you are cut down in a shower of bullets. Then, as you lie dying, you glimpse the soldier who flanked you from behind while his two buddies drew your attention.

Thankfully, it was only a video game, so in fact you’re not mortally wounded. Still, your ego might well be bruised, because you were not only outgunned but also outsmarted by artificial intelligence (AI).

The game is called F.E.A.R. , short for First Encounter Assault Recon, and its use of AI, along with its impressive graphics, are its prime attractions. The developer, Monolith Productions of Kirkland, Wash., released it in 2005 to rave reviews, including the GameSpot Web site’s Best Artificial Intelligence award. Such recognition means a lot to the game’s creators, who face stiff competition in what has become a multibillion-dollar industry.

The game is a far cry from the traditional diversions that AI researchers like ourselves have long studied, such as chess and checkers. Whereas the goal in the past was to write computer programs capable of beating expert players at such board games, now the metric of success for AI is whether it makes video games more entertaining.

Because a high fun factor is what sells, the video-game industry has become increasingly keen to make use of developments in AI research—and computer scientists have taken notice. A watershed came in 2000, when John E. Laird, a professor of engineering at the University of Michigan, and Michael van Lent, now chief scientist at Soar Technology, in Ann Arbor, Mich., published a call to arms that described commercial video games as “AI’s killer application.” Their point was that research to improve AI for such games would create spin-offs in many other spheres.

The main challenge is to make computer-generated characters—dubbed bots—act realistically. They must, of course, look good and move naturally. But, ideally, they should also be able to engage in believable conversations, plan their actions, find their way around virtual worlds, and learn from their mistakes. That is, they need to be smart.

Today many video games create only an illusion of intelligence, using a few programming tricks. But in the not-so-distant future, game bots will routinely use sophisticated AI techniques to shape their behavior. We and our colleagues in the University of Alberta GAMES (Game-playing, Analytical methods, Minimax search and Empirical Studies) research group, in Edmonton, Canada, have been working to help bring about such a revolution.

The AI of F.E.A.R. is based loosely on an automated planner called STRIPS (for STanford Research Institute Problem Solver), which Richard E. Fikes and Nils J. Nilsson, both now of Stanford University, developed way back in 1971. The general idea of STRIPS was to establish one or more goals along with a set of possible actions, each of which could be carried out only when its particular preconditions were satisfied. The planning system kept track of the physical environment and determined which actions were allowed. Carrying out one of them in turn modified the state of the environment, which therefore made other actions possible.

The designers of F.E.A.R. gave its soldiers such goals as patrolling, killing the player’s character, and taking cover to protect their own virtual lives. The makers of the game also gave each kind of bot a set of possible actions with which to accomplish each of its goals. One advantage of this approach is that it saves the developers the burden of trying to specify a response to every situation that might arise. Further, it allows seemingly intelligent behaviors to appear almost magically—such as the maneuver described above.

In that instance, the three attackers were carrying out two types of basic actions. One is to move to covered positions that are as close as possible to the player’s character. The other is simply to move around obstacles. The combination creates something that was not explicitly programmed into the game at all: a devastating flanking maneuver.

The spontaneous emergence of such complex behaviors is important because it provides a sense of deeper intelligence. That’s really what gets your heart pounding when you play the game. But you’d also like your adversaries to become more cunning over time, and F.E.A.R. has no mechanism for accomplishing that.

Why do bots need to get smarter? Imagine a game of badminton in which your opponent always reacts to your serves in the same way, always falls for your drops, and never attempts to anticipate your smashes. It would be a boring match. Up until recently, AI had been able to offer video gamers no better: the imps of Doom, released in 1993, never shoot their fireballs preemptively, and the civil-protection officers in Half‑Life 2 (2004) always take the nearest cover while reloading their weapons—to mention just a couple of things players experience with two well-known releases.

The standard solution is to add an element of randomness to the code that controls a bot’s decision making. Doing so varies a player’s experience, but the result does not necessarily come across as being intelligent.

A better approach is for the computer to learn about the player and to adapt a bot’s tactics and strategy appropriately. Of course, you don’t want the bot to become so good that it will win all the time; you just want it to give the human player a good run for the money. This capability, known as machine learning, is found in very few commercial games: Creatures, from the now-defunct Creature Labs, employed machine learning as early as 1997, as did Black & White, developed by the UK-based Lionhead Studios a few years later. But most video games are not able to “learn” on the fly or otherwise adapt to the person playing. Our group is hoping to push things forward in this regard using a system we’ve created for research purposes called PaSSAGE, which stands for Player-Specific Stories via Automatically Generated Events.

PaSSAGE, as its name implies, is all about storytelling, which has long been a staple of various role-playing games. But video games of all types rely to some extent on engaging storytelling. You can categorize such games by the way they vary their repertoire to appeal to different people.

Some games— Half-Life (2001), for example—are immensely popular even though they feature just a single linear story. So good scriptwriting can clearly go a long way. Other games, such as Star Wars: Knights of the Old Republic (2003), offer several alternatives to the main plot. This gives you the impression that you can shape your virtual fate—what psychologists call a sense of agency. That feeling of being in control is usually limited, however, because the branching plot lines often merge later on.

Titles like The Elder Scrolls IV: Oblivion (2006) and S.T.A.L.K.E.R.: Shadow of Chernobyl (2007) work similarly, taking one main story and complementing it with episodes drawn from a library of side quests. Other games, such as The Sims 2 (2005), go a step further by dispensing with a scripted plot altogether and creating an open-ended world in which players can effectively design their own happenings.

Although each of these techniques has enjoyed success, they all force the designer to make a trade-off between scriptwriter expressiveness and player agency. The approach we’ve taken with PaSSAGE avoids that conundrum by having the computer learn players’ interests and preferences and mold the story to suit them as the game progresses.

PaSSAGE uses the same game engine as Neverwinter Nights, a fantasy adventure set in medieval times, produced by BioWare of Edmonton. With PaSSAGE, scriptwriters determine only the most general arc to the story and provide a library of possible encounters the player’s character may have. The computer studies the player as he or she progresses and cues in the kinds of experiences that are most desired. For instance, if you like fighting, the game will provide ample opportunities for combat. If you prefer to amass riches, the game will conjure up ways for you to be rewarded for your actions. The software is able to make the sequence of events globally consistent by maintaining a history of the virtual world’s changing state and modifying the player’s future encounters appropriately. The game will therefore always appear to make sense, even though it unfolds quite differently for different people—or even for the same person as his moods and tastes change.

Machine learning can also be used to formulate the tactics that bots use, a job that now must be handcrafted by a game’s designers. Pieter Spronck and his colleagues, of the University of Tilburg, in the Netherlands, demonstrated this ability in 2005 using Neverwinter Nights. Spronck had one computer play against computerized opponents, programming it to get better over time by choosing the combat tactics that most often led to victory.

Members of our research group have been following through on Spronck’s work with Neverwinter Nights, using a different learning algorithm. Other colleagues of ours at the University of Alberta aim to do something similar with a multiplayer online game called Counter-Strike (2003), which pits a group of terrorists against a squad of antiterrorist commandos. Each character can be controlled either by a person or by the computer. As with F.E.A.R., players view the virtual world from the perspective of the characters they manipulate, making Counter-Strike an example of what’s known as a first-person-shooter game.

This project has so far produced a formal system for analyzing and classifying a team’s opening moves. That may not sound like much, but this task proved immensely challenging, because positions and actions are not nearly as constrained as they are in a game like chess. Researchers in our group have used this formalism to analyze computer logs of more than 50 hours of tournament-level play between seasoned Counter-Strike teams. Soon, we expect, computer bots programmed to learn tactics from such logs will play reasonably well—doing things a person might do. It’ll be a long time before these bots will be able to beat expert human players, though. But that’s not the objective, after all—they just need to make for entertaining adversaries.

Jeff Orkin and Deb Roy of MIT are undertaking a similar effort with something they call The Restaurant Game, for which they are applying machine learning to the task of making bots speak and act believably in social settings. In this case, the bots’ behaviors are based on observations gleaned from more than 10 000 sessions of human play.

Machine learning can also pay off for poker, which has become an especially hot game in recent years with the explosion of opportunities for playing it online. The strongest programs for two-player fixed-bet-size poker attempt to calculate the mathematically optimal solution for winning each hand. It turns out that finding such solutions is computationally infeasible, at least right now—there are just too many possible combinations of cards and betting sequences. But members of our research group have devised ways to calculate near-optimal strategies using certain simplifying assumptions. For example, instead of allowing four rounds of betting—which is permitted in competition poker—the program sets the limit at three. By further reducing the complexity of the game in clever ways, the computational burden can be reduced to a reasonable level. BioTools, a commercial spin-off of our research group in Edmonton, has incorporated some of our group’s work in this area in its Poker Academy software.

Although this program plays poker pretty well, it can’t yet do what is most required—spot and exploit the other player’s weaknesses. Figuring out how to program a computer to do that is extraordinarily hard. Why so? Studying an opponent should be easy, after all—and it is, but only if you have thousands of poker hands to analyze. What do you do if you have only a few? To make matters worse, human poker players make a point of changing their style so as to be hard to predict.

Right now, the best poker-playing programs to come out of our research group will make money off your average human player, and they are beginning to beat even some of the best in the world in organized competitions. This suggests that poker is just now joining the ranks of chess and checkers—games at which computers have trounced even world champions.

One lesson that computer scientists learned from working on chess and checkers is that programs must strike a balance in how they decide what move to make next. At one extreme, the computer can look all the way to the end of a game, examine every possible final position, and evaluate whether each one constitutes a win, a draw, or a loss. Then it can work backward from those possibilities, assuming best play by both sides at every stage, to select the optimal move. But searching that far ahead would take a great deal of time—for chess, enough for the sun to burn out.

The alternative is to use an evaluation function that incorporates knowledge of the game, enough to go beyond just recognizing an outright win to sense, rather, the slightest inkling of an advantage. In the ideal case, such a program would play perfectly while looking only a single move ahead. Of course, such a sophisticated evaluation would also require a lot of computational power.

In actuality, chess-playing programs operate somewhere between these two extremes. The computer typically examines all the possibilities several moves ahead and evaluates each, say, by tallying points, having assigned a different number of points to a pawn, a knight, a rook, and so forth. The computer then works backward to the current board position. The result is a ranking of all the available next moves, making it easy to pick the best one.

The trade-off between blind searching and employing specialized knowledge is a central topic in AI research. In video games, searching can be problematic because there are often vast sets of possible game states to consider and not much time and memory available to make the required calculations. One way to get around these hurdles is to work not on the actual game at hand but on a much-simplified version. Abstractions of this kind often make it practical to search far ahead through the many possible game states while assessing each of them according to some straightforward formula. If that can be done, a computer-operated character will appear as intelligent as a chess-playing program—although the bot’s seemingly deft actions will, in fact, be guided by simple brute-force calculations.

Take, for example, the problem of moving around intelligently in a virtual world—such as finding the shortest path to take from one spot to another. That’s easy enough to figure out if you can fly like a crow. But what if you’re earthbound and there are obstacles to contend with along the way?

A general algorithm for determining the best route between two points on a map has been around since the late 1960s. The problem with this scheme—known as A*—is that the amount of time the solution takes to compute scales with the size of the territory, and the domains of video games are normally quite large. So there isn’t time to calculate the optimal path in this way. In some games, the computer needs to move hundreds—or even thousands—of bots around their virtual stomping grounds without the action grinding to a crawl, which means that computation times must often be kept to just a few milliseconds per bot.

To address this issue, our research group has developed a series of pathfinding algorithms that simplify the problem. Rather than considering each of the vast number of possible positions each bot can take, these algorithms seek good paths by using coarser versions of the game map. Some of these algorithms can use a set amount of time for planning each move, no matter how vast the playing field, so they can be applied to game worlds of any size and complexity. They are also suitable for environments that change frequently, for instance when paths are blocked, bridges destroyed, doors closed, and so forth. BioWare will be using some of our group’s pathfinding algorithms in its forthcoming Dragon Age: Origins.

This same general approach can help computers master real-time strategy games, such as the Warcraft series, introduced in 1994, which was developed by Blizzard Entertainment of Irvine, Calif. In this popular genre, players control armies of game characters that work together to gather resources and battle enemies on uncharted terrain. The fast pace and large numbers of bots make these games too complex for today’s AI systems to handle, at least at a level that would challenge good human players.

Our research tries to address this problem by considering only the relatively small set of high-level strategies each player can follow, such as having your army of characters rush the opponent or expand aggressively so as to take over more territory. The computer simulates what the outcome would be, given the current state of play, if each side picked one of these strategies and kept to it for the duration of the game. By taking into account whether its human opponent is using all or just a few particular strategies, the computer can choose the counterstrategy that is most likely to succeed. This approach works better than the scripted maneuvers computers now employ in real-time strategy games when pitted against a human player.

The need for better AI in commercial video games is readily apparent—especially to the people playing them. And their thirst for more computer-generated intelligence will only continue to grow. Yet game makers rarely have the time or resources to conduct the research required to solve the many thorny problems involved, which is why they have come to recognize the value of engaging the scholarly community—a community that is hard at work in such places as Georgia Tech; Simon Fraser University, in Burnaby, B.C., Canada; the University of Teesside, in the UK; and the Technical University of Lisbon, to name but a few of the many research centers around the world involved in this kind of work.

With the increased participation of academics in game-related AI research, it will not be long before major improvements are apparent in the quality of the games entering the market. But there is a more significant reason to applaud the growing interest of AI researchers in the video-game industry—something Laird and van Lent pointed out to us and other computer scientists nearly a decade ago. The work we must do to make games feel more realistic will also take us a long way toward our ultimate goal of developing general-purpose machine intelligence. Now that sounds like a smart move.

About the Author

VADIM BULITKO, JONATHAN SCHAEFFER, and MICHAEL BURO are all part of the GAMES group at the University of Alberta, in Canada. They describe how they are using artificial intelligence to develop the next generation of interactive video games in “Bots Get Smart” [p. 48]. As its acronym suggests, their research group creates software for games, with the goal of beating—or at least seriously challenging—the human competitor. In 1994, Chinook, the team’s checkers program, became the first game software to win a championship against humans, earning it a place in Guinness World Records.

Source:
http://www.spectrum.ieee.org/dec08/7011/2

Popularity: 3% [?]

Last year, Khanna’s construction of a small supercomputer using eight Sony-donated Playstation 3 gaming consoles made headlines nationwide in the scientific community. On the consoles, he is solving complex equations designed to predict the properties of gravitational waves generated by the black holes located at the center of the galaxies.

“Science budgets have been significantly dropping over the last decade,” Khanna said. “Here’s a way that people can do science projects less expensively. This new web site will show people how to move forward.”

Typically, scientists rent supercomputer time by the hour. A single simulation can cost more than 5,000 hours at $1 per hour on the National Science Foundation’s TeraGrid computing infrastructure. “For the same cost, you can build your own supercomputer and it works just as well if not better,” Khanna said. “Plus, you can use it over and over again, indefinitely.” The cost for his initial Playstation grid was $4,000.

The guide is freely available to the public under an open source license.

The Cluster Workshop project is partially funded by the National Science Foundation and was first announced and demonstrated at the 2nd Annual Georgia Tech, Sony/Toshiba/IBM Workshop on Software and Applications for the Cell/B.E. Processor.

“This opens up a huge door to partnerships with industry and other universities,” said Khanna, noting that the UMass Dartmouth College of Engineering has an interest and focus in simulation sciences. Tyco Electronics (through the UMass Dartmouth Advanced Technology and Manufacturing Center in Fall River), Sony, Terra Soft Solutions and IBM are among the companies already involved with this effort. The scientists are seeking input from industry members and researchers to determine future project direction.

“We hope to continue to bring supercomputing to a broader audience by providing tools that simplify the use of these systems,” said Poulin, who specializes in distributed pattern recognition and artificial intelligence.

For the full guide, how-to and screenshots head over to:
http://www.ps3cluster.org/

Provided by University of Massachusetts Dartmouth

http://www.physorg.com/news148749271.html

Popularity: 3% [?]

When you enter the computer room on the second floor of Tokyo Institute of Technology’s computer building, you’re not immediately struck by the size of Japan’s second-fastest supercomputer. You can’t see the Tsubame computer for the industrial air conditioning units that are standing in your way, but this in itself is telling. With more than 30,000 processing cores buzzing away, the machine consumes a megawatt of power and needs to be kept cool.

Tsubame was ranked 29th-fastest supercomputer in the world in the latest Top 500 ranking with a speed of 77.48T Flops (floating point operations per second) on the industry-standard Linpack benchmark.

While its position is relatively good, that’s not what makes it so special. The interesting thing about Tsubame is that it doesn’t rely on the raw processing power of CPUs (central processing units) alone to get its work done. Tsubame includes hundreds of graphics processors of the same type used in consumer PCs, working alongside CPUs in a mixed environment that some say is a model for future supercomputers serving disciplines like material chemistry.

Graphics processors (GPUs) are very good at quickly performing the same computation on large amounts of data, so they can make short work of some problems in areas such as molecular dynamics, physics simulations and image processing.

“I think in the vast majority of the interesting problems in the future, the problems that affect humanity where the impact comes from nature … requires the ability to manipulate and compute on a very large data set,” said Jen-Hsun Huang, CEO of Nvidia, who spoke at the university this week. Tsubame uses 680 of Nvidia’s Tesla graphics cards.

Just how much of a difference do the GPUs make? Takayuki Aoki, a professor of material chemistry at the university, said that simulations that used to take three months now take 10 hours on Tsubame.

Tsubame itself – once you move past the air-conditioners – is split across several rooms in two floors of the building and is largely made up of rack-mounted Sun x4600 systems. There are 655 of these in all, each of which has 16 AMD Opteron CPU cores inside it, and Clearspeed CSX600 accelerator boards.

The graphics chips are contained in 170 Nvidia Tesla S1070 rack-mount units that have been slotted in between the Sun systems. Each of the 1U Nvidia systems has four GPUs inside, each of which has 240 processing cores for a total of 960 cores per system.

The Tesla systems were added to Tsubame over the course of about a week while the computer was operating.

“People thought we were crazy,” said Satoshi Matsuoka, director of the Global Scientific Information and Computing Center at the university. “This is a ¥1 billion (US$11 million) supercomputer consuming a megawatt of power, but we proved technically that it was possible.”

The result is what university staff call version 1.2 of the Tsubame supercomputer.

“I think we should have been able to achieve 85 [T Flops], but we ran out of time so it was 77 [T Flops],” said Matsuoka of the benchmarks performed on the system. At 85T Flops it would have risen a couple of places in the Top 500 and been ranked fastest in Japan.

There’s always next time: A new Top 500 list is due out in June 2009, and Tokyo Institute of Technology is also looking further ahead.

“This is not the end of Tsubame, it’s just the beginning of GPU acceleration becoming mainstream,” said Matsuoka. “We believe that in the world there will be supercomputers registering several petaflops in the years to come, and we would like to follow suit.”

Tsubame 2.0, as he dubbed the next upgrade, should be here within the next two years and will boast a sustained performance of at least a petaflop (a petaflop is 1,000 teraflops), he said. The basic design for the machine is still not finalized but it will continue the heterogeneous computing base of mixing CPUs and GPUs, he said.

Source:
http://goodgearguide.com.au/article/270416

Popularity: 2% [?]

The next big stage in the evolution of the Internet, according to many experts and luminaries, will be the advent of the Semantic Web–that is, technologies that let computers process the meaning of Web pages instead of simply downloading or serving them up blindly. Microsoft’s acquisition of the semantic search engine Powerset earlier this year shows faith in this vision. But thus far, little Semantic Web technology has been available to the general public. That’s why many eyes will be on Twine, a Web organizer based on semantic technology that launches publicly today.

Developed by Radar Networks, based in San Francisco, Twine is part bookmarking tool, part social network, and part recommendation engine, helping users collect, manage, and share online information related to any area of interest. For the novice, it can be tricky figuring out exactly where to start. But for experienced users, Twine can be a powerful way to research a subject collaboratively or find people with common interests, with the usual features of a bookmarking site augmented by Twine’s underlying semantic technology.

After creating an account, a user adds a Twine bookmarklet to her browser’s bookmarks, then adds items to her Twine page by clicking the bookmarklet as she surfs the Web. Bookmarks, too, can easily be imported from a browser or from another Web bookmarking service.

Twine uses artificial intelligence–machine learning and natural language processing–to parse the contents of Web pages and extract key concepts, such as people, places, and organizations, from the pages that a user saves. The site then uses these concepts to link information and users. For example, creating a twine–a bundle of bookmarks related to a particular topic–devoted to a specialized technique in computer game design quickly led to the discovery of twines (created by other users) devoted to other areas of game design and to twines devoted to a popular game that uses the technique. It also led to other users interested in the subject. Twine is also meant to automatically generate tags, descriptions, and summaries of bookmarked Web pages. In the preview, or beta, version, this feature didn’t always work properly, but Nova Spivack, CEO of Radar Networks, says that the functionality has been improved ahead of the public launch. Twines offer a hub for collecting, sharing, and discussing information. For example, users have created twines devoted to twentieth-century music, science and technology, philosophy, and cool things found around the Web.

On the surface, Twine looks a lot like many other social-networking applications: users make connections, share, and discuss information, and the artificial intelligence, machine learning, and natural language processing built into the website is not immediately obvious. “The Semantic Web is a technology that’s useful. It’s a means to an end, not an end in itself,” says Spivack. “What we’re doing with this release and going forward is, we’re talking about what you can use Twine for, and the fact that it’s powered by the Semantic Web is a detail for geeks.”

But Jim Hendler, a professor of computer science at Rensselaer Polytechnic Institute and a member of Twine’s advisory board, says that Semantic Web technologies can set Twine apart from other social-networking sites. This could be true, so long as users learn to take advantage of those technologies by paying attention to recommendations and following the threads that Twine offers them. Users could easily miss this, however, by simply throwing bookmarks into Twine without getting involved in public twines or connecting to other users.

It would be nice to be able to use Twine for a few more specialized purposes. For example, it seems ideal for finding events related to areas of interest–indie rock bands playing in Boston, for example. But the current interface deals awkwardly with dates. A Twine calendar, which categorizes events intelligently, would be a logical extension of the service. Spivack says that such a feature, as well as further developments, are on the way. As these arrive, and as the company adds more ways to classify data, the real value of the Semantic Web could well start to surface.

http://www.technologyreview.com/web/21583/?a=f

Popularity: 2% [?]

This post takes a look at the speed – latency and throughput – of various subsystems in a modern commodity PC, an Intel Core 2 Duo at 3.0GHz. I hope to give a feel for the relative speed of each component and a cheatsheet for back-of-the-envelope performance calculations.

I’ve tried to show real-world throughputs (the sources are posted as a comment) rather than theoretical maximums. Time units are nanoseconds (ns, 10-9 seconds), milliseconds (ms, 10-3 seconds), and seconds (s). Throughput units are in megabytes and gigabytes per second. Let’s start with CPU and memory, the north of the northbridge:

Latency and throughput in an Intel Core 2 Duo computer, North Side

The first thing that jumps out is how absurdly fast our processors are. Most simple instructions on the Core 2 take less than a cycle to execute, hence less than a third of a nanosecond at 3.0Ghz. For reference, light only travels ~4 inches (10 cm) in the time taken by a clock cycle. It’s worth keeping this in mind when you’re thinking of optimization – instructions are comically cheap to execute nowadays.

As the CPU works away, it must read from and write to system memory, which it accesses via the L1 and L2 caches. The caches use static RAM, a much faster (and expensive) type of memory than the DRAM memory used as the main system memory. The caches are part of the processor itself and for the pricier memory we get very low latency. One way in which instruction-level optimization is still very relevant is code size. Due to caching, there can be massive performance differences between code that fits wholly into the L1/L2 caches and code that needs to be marshalled into and out of the caches as it executes.

Normally when the CPU needs to touch the contents of a memory region they must either be in the L1/L2 caches already or be brought in from the main system memory. Here we see our first major hit, a massive ~250 cycles of latency that often leads to a stall, when the CPU has no work to do while it waits. To put this into perspective, reading from L1 cache is like grabbing a piece of paper from your desk (3 seconds), L2 cache is picking up a book from a nearby shelf (14 seconds), and main system memory is taking a 4-minute walk down the hall to buy a Twix bar.

The exact latency of main memory is variable and depends on the application and many other factors. For example, it depends on the CAS latency and specifications of the actual RAM stick that is in the computer. It also depends on how successful the processor is at prefetching – guessing which parts of memory will be needed based on the code that is executing and having them brought into the caches ahead of time.

Looking at L1/L2 cache performance versus main memory performance, it is clear how much there is to gain from larger L2 caches and from applications designed to use it well. For a discussion of all things memory, see Ulrich Drepper’s What Every Programmer Should Know About Memory (pdf), a fine paper on the subject.

People refer to the bottleneck between CPU and memory as the von Neumann bottleneck. Now, the front side bus bandwidth, ~10GB/s, actually looks decent. At that rate, you could read all of 8GB of system memory in less than one second or read 100 bytes in 10ns. Sadly this throughput is a theoretical maximum (unlike most others in the diagram) and cannot be achieved due to delays in the main RAM circuitry. Many discrete wait periods are required when accessing memory. The electrical protocol for access calls for delays after a memory row is selected, after a column is selected, before data can be read reliably, and so on. The use of capacitors calls for periodic refreshes of the data stored in memory lest some bits get corrupted, which adds further overhead. Certain consecutive memory accesses may happen more quickly but there are still delays, and more so for random access. Latency is always present.

Down in the southbridge we have a number of other buses (e.g., PCIe, USB) and peripherals connected:

Latency and throughput in an Intel Core 2 Duo computer, South Side

Sadly the southbridge hosts some truly sluggish performers, for even main memory is blazing fast compared to hard drives. Keeping with the office analogy, waiting for a hard drive seek is like leaving the building to roam the earth for one year and three months. This is why so many workloads are dominated by disk I/O and why database performance can drive off a cliff once the in-memory buffers are exhausted. It is also why plentiful RAM (for buffering) and fast hard drives are so important for overall system performance.

While the “sustained” disk throughput is real in the sense that it is actually achieved by the disk in real-world situations, it does not tell the whole story. The bane of disk performance are seeks, which involve moving the read/write heads across the platter to the right track and then waiting for the platter to spin around to the right position so that the desired sector can be read. Disk RPMs refer to the speed of rotation of the platters: the faster the RPMs, the less time you wait on average for the rotation to give you the desired sector, hence higher RPMs mean faster disks. A cool place to read about the impact of seeks is the paper where a couple of Stanford grad students describe the Anatomy of a Large-Scale Hypertextual Web Search Engine (pdf).

When the disk is reading one large continuous file it achieves greater sustained read speeds due to the lack of seeks. Filesystem defragmentation aims to keep files in continuous chunks on the disk to minimize seeks and boost throughput. When it comes to how fast a computer feels, sustained throughput is less important than seek times and the number of random I/O operations (reads/writes) that a disk can do per time unit. Solid state disks can make for a great option here.

Hard drive caches also help performance. Their tiny size – a 16MB cache in a 750GB drive covers only 0.002% of the disk – suggest they’re useless, but in reality their contribution is allowing a disk to queue up writes and then perform them in one bunch, thereby allowing the disk to plan the order of the writes in a way that – surprise – minimizes seeks. Reads can also be grouped in this way for performance, and both the OS and the drive firmware engage in these optimizations.

Finally, the diagram has various real-world throughputs for networking and other buses. Firewire is shown for reference but is not available natively in the Intel X48 chipset. It’s fun to think of the Internet as a computer bus. The latency to a fast website (say, google.com) is about 45ms, comparable to hard drive seek latency. In fact, while hard drives are 5 orders of magnitude removed from main memory, they’re in the same magnitude as the Internet. Residential bandwidth still lags behind that of sustained hard drive reads, but the ‘network is the computer’ in a pretty literal sense now. What happens when the Internet is faster than a hard drive?

I hope this diagram is useful. It’s fascinating for me to look at all these numbers together and see how far we’ve come. Sources are posted as a comment. I posted a full diagram showing both north and south bridges here if you’re interested

http://duartes.org/gustavo/blog/post/what-your-computer-does-while-you-wait

Popularity: 2% [?]

Robots that develop and display emotions as they interact with humans, and become attached to them, will be exhibited at the ICT’08 event organized by the European Commission in Lyon next week. Dr Lola Cañamero, of the University of Hertfordshire’s School of Computer Science, is co-ordinating a European project which is developing robots that are capable of growing emotionally, responding to humans and of expressing their own emotional states as they interact with people.

Prototypes of some of these robots showing mid-term project results will be exhibited at ICT 2008, Europe’s leading information and communication technologies event, which will take place in Lyon from 25-27 November 2008.

The project, FEELIX GROWING (FEEL, Interact, eXpress: a Global approach to development With Interdisciplinary Grounding; funded by the Sixth Framework Programme of the European Commission, aims to develop autonomous robots which will be capable of interacting with humans in everyday environments, and will learn and develop emotionally, socially and cognitively in accordance with the needs and personalities of the individuals with which they associate.

“The aim is to develop robots that grow up and adapt to humans in everyday environments,” said Dr Cañamero. “If robots are to be truly integrated in humans’ everyday lives as companions or carers, they cannot be just taken off the shelf and put into a real-life setting, they need to live and grow interacting with humans, to adapt to their environment.”

At ICT 2008, Dr Cañamero and the project’s international team of researchers will explain and demonstrate this approach using live interactive demonstrations and videos. Live demonstrations will include a baby pet robot learning to control its stress as it explores a new environment helped by a human caregiver, several robotic heads that show facial emotional responses to humans’ faces and voices, humanoid robots that learn to execute simple tasks by observing and imitating humans, and an interactive floor that responds to human touch and movement with different light and sound patterns. Videos and demonstrations will also show how non-human primates (chimpanzees) react to some of these robots.

The other players in the FEELIX GROWING project are: Centre National de la Recherche Scientifique, France; Université de Cergy Pontoise, France; Ecole Polytechnique Fédérale de Lausanne, Switzerland; University of Portsmouth, UK; Institute of Communication and Computer Systems, Greece; Entertainment Robotics, Denmark; and SAS Aldebaran Robotics, France.

http://www.sciencedaily.com/releases/2008/11/081120111622.htm

Adapted from materials provided by University of Hertfordshire, via AlphaGalileo.

Popularity: 2% [?]

We stand on the threshold of the most profound and transformative event in the history of humanity, the “Singularity.” What is the Singularity? From my perspective, the Singularity is a future period during which the pace of technological change will be so fast and far-reaching that human existence on this planet will be irreversibly altered. We will combine our brain power—the knowledge, skills, and personality quirks that make us human—with our computer power in order to think, reason, communicate, and create in ways we can scarcely even contemplate today.

Click here to Download the pdf of the full article

This merger of man and machine, coupled with the sudden explosion in machine intelligence and rapid innovation in the fields of gene research as well as nanotechnology, will result in a world where there is no distinction between the biological and the mechanical, or between physical and virtual reality. These technological revolutions will allow us to transcend our frail bodies with all their limitations. Illness, as we know it, will be eradicated. Through the use of nanotechnology, we will be able to manufacture almost any physical product upon demand, world hunger and poverty will be solved, and pollution will vanish. Human existence will undergo a quantum leap in evolution. We will be able to live as long as we choose. The coming into being of such a world is, in essence, the Singularity.

How is it possible we could be so close to this enormous change and not see it? The answer is the quickening nature of technological innovation. In thinking about the future, few people take into consideration the fact that human scientific progress is exponential: It expands by repeatedly multiplying by a constant (10 to times 10 times 10 and so on) rather than linear; that is, expanding by repeatedly adding a constant (10 plus 10 plus 10, and so on). I emphasize the exponential-versus-linear perspective because it’s the most important failure that prognosticators make in considering future trends.

Our forebears expected what lay ahead of them to resemble what they had already experienced, with few exceptions. Because they lived during a time when the rate of technological innovation was so slow as to be unnoticeable, their expectations of an unchanged future were continually fulfilled. Today, we have witnessed the acceleration of the curve. Therefore, we anticipate continuous technological progress and the social repercussions that follow. We see the future as being different from the present. But the future will be far more surprising than most people realize, because few observers have truly internalized the implications of the fact that the rate of change is itself accelerating.

Exponential growth starts out slowly and virtually unnoticeably, but beyond the knee of the curve it turns explosive and profoundly transformative. My models show that we are doubling the paradigm-shift rate for technology innovation every decade. In other words, the twentieth century was gradually speeding up to today’s rate of progress; its achievements, therefore, were equivalent to about 20 years of progress at the rate of 2000. We’ll make another “20 years” of progress in just 14 years (by 2014), and then do the same again in only seven years. To express this another way, we won’t experience 100 years of technological advance in the twenty-first century; we will witness on the order of 20,000 years of progress (again, when measured by today’s progress rate), or progress on a level of about 1,000 times greater than what was achieved in the twentieth century.

How Will We Know the Singularity is Upon Us?

The first half of the twenty-first century will be characterized by three overlapping revolutions—in genetics, nanotechnology, and robotics. These will usher in the beginning of this period of tremendous change I refer to as the Singularity. We are in the early stages of the genetics revolution today. By understanding the information processes underlying life, we are learning to reprogram our biology to achieve the virtual elimination of disease, dramatic expansion of human potential, and radical life extension. However, Hans Moravec of Carnegie Mellon University’s Robotics Institute points out that no matter how successfully we fine-tune our DNA-based biology, biology will never be able to match what we will be able to engineer once we fully understand life’s principles of operation. In other words, we will always be “second-class robots.”

The nanotechnology revolution will enable us to redesign and rebuild—molecule by molecule—our bodies and brains and the world with which we interact, going far beyond the limitations of biology.

But the most powerful impending revolution is the robotic revolution. By robotic, I am not referring exclusively—or even primarily—to humanoid-looking droids that take up physical space, but rather to artificial intelligence in all its variations.

Following, I have laid out the principal components underlying each of these coming technological revolutions. While each new wave of progress will solve the problems from earlier transformations, each will also introduce new perils, but each, operating both separately and in concert, underpins the Singularity.

The Genetic Revolution

Genetic and molecular science will extend biology and correct its obvious flaws (such as our vulnerability to disease). By the year 2020, the full effects of the genetic revolution will be felt across society. We are rapidly gaining the knowledge and the tools to drastically extend the usability of the “house” each of us calls his body and brain.

Nanomedicine researcher Robert Freitas estimates that eliminating 50% of medically preventable conditions would extend human life expectancy 150 years. If we were able to prevent 90% of naturally occurring medical problems, we’d live to be more than 1,000 years old.

We can see the beginnings of this awesome medical revolution today. The field of genetic biotechnology is fueled by the growing arsenal of tools. Drug discovery was once a matter of finding substrates (chemicals) that produced some beneficial result without excessive side effects, a research method similar to early humans’ seeking out rocks and other natural implements that could be used for helpful purposes. Today we are discovering the precise biochemical pathways that underlie both disease and aging processes. We are able to design drugs to carry out precise missions at the molecular level. With recently developed gene technologies, we’re on the verge of being able to control how genes express themselves. Gene expression is the process by which cellular components (specifically RNA and the ribosomes) produce proteins according to a precise genetic blueprint. While every human cell contains a complete DNA sample, and thus the full complement of the body’s genes, a specific cell, such as a skin cell or a pancreatic islet cell, gets its characteristics from only the fraction of genetic information relevant to that particular cell type.

Gene expression is controlled by peptides (molecules made up of sequences of up to 100 amino acids) and short RNA strands. We are now beginning to learn how these processes work. Many new therapies currently in development and testing are based on manipulating peptides either to turn off the expression of disease-causing genes or to turn on desirable genes that may otherwise not be expressed in a particular type of cell. A new technique called RNA interference is able to destroy the messenger RNA expressing a gene and thereby effectively turn that gene off.

Accelerating progress in biotechnology will enable us to reprogram our genes and metabolic processes to propel the fields of genomics (influencing genes), proteomics (understanding and influencing the role of proteins), gene therapy (suppressing gene expression as well as adding new genetic information), rational drug design (formulating drugs that target precise changes in disease and aging processes), as well as the therapeutic cloning of rejuvenated cells, tissues, and organs.

The Nanotechnology Revolution

Nanotechnology promises the tools to rebuild the physical world—our bodies and brains included—molecular fragment by molecular fragment and potentially atom by atom. We are shrinking the key features (working parts), in accordance with the law of accelerating returns, at an exponential rate (over four per linear dimension per decade or about 100 per 3-D volume.) At this rate the key feature sizes for most electronic and many mechanical technologies will be in the nanotechnology range—generally considered to be less than 100 nanometers (one billionth of one meter)—by the 2020s. Electronics has already dipped below this threshold, although not yet in three-dimensional structures and not yet in structures that are capable of assembling other similar structures—an essential step before nanotechnology can reach its promised potential. Meanwhile, rapid progress has been made recently in preparing the conceptual framework and design ideas for the coming age of nanotechnology.

Nanotechnology has expanded to include any technology in which a machine’s key features are measured by fewer than 100 nanometers. Just as contemporary electronics has already quietly slipped into this nano realm, the area of biological and medical applications has already entered the era of nanoparticles, in which nanoscale objects are being developed to create more-effective tests and treatments.

In the area of testing and diagnosis, nanoparticles are already being employed in experimental biological tests as tags and labels to greatly enhance sensitivity in detecting substances such as proteins. Magnetic nanotags can be used to bind with antibodies that can then be read using magnetic probes while still inside the body. Successful experiments have been conducted with gold nanoparticles that are bound to DNA segments and can rapidly test for specific DNA sequences in a sample. Small nanoscale beads called quantum dots can be programmed with specific codes combining multiple colors, similar to a color bar code, that can facilitate tracking of substances through the body.

In the future, nanoscale devices will run hundreds of tests simultaneously on tiny samples of a given substance. These devices will allow extensive tests to be conducted on nearly invisible samples of blood.

In the area of treatment, a particularly exciting application of this technology is the harnessing of nanoparticles to deliver medication to specific sites in the body. Nanoparticles can guide drugs into cell walls and through the blood-brain barrier. Nanoscale packages can be designed to hold drugs, protect them through the gastrointestinal tract, ferry them to specific locations, and then release them in sophisticated ways that can be influenced and controlled, wirelessly, from outside the body.

Nanotherapeutics in Alachua, Florida has developed a biodegradable polymer only several nanometers thick that uses this approach. Meanwhile, scientists at McGill University in Montreal have demonstrated a nanopill with structures in the 25 to 45 nanometer range. The nanopill is small enough to pass through the cell wall and deliver medications directly to targeted structures inside the cell.

MicroCHIPS of Bedford, Massachusetts, has developed a computerized device that is implanted under the skin and delivers precise mixtures of medicines from hundreds of nanoscale wells inside the device. Future versions of the device are expected to be able to measure blood levels of substances such as glucose. The system could be used as an artificial pancreas, releasing precise amounts of insulin based on the blood glucose response. The system would also be capable of simulating any other hormone-producing organ, and if trials go smoothly, the system could be on the market by 2008. Another innovative proposal is to guide nanoparticles (probably composed of gold) to a tumor site and then heat them with infrared beams to destroy the cancer cells.

The revolution in nanotechnology will allow us to do a great deal more than simply treat disease. Ultimately, nanotech will enable us to redesign and rebuild not only our bodies and brains, but also the world with which we interact. The full realization of nanotechnology, however, will lag behind the biotechnology revolution by about one decade. But by the mid to late 2020s, the effects of the nanotech revolution will be wide spread and obvious.

Nanotechnology and the Human Brain

The most important and radical application particularly of circa-2030 nanobots will be to expand our minds through the merger of biological and nonbiological, or “machine,” intelligence. In the next 25 years, we will learn how to augment our 100 trillion very slow interneuronal connections with high-speed virtual connections via nanorobotics. This will allow us to greatly boost our pattern-recognition abilities, memories, and overall thinking capacity, as well as to directly interface with powerful forms of computer intelligence. The technology will also provide wireless communication from one brain to another.

In other words, the age of telepathic communication is almost upon us.

Our brains today are relatively fixed in design. Although we do add patterns of interneuronal connections and neurotransmitter concentrations as a normal part of the learning process, the current overall capacity of the human brain is highly constrained. As humanity’s artificial-intelligence (AI) capabilities begin to upstage our human intelligence at the end of the 2030s, we will be able to move beyond the basic architecture of the brain’s neural regions.

Brain implants based on massively distributed intelligent nanobots will greatly expand our memories and otherwise vastly improve all of our sensory, pattern-recognition, and cognitive abilities. Since the nanobots will be communicating with one another, they will be able to create any set of new neural connections, break existing connections (by suppressing neural firing), create new hybrid biological and computer networks, and add completely mechanical networks, as well as interface intimately with new computer programs and artificial intelligences.

The implementation of artificial intelligence in our biological systems will mark an evolutionary leap forward for humanity, but it also implies we will indeed become more “machine” than “human.” Billions of nanobots will travel through the bloodstream in our bodies and brains. In our bodies, they will destroy pathogens, correct DNA errors, eliminate toxins, and perform many other tasks to enhance our physical well-being. As a result, we will be able to live indefinitely without aging.

In our brains, nanobots will interact with our biological neurons. This will provide full-immersion virtual reality incorporating all of the senses, as well as neurological correlates of our emotions, from within the nervous system. More importantly, this intimate connection between our biological thinking and the machine intelligence we are creating will profoundly expand human intelligence.

Warfare will move toward nanobot-based weapons, as well as cyber-weapons. Learning will first move online, but once our brains are fully online we will be able to download new knowledge and skills. The role of work will be to create knowledge of all kinds, from music and art to math and science. The role of play will also be to create knowledge. In the future, there won’t be a clear distinction between work and play.

The Robotic Revolution

Of the three technological revolutions underlying the Singularity (genetic, nano-mechanical, and robotic), the most profound is robotic or, as it is commonly called, the strong artificial intelligence revolution. This refers to the creation of computer thinking ability that exceeds the thinking ability of humans. We are very close to the day when fully biological humans (as we now know them today) cease to be the dominant intelligence on the planet. By the end of this century, computational or mechanical intelligence will be trillions of trillions of times more powerful than unaided human brain power. I argue that computer, or as I call it nonbiological intelligence, should still be considered human since it is fully derived from human-machine civilization and will be based, at least in part, on a human-made version of a fully functional human brain. The merger of these two worlds of intelligence is not merely a merger of biological and mechanical thinking mediums, but also and more importantly, a merger of method and organizational thinking that will expand our minds in virtually every imaginable way.

Biological human thinking is limited to 10 to the 16th power calculations per second (cps) per human brain (based on neuromorphic modeling of brain regions) and about 10 to the 26th power cps for all human brains. These figures will not appreciably change, even with bioengineering adjustments to our genome. The processing capacity of nonbiological intelligence or strong AI, in contrast, is growing at an exponential rate (with the rate itself increasing) and will vastly exceed biological intelligence by the mid-2040s.

Artificial intelligence will necessarily exceed human intelligence for several reasons.

First, machines can share knowledge and communicate with one another far more efficiently than can humans. As humans, we do not have the means to exchange the vast patterns of interneuronal connections and neurotransmitter-concentration levels that comprise our learning, knowledge, and skills, other than through slow, language-based communication.

Second, humanity’s intellectual skills have developed in ways that have been evolutionarily encouraged in natural environments. Those skills, which are primarily based on our abilities to recognize and extract meaning from patterns, enable us to be highly proficient in certain tasks such as distinguishing faces, identifying objects, and recognizing language sounds. Unfortunately, our brains are less well-suited for dealing with more-complex patterns, such as those that exist in financial, scientific, or product data. The application of computer-based techniques will allow us to fully master pattern-recognition paradigms. Finally, as human knowledge migrates to the Web, machines will demonstrate increased proficiency in reading, understanding, and synthesizing all human-machine information.

The Chicken or the Egg

A key question regarding the Singularity is whether the “chicken” (strong AI) or the “egg” (nanotechnology) will come first. In other words, will strong AI lead to full nanotechnology (molecular-manufacturing assemblers that can turn information into physical products), or will full nanotechnology lead to strong AI?

The logic of the first premise is that strong AI would be in a position to solve any remaining design problems required to implement full nanotechnology. The second premise is based on the assumption that hardware requirements for strong AI will be met by nanotechnology-based computation. Likewise, the software requirements for engineering strong AI would be facilitated by nanobots. These microscopic machines will allow us to create highly detailed scans of human brains along with diagrams of how the human brain is able to do all the wonderful things that have long mystified us such as create meaning, contextualize information, and experience emotion. Once we fully understand how the brain functions, we will be able to recreate the phenomena of human thinking in machines. We will endow computers, already superior to us in the performance of mechanical tasks, with lifelike intelligence.

Progress in both areas (nano and robotic) will necessarily use our most-advanced tools, so advances in each field will simultaneously facilitate the other. However, I do expect that the most important nanotechnological breakthroughs will emerge prior to strong AI, but only by a few years (around 2025 for nanotechnology and 2029 for strong AI).

As revolutionary as nanotechnology will be, strong AI will have far more profound consequences. Nanotechnology is powerful but not necessarily intelligent. We can devise ways of at least trying to manage the enormous powers of nanotechnology, but superintelligence by its nature cannot be controlled.

The nano/robotic revolution will also force us to reconsider the very definition of human. Not only will we be surrounded by machines that will display distinctly human characteristics, but we will be less human from a literal standpoint.

Despite the wonderful future potential of medicine, real human longevity will only be attained when we move away from our biological bodies entirely. As we move toward a software-based existence, we will gain the means of “backing ourselves up” (storing the key patterns underlying our knowledge, skills, and personality in a digital setting) thereby enabling a virtual immortality. Thanks to nanotechnology, we will have bodies that we can not just modify but change into new forms at will. We will be able to quickly change our bodies in full-immersion virtual-reality environments incorporating all of the senses during the 2020s and in real reality in the 2040s.

Implications of the Singularity

What will be the nature of human experience once computer intelligence predominates? What are the implications for the human-machine civilization when strong AI and nanotechnology can create any product, any situation, any environment that we can imagine at will? I stress the role of imagination here because we will still be constrained in our creations to what we can imagine. But our tools for bringing imagination to life are growing exponentially more powerful.

People often go through three stages in considering the impact of future technology: awe and wonderment at its potential to overcome age-old problems, then a sense of dread at the new grave dangers that accompany these novel technologies, followed finally by the realization that the only viable and responsible path is to set a careful course that can realize the benefits while managing the dangers.

My own expectation is that the creative and constructive applications of these technologies will dominate, as I believe they do today. However, we need to vastly increase our investment in developing specific defensive technologies. We are at the critical stage where we need to directly implement defensive technologies for nanotechnology during the late teen years of this century.

I believe that a narrow relinquishment of the development of certain capabilities needs to be part of our ethical response to the dangers of twenty-first-century technological challenges. For example, Bill Joy and I wrote a joint op-ed piece in the New York Times recently criticizing the publication of the 1918 flu genome on the web as it constitutes a dangerous blueprint. Another constructive example of this are the ethical guidelines proposed by the Foresight Institute: namely, that nanotechnologists agree to relinquish the development of physical entities that can self-replicate in a natural environment free of any human control or override mechanism. However, deciding in favor of too many limitations and restrictions would undermine economic progress and is ethically unjustified given the opportunity to alleviate disease, overcome poverty, and clean up the environment.

We don’t have to look past today to see the intertwined promise and peril of technological advancement. Imagine describing the dangers (atomic and hydrogen bombs for one thing) that exist today to people who lived a couple of hundred years ago. They would think it mad to take such risks. But how many people in 2006 would really want to go back to the short, brutish, disease-filled, poverty-stricken, disaster-prone lives that 99% of the human race struggled through two centuries ago?

We may romanticize the past, but up until fairly recently most of humanity lived extremely fragile lives in which one all-too-common misfortune could spell disaster. Two hundred years ago, life expectancy for females in the record-holding country (Sweden) was roughly 35-five years, very brief compared with the longest life expectancy today-almost 85 years for Japanese women. Life expectancy for males was roughly 33 years, compared with the current 79 years. Half a day was often required to prepare an evening meal, and hard labor characterized most human activity. There were no social safety nets. Substantial portions of our species still live in this precarious way, which is at least one reason to continue technological progress and the economic improvement that accompanies it. Only technology, with its ability to provide orders of magnitude of advances in capability and affordability has the scale to confront problems such as poverty, disease, pollution, and the other overriding concerns of society today. The benefits of applying ourselves to these challenges cannot be overstated.

As the Singularity approaches, we will have to reconsider our ideas about the nature of human life and redesign our human institutions. Intelligence on and around Earth will continue to expand exponentially until we reach the limits of matter and energy to support intelligent computation. As we approach this limit in our corner of the galaxy, the intelligence of our civilization will expand outward into the rest of the universe, quickly reaching the fastest speed possible. We understand that speed to be the speed of light, but there are suggestions that we may be able to circumvent this apparent limit (conceivably by taking shortcuts through “wormholes,” or hypothetical shortcuts through space and time.)

A common view is that science has consistently been correcting our overly inflated view of our own significance. Stephen Jay Gould said, “The most important scientific revolutions all include, as their only common feature, the dethronement of human arrogance from one pedestal after another of previous convictions about our centrality in the cosmos.”

Instead, it turns out we are central. Our ability to create models virtual realities—in our brains, combined with our modest-looking thumbs, has been sufficient to usher in another form of evolution: technology. That development enabled the persistence of the accelerating pace that started with biological evolution. It will continue until the entire universe is at our fingertips.

http://www.kurzweilai.net/articles/art0635.html

© Ray Kurzweil 2006. Reprinted with permission.

Popularity: 2% [?]