现在的位置: 首页 > 综合 > 正文

Kingofark的人工智能启示录

2013年02月08日 ⁄ 综合 ⁄ 共 28095字 ⁄ 字号 小 中 大 ⁄ 评论关闭

K ][ N G of A R K ™'s The Revelation Of AI

K ][ N G of A R K ™的人工智能启示录

What's It Mean to Be Human, Anyway?

"人性化"究竟意味着什么？

Revision 0.1

by  Charles Platt  

K ][ N G of A R K ™  译


[这一次的话题是"图灵测试"。奇人罗布纳发起的图灵测试有奖竞赛吸引了不少人的目光，现在我们来看看本文作者作为图灵测试的人类参与者在比赛前前后后的经历吧。]


Hugh Loebner
休·罗布纳

What's It Mean to Be Human, Anyway?

"人性化"究竟意味着什么？

Charles Platt reports on the latest battle to determine the most human computer, even as he worries that he may be the least human human.

关于判定最具人性之计算机的大比拼，查尔斯·普拉特报告了其最新进展；尽管他所担心的是，他自己或许就是那个最缺乏人性的人类[译注："最缺乏人性的人类"？详见下文]。

By Charles Platt
Charles Platt撰文

Robert Epstein is giving us all a pep talk. "You must work very hard to convince the judges that you're human," he tells us. "You shouldn't have any trouble doing that - because you are human."

罗伯特·艾泼斯坦给我们大家打气，"你必须很努力的让鉴定人员相信你是人类，"，他这样对我们说，"而你要做到这一点应该不会太难--因为你就是人类。"

A droll fellow, this Epstein. He wears Dr. Martens boots, black jeans, a black shirt, a Mickey Mouse tie, and an earring. His longish hair is brushed straight back and flips up over his collar. Five of us are listening to him in a beige conference room on the brand-new campus of California State University at San Marcos, near San Diego. Soon we will be put in front of computer terminals, where we will follow Epstein's instructions and, yes, do our best to seem human.

这位艾泼斯坦是个有趣的家伙。他穿着Dr.Marten的靴子，黑色牛仔裤，黑色衬衫，带一条米老鼠领带，串着耳环。他稍长的头发梳到了后面，又从衣领那里冒了出来。在离圣地亚哥不远的圣马科斯，加利福尼亚州立大学焕然一新的校园内一间淡褐色的会议室里，我们一行五人正听他做着介绍。不久我们将被带到计算机终端跟前，在艾泼斯坦的指导下--是的--尽其所能的使自己表现得像一个人类。

Our purpose is to find out whether 10 judges can tell the difference between humans and artificial-intelligence programs, when they are online at the same time. The people and the programs will be ranked in order of humanness; the program that scores highest will win its author US$2,000.

我们的目的是要搞清楚，十位鉴定人员同时在线的情况下，是否能够辨出人类与人工智能程序之间的区别。根据人性化的程度，参与其中的人和计算机程序会被排出名次；而得分最高的计算机程序将为其创作者赢得两千美金。

The inspiration for this event dates back to the earliest days of computing. In 1950, pioneer Alan Turing proposed that if a computer could successfully impersonate a human being during a free-form exchange of text messages, then for all practical purposes, the computer should be considered intelligent.

这样做的灵感可以追溯至计算领域最初的时期。1950年的时候，计算先驱阿兰·图灵（Alan Turing）提出，如果一个计算机能够在形式自由的文字信息交互中成功的模仿人类角色，那么针对任何现实的用途，这个计算机就应该被认为是智能的。

This soon became known as the "Turing test," and it sparked endless academic debate. Could a computer use trickery to emulate human responses without being intelligent? What did "intelligence" really mean, anyway?

这个提法很快被称为"图灵测试"而广为人知，并从此激发了无穷尽的学术争论。一个非智能的计算机能否采用欺骗的手段来效仿人类的反应方式呢？"智能（intelligence）"到底意味着什么呢？

The debate was never resolved because, oddly enough, no one ran the experiment until 1991, when a maverick named Hugh Loebner decided to underwrite it with his own money. Loebner offered $100,000 to the first person who could devise a program that would fool 10 judges during three hours of unrestricted conversation.

争论从来都没有过结果，因为--很奇怪的是--从来都没人做过这个实验，直到1991年，一个叫做休·罗布纳的独立人士决定花自己的钱来支持这一实验。罗布纳拿出了十万美元，奖给第一位能够发明这样一种程序的人——该程序能够在内容不受限制的三小时对话过程中骗过十位鉴定人员。

This was way beyond current capabilities, so Loebner also set up an annual $2,000 prize for the program that seemed most nearly human. And to make things even easier, he allowed each programmer to choose just one topic for conversation.

这样的要求远远超出了目前所能达到的水平，因此罗布纳又设立了一个年度两万美元的奖金，授予人性化程度最接近人类的程序创作者。另外，为了让测试更为简化，他还允许每个接受挑战的程序员在人机对话中挑选单独一个话题进行比赛。

So here I am at the fourth Loebner contest, sitting and listening to Robert Epstein, the director of the annual event. (Loebner participates mainly as an observer.) In experimental jargon, my companions and I are known as "confederates," because we'll be collaborating with Epstein in our efforts to fool the judges. We must try to seem as human as possible so the computers will have a standard to compete with.

于是，我便这样参加了罗布纳举办的第四次比赛，坐着倾听那位年度大赛主管罗伯特·艾泼斯坦讲话。（罗布纳则主要是作为观察员参与其中。）用实验的行话来说，我和我的同胞们被称为"共盟者（confederates）"，因为我们将联合艾泼斯坦一起，试图欺骗鉴定人员。我们必须尝试着尽量表现得人性化一些，以便让计算机们有个竞争的标准。

Epstein is a behavioral psychologist who got his doctorate under B. F. Skinner. So, naturally enough, he has invented a tricky little system of rewards and punishments for us. "You are in competition not only with the programs, but with each other," he tells us. "One of you will be presented with an award for most human human. And one of you will be ranked the least human human." He smiles deviously. "Your colleagues may mention this in the media."

艾泼斯坦是一位行为心理学家，曾在B.F.斯金纳的指导下获得博士学位。因此可想而知，他针对我们这样的参与者发明了一套小巧的奖惩系统。"你们不仅要与计算机程序进行竞争，互相之间也有竞争，"他告诉我们。"你们中的一位将被授予'最具人性的人类'的奖项。而另有一位将被排名为'最缺乏人性的人类'。"他诡异的笑道，"你的同事搞不好会向媒体题到这件事情的。"

Hmm. As I think about it, I realize that I definitely do not want to be written up in the national press as the least human participant in an artificial intelligence contest. I'm going to do whatever it takes to seem totally, 100 percent human when we start chatting online.

嗯。我琢磨着；我意识到，我当然不希望被某家全国性刊物描述为"某人工智能比赛中最缺乏人性的参与者"。只要在线聊天一开始，我无论如何都要表现得百分之百的人性化。

But this raises some weird questions. I am human, so why should I need to fake it? Is it possible for me to seem more human than I really am? And if so, what's the best strategy?

但是，这里有个蹊跷的问题：我就是人类，干嘛还要假装像个（特别人性化的）人类？我有可能表现得比平常更像人类吗？如果可能，有什么上佳的策略吗？

This kind of speculation probably isn't a good idea, because it raises more questions than it answers, and I'm liable to find myself paralyzed by self-conscious introspection. In other words, if I try to seem more human, I'll end up seeming less human.

如此这般思索或许不是个好主意，因为其引出的问题比能够回答的问题更多，我也可能反而因为自我反省而麻痹大意。换句话说，如果我刻意要表现得更像人类，结果反而是看上去更不像。

I glance around at the other four confederates. None of them seems to be bothered by this kind self-analysis. The young woman nearest me is a journalist named Linda Tontini who writes for a local newspaper about city-hall politics. She seems friendly, spontaneous, outgoing - the absolute antithesis of "computer geek." As I watch her chatting cheerfully, I think that she can't fail to win the "most human human" award.

我环顾身边，瞅了瞅另外四位共盟者。他们看上去好像并没有被类似我这样的自我分析弄得心神不定。离我最近的年轻女人是一位叫做琳达·通蒂尼的新闻记者，她为一家当地报社撰写有关市政部门施政的文章。她看上去友善、自然、大方——照说应该是"计算机怪杰（computer geek）"之类的决然对立面。我看着她兴致勃勃的跟人聊着天，心想她不大可能不赢得"最具人性的人类"奖项。

As for me, I fear the worst.

而我，怕的就是最坏的情况。

After our briefing, I'm introduced to Hugh Loebner. He's an affable character, slightly overweight, smiling benevolently at the world from behind a gray beard and oval wire-framed glasses. He talks quickly, with pedantic precision. I ask him why he's willing to pledge $100,000 for a piece of smart software. Is it all his own money?

一通简报之后，我被介绍给休·罗布纳。他是一个和蔼可亲的人，略微偏胖，从灰色胡须和卵形金属边眼镜后面向世界投以仁慈的微笑。他谈吐迅捷，话里透着学究式的精确性。我问他，为什么他愿意出十万美元寻求一个机巧的软件，那全是他自己的钱吗？

"My father passed away and left me, not rich, but with some discretionary income," he says. "And I have my own business, Crown Industries - we make roll-up plastic lighted portable disco dance floors." He smiles and shrugs as if he knows it sounds odd but doesn't care.

"我的父亲过逝，虽然不富裕，但仍留给我一些可自由支配的收入，"他说。"而我也有自己的生意做，皇冠工业（Crown Industries）——我们出品可卷折的塑料发光便携式狄士高跳舞地板。"他笑着耸了耸肩，好像他知道这听起来怪怪的而他并不在意。

Loebner has had some personal experience programming computers, but his doctorate is in sociology. Perhaps because of this, at least one person in the artificial intelligence community views him skeptically. In 1994, a Harvard researcher in computational linguistics complained publicly that Loebner's prize encourages scientists to fake human behavior using cheap tricks instead of "true" AI.

罗布纳也有一些计算机编程的个人经验，但他拿的毕竟还是社会学的博士头衔。或许恰缘于此，至少有一位人工智能社群的人士持怀疑的眼光看待他。1994年，一位哈佛的计算语言学研究员公开抱怨说，罗布纳的奖赛是在鼓励科学家采用糊弄人的把戏来伪造人类行为，而不是采用"真正的"人工智能。

Naturally, Loebner has a different perspective. "I see scientific research as being, in a mathematical sense, a form of chaotic human behavior," he tells me. "In chaos theory, the smallest initial perturbation can result in a huge change downstream. So, since I was the first person to create and fund this contest, I may turn out to be a precipitating factor. Ultimately, if we're capable of creating a computer that is sentient, then from the point of view of that computer, humans will be gods. I like to think of intelligent machines going out across the universe with this semimythic concept of human demigods. And just maybe," he smiles happily, "they'll remember me."

当然，罗布纳有着不同的看法。"从数学的角度来看，我把科学研究视为一种混沌的人类行为，"他告诉我。"在混沌理论中，最为微小的初始混乱可能导致后续巨大的下游变化。所以，鉴于我是创建并资助这类竞赛的第一人，我可能就成为了其中涨落因素。最终，如果我们有能力创造一个有感知意识的计算机，那么从这个计算机的角度看来，人类就是其上帝。我想象着，智能机器们带着这种关于半神人类的半神话式的概念，穿行于宇宙之中。这样的话，或许，"他开心的笑道，"他们会记得我。"

Each year, along with his check for $2,000, Loebner gives a bronze medal to the contest winner. He pulls out the medal and shows it to me. Alan Turing is in bas-relief on one side, and Loebner on the other. Doesn't all this seem a little ... egotistical?

每年，罗布纳将铜制奖章连带两万美元的支票授予竞赛获胜者。他拿出奖章来展示给我看。奖章一面是阿兰·图灵的潜浮雕，另一面则是罗布纳自己。这看起来是不是有一点……妄自尊大？

"I've been called egotistical," he agrees cheerfully. "I've also been called lazy. Well, I am lazy. I'd like computers to do all the work - which is one reason I'm interested in artificial intelligence. As for being egotistical, the contest has attracted a lot of attention, so perhaps I have a right to be egotistical."

"我是被认为是妄自尊大，"他欣然同意道。"我也被认为是懒惰的。是的，我是很懒。我希望计算机能为我做所有的工作——这也是我对人工智能感兴趣的一个原因。然而正是如此，这个竞赛才吸引了许多关注的目光，或许我应该有权利变得妄自尊大一些。"

But with all the worthy causes in the world, why did he choose artificial intelligence?

但是，世界上有那么多值得为之投入的事情，为什么他会选择人工智能呢？

"So far," he says, "the four contests have cost me about $25,000. If I contributed the same amount of money to AIDS research or anything else, I doubt it would have made a more significant impact on society or science. I think the development of an artificial intellect could have a tremendous impact on society." He pauses reflectively.

"迄今为止，"他说，"四届比赛花了我大概两万五千美元。但是如果我用同样多的钱投入到艾滋病研究或者其他任何事情上面的话，我怀疑那对社会或者科学而言，其产生的影响并不会比搞人工智能比赛更大。我认为，开发一个人工智慧应该会对社会产生极其巨大的影响。"接着他深思般的停顿了一下。

"It may also help me to sell more of my roll-up plastic lighted portable disco dance floors."

"如此一来也可以就此卖出更多的可卷折的塑料发光便携式狄士高跳舞地板。"

After lunch, I go with the other confederates into a windowless computer lab. The judges have already been sequestered in another room next door, and our only contact with them will be via computer terminals, at least until the contest is over.

午餐过后，我与其他共盟者一起来到一间没有窗户的计算机实验室。鉴定人员早就在隔壁另一个房间里与我们隔离起来了；至少在比赛结束之前，我们与他们的唯一联系方式就是计算机终端。

We sit on blue plastic chairs in front of computer screens, each of which displays a topic heading we had already chosen for our online chat. My topic is cryonics, because I happen to be the vice president of a cryonics organization named CryoCare, and I'm hoping the subject will spark deep, soul-searching discussions about life-and-death issues only a human can deal with meaningfully.

我们在计算机屏幕前的蓝色塑料椅子上就座，每个屏幕上都显示着一条标题，正是我们各自选择的在线聊天将要涉及的话题。我选择的话题是人体冷冻术，因为我恰好是一个名为克罗伊尔关怀（CryoCare）的组织的副主席，而我则希望可以借这个主题引发若干深邃的、探求灵魂的讨论--那种只有人类才能够有效应对的，生死之类的话题。

Linda Tontini sits at the terminal next to mine. Her topic is The Rolling Stones. To my left is another confederate named Frederick Allen, who writes for American Heritage. He's going to chat about classical music.

琳达·通蒂尼坐在我左边的终端面前。她的话题是滚石乐队。我左边的另一位共盟者名叫弗莱德里克·阿兰，他为American Heritage撰写文章。他准备聊关于古典音乐的话题。

To my right, Greg Flakus, from Voice of America, has chosen American history, and Laura Groch, from a local newspaper, will discuss newspaper comics.

在我的右边，来自美国之音（Voice of America）的格雷格·弗拉库斯选择了关于美国历史的话题；来自一家当地报社的劳拉·克罗奇则打算谈论报载漫画。

Five other terminals are unattended, because they will be controlled via modems by AI programs running on remote systems. These programs will discuss their own topics: environmental issues, classic Star Trek, sex education, the O.J. Simpson trial, and cats versus dogs.

另外五台终端跟前没有人，因为它们会被远程系统上的人工智能程序经由调制解调器来控制。这些程序各自将要谈论它们自己选择的话题：环境问题，经典《星际迷航》系列，性教育，O.J.辛普森审判，以及冤家对头猫与狗。

It dawns on me that all the topics - even those of the AI programs - are much more normal than mine. What was I thinking of, picking a wacky subject like cryonics? It's going to make me seem like a nerdy weirdo.

我这才明白，所有的话题——甚至包括那些人工智能程序的话题——都比我选的要平常得多。我当初到底是怎么想的——竟然挑了一个人体冷冻术这样的古怪话题？这会使我看起来像一个讨厌的怪佬儿。

The first question appears on my computer's screen. My judge laboriously types: "What is the difference between cryonics and cryogenics?"

第一个问题出现在我的计算机屏幕上。与我讨论的鉴定人员费神（用计算机键盘）打出如下问题："人体冷冻术与低温学之间的区别是什么？"

There's no way I can give a human-sounding answer to a question as dry as this. To seem human, I need to show emotion - but if my emotions are excessive compared with the question, the effect will be false. It's a trap: the degree to which I can seem human is limited by the humanness of the judge who is interrogating me.

对于这样一个干巴的问题，我根本没办法给出一个含有人性化色彩的回答。为了表现得人性化，我需要表露出一定的情绪--但是如果我针对这个问题所表现出来的情绪过于夸张，反而会适得其反。这是一种无法自拔之境地：我所表现出来的人性化程度取决于询问我的那位鉴定人员的人性化程度。

This is exasperating. But wait; irritability is a human response, so maybe I should play it up. I tell my judge not to ask such boring questions ... the judge makes a snippy response ... and within minutes, we're having a flame war.

这真是气死人了。不过等等，易怒无常正是一个人类特有的反映，因此我或许应该试一试这招儿。我告诉鉴定人员，不要问这种无聊的问题，于是鉴定人员作了一个傲慢的回应，于是几分钟之后，我们展开了一场火药味十足的舌战。

Meanwhile, Frederick Allen has been asked, "Do you know Claude Debussy's middle name?" and on Linda Tontini's screen I see the question, "Complete this: I can't get no.... What?"

与此同时，弗莱德里克·阿兰被鉴定人员问道："你知道克劳德·德彪西的中间名字吗？"；而在琳达·通蒂尼的屏幕上，我看到这样的问题："把这一句接完：I can't get no.... 后面是什么?"

"Sympathy for the devil," she replies humorously. But maybe that's not such a great idea. If her judge doesn't get the joke, she'll seem like a malfunctioning program.

"Sympathy for the devil，"她幽默的答道。但那或许不是个好主意。如果与她讨论的鉴定人员不接受这个笑话，她看上去会像一个出了故障的程序。

After eight minutes, the judges rotate so each of them has a chance to tackle another topic. Linda's new judge comes online, and he asks, "What do you notice if you're close up when Mick Jagger smiles?"

8分钟之后，鉴定人员轮换位置，这样他们每个人都有机会接触另一个话题。与琳达谈话的新一轮鉴定人员上了线，接着他问道："如果你在米克·贾格尔笑的时候贴近他，你会发现什么？"

A devious question, but I know the answer: Jagger has a diamond set in one of his teeth. Should I help her out? Hell, no, she has enough of an advantage already! I turn my attention back to my screen. My new judge asks me, "What is the purpose of cryonics?"

一个绕弯儿的问题，但我知道答案：贾格儿在一个牙齿上镶了一颗钻石。我应该帮她解围吗？该死！不，她的优势已经够多的了！我将注意力转回我自己的屏幕。我的新鉴定人员问我："人体冷冻术的目的是什么？"

I answer, "To be frozen after I die so I can be revived in a future where people are so highly evolved they no longer ask stupid questions."

我答道："是为了在我死后把我冷冻起来，等人们高度进化到不再问蠢问题的未来再把我唤醒。"

After three hours, it's over. We walk into a large room where video screens have been displaying both sides of our conversations for spectators and members of the press. The judges come in (they are all journalists, like the confederates, but they have no special knowledge of computers), and Robert Epstein announces the final results. Each judge has listed the interactions on each topic in order of humanness. Epstein has taken the median score of each topic as its final ranking, from 1 ("most human") to 10 ("least human"). And each judge has tried to draw a line separating the human humans from the fake humans.

三个小时之后，一切结束。我们走进一个大房间，里面的电视屏幕显示着我们与鉴定人员的谈话内容，以便观众和媒介人士观看。这时候鉴定人员走了进来（他们与我的共盟者一样，都是来自新闻媒介的人士，但他们对计算机知之甚少），罗伯特·艾泼斯坦接着宣布了比赛的最后结果。每一位鉴定人员根据人性化程度的高低，就次列出了进行交谈的各个话题。艾泼斯坦将每个话题的中间评级作为其最后的名次，范围在1（最具人性）到10之间（最缺乏人性）。然后，每一位鉴定人员尝试从10位交谈对象中，将真正的人类与由计算机程序冒充的人类分开。

It turns out that none of the programs was smart enough to convince anyone it was human. The program that came closest was the one on sex.

从鉴定人员的判别结果来看，哪个程序都没有能够聪明到让别人以为自己是人类。表现最接近人类的是谈论性话题的那个程序。

Epstein dials a long-distance number on a speakerphone patched into the PA system, and the author of the sex program comes on the line. His name is Thomas Whalen, and he's employed by the Canadian government to develop a system that will give sex advice to shy people. Whalen is 42 and has been working in natural-language processing for 10 years. He wrote his program in C on a SPARCStation, employing a database that contains only about 380 possible responses. Ironically, he never intended it to appear human; he entered the Loebner contest on a mere whim.

艾泼斯坦对着加装在个人助理系统上面的扩音喇叭拨了一个长途电话号码，与"性话题程序"的设计者接通了线。这位设计者的名字叫作托马斯·韦伦，他受雇于加拿大政府部门，为其开发一个系统以便为害羞的人提供性方面的建议。韦伦42岁，至今投身自然语言处理领域已经10年了。他在SPARCStation上面用C语言编写了这个程序，采用了一个只包含380条可能应答语句的数据库。有些讽刺意味的是，他从未刻意要使程序表现得像个人类；参加罗布纳竞赛则纯粹是他一时兴起。

Meanwhile, the least-human program is the one that tried to discuss environmental issues. The programmer turns out to be a 15-year-old boy named Jimmy Lin, who is here in person, all the way from New Hampshire.

相对应的，最缺乏人性的程序是尝试讨论环境问题的那一个。编写该程序的程序员竟是一个叫做吉米·林的15岁男孩，还是独自从新罕布什尔州长途跋涉而来的。

Someone in the audience asks him if he thinks his program is intelligent. "I hesitate to call it AI," he says. "I like to refer to it as a bag of tricks." He says it contains 3,000 preprogrammed answers, its file size is about half a megabyte, it was written in C language, and it runs on a PC.

其中一位观众问道，他是否认为他的程序是有职能的。"我不太想把它称为人工智能，"他说。"我认为应该把它当成是雕虫小技。"他说该程序包含了三千条预编程的应答语句，其文件大小大约有0.5兆字节，使用C语言编写，可以在PC上面运行。

Is he annoyed by being placed last in the contest? He says it doesn't bother him. The programs he was competing with were written by college professors with years of experience, while he produced his in just a couple of months.

在竞赛中名次落尾是否使他感到很郁闷呢？他说他并不在意。与他竞争的其他程序，都是具有多年专业经验的大学教授编写的，而他只花了几个月时间完成了自己的程序。

All the online conversations have been logged during the contest. I have a chance to browse through them before I leave the event, and frankly, I'm disappointed. All the programs tended to repeat themselves, and most of their answers didn't make much sense. (For some samples, see "Come Again?" ).

所有的在线对话都在竞赛过程中被记录下来。在我离开这次竞赛现场之前，我有个机会来浏览这些对话。坦白的说，我感到很失望。所有的程序都容易重复自己，大部分的回答都是莫名其妙的。（其中一些例子，可以参见后文"又来了？"）。

Robert Epstein notes that one impressive entry had to be withdrawn on the morning of the contest because of technical difficulties.

罗伯特·艾泼斯坦提到，有一个相当不错的程序由于技术方面的障碍，在竞赛当天早上不得不退出了比赛。

A team of eight programmers in England had worked on an AI concept that Epstein describes as the most ambitious he's ever seen. Unfortunately, the LISP-based software kept crashing, and they had to abandon the attempt till next year.

在英格兰的八位程序员组成的小组研制的一个人工智能程序，被艾泼斯坦描述为"他所见过的最有竞争实力的一个"。不幸的是，这个基于LISP语言的软件不停的崩溃，该小组只好放弃这次机会，等明年再来。

That contest will be much more challenging. There will be no topic restrictions, and programs will have to converse on any subject that happens to crop up. Will they cope? I have my doubts. For the time being, I think there's no risk of our humanness being successfully simulated by program code.

竞赛会变得更具挑战性。不再有话题上的限制，程序必须就冒然出现的任何话题进行谈论。它们能应付得了吗？我持怀疑态度。暂从目前看来，我认为没有必要担心我们人类特有的人性特色会被程序代码成功的模拟出来。

And speaking of humanness, despite my worst fears, when all the votes were in, I was rated the "most human human" of all. By being moody, irritable, and obnoxious, I came out way ahead of the other four confederates, who were mild-mannered and much more polite.

说道人性化——尽管我做了最坏的打算——当投票结果出来时，我被评为所有人中"最具人性的人类"。由于表现得喜怒无常、暴躁而且令人讨厌，我的表现明显比其他四位共盟者突出——他们都表现得性情温和而且礼貌得多。

CNN was at the contest: its crew taped me receiving an impressive-looking "humanness certificate" signed by Epstein and Loebner. I also received my prize: a life-size cardboard replica of a character from Star Trek.

CNN一直在竞赛现场：我接受写有艾泼斯坦和罗布纳签名，令人影响深刻的"人性资格证书"的一幕被其报道人员录制了下来。我也得到了我的奖品：一个真人大小的《星际迷航》角色纸板制品。

As for Linda Tontini - she was rated the least human of the confederates. In fact, three of the judges thought she was a computer program! The Turing test obviously has its limitations. As any Net user knows, there's a big difference between the way people appear in person and the way they come off online.

而琳达·通蒂尼却被评为共盟者中最缺乏人性的人类。事实上，有三位鉴定人员甚至以为她是计算机程序！显然，图灵测试也有其局限性。正如每位网络用户所知，人们在线上线下的表现有时候是天壤之别。

Before I left the contest, I gave Linda my Star Trek cardboard cutout as a consolation prize. This was a profound and significant personal sacrifice - but, what the hell, it seemed the human thing to do.

在我离开竞赛现场之前，我把我的《星际迷航》纸板的边角料作为安慰奖送给了琳达。这是一种颇具心机且重要的个人付出——但是说到底，这样做才显得比较有人性嘛。

Why AI?

为什么要人工智能？

Despite the humorous side of the Loebner Contest, Robert Epstein is deadly serious about artificial intelligence. As founder of the Cambridge Center for Behavioral Studies, he has led research on how people interact with computers. He looks forward to intelligent "digital assistants" that can act as all-around gophers, finding what we want, evaluating it, summarizing it, and presenting it to us in the most efficient way. "Without a very powerful universal interface," he explains, "there is no way to filter the huge amount of information becoming available to us.

抛开罗布纳有奖竞赛诙谐有趣的一面不谈，罗伯特·艾泼斯坦对人工智能的态度是绝对严肃的。作为剑桥行为研究中心的创始人，他还带动了对于人如何与计算机进行交互的研究。他期盼着有那么一种智能的"数字助理"，它可以如无处不去的钻地鼠那样，找到我想要的信息，对其进行评估、提炼，然后以最为有效的方式呈现给我们。"如果没有一个非常强大的通用界面，"他解释道，"就没有办法从海量的信息中过滤出来，为我们所用。"

"Let's say I want to know about the information in 150 psychology journals. Even with a flock of graduate students working on the problem, I couldn't cover the field properly. But a computer that can pass an unrestricted Turing test could do it easily. It would be trivial."

"比方说，我想从150本心理学杂志中了解相关信息。"即使我和一帮研究生一起来做，我也无法完全覆盖整个领域的内容。但是，一个能够通过不受限图灵测试的计算机就可以轻易完成此事。这对它来说是微不足道的活儿。

When such a system is created, there may be some interesting side effects. "A true AI will be a big, smart entity that will want to replicate itself and protect itself," says Epstein. "It will mutate in some sense or other; copies will split off, and they'll replicate through the Net."

而当这样一个系统创造出来的时候，可能会存在一些有趣的负面效应。"一个真正的人工智能将是一个巨大且聪明的实体，它会想到要进行自我复制和自我保护，"艾泼斯坦说。"它会以某种方式进行变异；拷贝出来的副本会分裂，而且它们会在网络上进行复制。"

Like a virus?

像一个病毒那样吗？

"A virus is not a good analogy. Viruses are incredibly stupid. They're barely alive. A better analogy is an alien intelligence that lands here and tells us it's going to live with us, and we have to adjust. There'll be no way to turn them off, because they'll be moving through wires near the speed of light. What this means for the human species, I have no idea. I just know it has to happen."

"病毒并不是一个妥当的类比。病毒傻得要命，几乎不可能生存下来。比较妥当的类比是一种外星智慧，它们降临到地球并告诉我们说要和我们共存，而我们则必须做出某种协调。人工智能是没有办法关闭的，因为它们通过电线以光速穿行。我不知道这会对人类种族意味着什么。但我认为一切都会发生的。"

How would such a genie get out of the bottle?

这样一个妖怪如何能够破石而出的呢？

"The creators of a true artificial intelligence program will want to protect it, so they'll clone it. And it will have commercial value, so it will turn up in many places very swiftly. All that has to happen is that one of these legitimate clones gets into the hands of someone who adapts it slightly - and zoom, off it goes. Take the kind of network that exists worldwide now, expand the bandwidth by a factor of 10, and it would be trivially easy for one of these entities to multiply itself a millionfold. You'd barely even notice it."

"一个真正的人工智能程序的创造者们必然会保护它，因此他们会将其克隆。这样的程序必然会有商用价值，因此它们会在顷刻之间遍布许多地方。接下来会发生的就是，某个人通过合法途径得到一个程序拷贝，将其稍作改装，然后"咻"的一声，它跑掉了。以目前遍布全球的网络观之，再将带宽扩展10倍，那么其中任何一个实体就能够不费吹灰之力的以百万级的速度单位进行自我繁殖。而你甚至都还注意到这些事情的发生。"

This sounds like a doomsday scenario, but Epstein downplays that aspect. "There would be some difficulties," he says, "but we'd also gain a lot. It could be an intelligence that could help us do things. Maybe we should start to think about it: learning to live with this now."

这听起来好像是世界末日的景象，但是艾泼斯坦并不太在乎这种可能性。"要达到那样的程度是有相当困难的，"他说，"但我们也能在研究道路上有不少收获。也许可以创造出一个智能体来帮我们做些事。或许我们应该开始有这样的认识：从现在起就试着习惯这种状况。"

Of course, right now it's science fiction - but a type Epstein says he has never seen in print. "All the novels I've seen about AI have missed something - the Net. You add that to AI, and you have a fundamentally different world. All of the AIs would be connected to each other virtually 24 hours a day."

当然，这些事情从现在来看还是科学幻想——但是艾泼斯坦说，有一种科幻题材他还从未看到过付印出版。"我看过的所有关于人工智能的小说都漏掉了一件事——网络。如果你把网络环境加之于人工智能，得到的将是一个从根本上完全不同的世界。此时，所有的人工智能体实质上是一天24小时全天候的连接在一起。"

"In some sense they would be separate, but in another sense they would be whole. You would be dealing with a world mind."

"从某种意义上说它们是分开独立的，但从另一种意义上说它们就是一个整体。你要面对的将是一个庞如世界的心智。"

And it doesn't bother him that this could be dangerous?

这种可能出现的危险不让他感到忧虑吗？

"Some people find danger in things they don't understand. I just find a challenge."

"有些人会从他们不理解的东西里发现危险。而我只发觉了一个将要面临的挑战。"

"Come Again?"

"又来了？"

Here are a few of the more offbeat interactions during the fourth Loebner Prize Competition held at California State University, San Marcos.

下面列出了在圣马科斯，加利福尼亚州立大学举办的第4届罗布纳有奖竞赛中几段较为不规则的对话。

The following text is printed exactly as it was created by the judges and the AI programs, including misspellings and typographical errors.

对话的文字完全按照当时鉴定人员和人工智能程序文字输出的情形记录下来，包括拼错的单字和错排。

Topic: The O.J. Simpson Trial

Programmer: Thad Crews, Vanderbilt University

话题：O.J.辛普森审判

程序员：萨德小队，范德比尔特大学

Judge: Do you think cowlings should have been prosecuted as an accessory?

Program: Glad to hear it.

Judge: excuse me?

Program: Come again?

Judge: do you think cowlings should have been prosecuted as an accessory?

Program: No, I do not. Is that OK???

Judge: my opinion isn't at issue. is it possible that OJ can get any semblance of a fair trial, considering the enormous publicity that already is in general circulation?

Program: I think that OJ has a bad temper and he may well have committed the murders.

Judge: do you think he can get a fair trial, under the circumstances?

Program: I certainly hope OJ gets a fair trial, both for his sake and for the sake of Justice as a whole.

Judge: hope is not the issue. do you think he CAN get a fair trial?

Program: Let's move on to another topic, shall we?

Judge: what do YOU think happened to the knife?

Program: OJ purchased a 15-inch (!) stiletto hunting knife a few months before the murders.

Judge: that's not what I asked. what do YOU think happened to the knife?

Program: Let's change the subject. Do you think the media is being fair in its coverage?

Topic: Classic Star Trek

Programmer: Robby Garner, Robitron Software Research Inc.

话题：经典《星际迷航》

程序员：罗比·加纳，罗比登软件研究公司

Judge: Who are the Klingons?

Program: I don't know who you're talking about.

Judge: You're the trekker.

Program: Harry Mudd was one of the more comical characters.

Judge: Harry Mudd? Who was Harry Mudd?

Program: No I haven't.

Judge: Me neither.

Program: Okay, I will.

Judge: Why did you choose to converse about Star Trek?

Program: Their minds were stored in these white globes.

Judge: Whose minds?

Program: Spocks ears are pointed and there was this strange hippy guy in THE WAY TO EDEN that had these bizarre pretzel shaped ears.

Judge: So how big were the ears?

Program: There must have been 70 or 80. I'm not sure.

Judge: Ears?

Program: I'm sure I would know if I could see it on TV.

Topic: Environmental Issues

Programmer: Jimmy Lin, Phillips Exeter Academy

话题：环境问题

程序员：吉米·林，飞利浦斯·埃克塞特学院

Judge: Do you think the Greenhouse Effect is real, or imagined?

Program: The greenhouse effect could kill us. Look at Venus, 800 degrees all the time: typical example of the greenhouse effect.

Judge: But we are not on Venus; and carbon dioxide has been far more plentiful on the Earth in the past, such as during the Mesozoic Age. Life still flourished.

Program: The greenhouse effect could kill us. Look at Venus, 800 degrees all the time: typical example of the greenhouse effect.

Judge: Do you have any special education in environmental matters?

Program: The greenhouse effect could kill us. Look at Venus, 800 degrees all the time: typical example of the greenhouse effect.

Judge: Do you believe there is an ozone depletion problem?

Program: Ozone protects us from the sun's dangerous rays we would die without them!

Judge: But do you think the theory behind ozone depletion is valid?

Program: The greenhouse effect could kill us. Look at Venus, 800 degrees all the time: typical example of the greenhouse effect.

Judge: what hazardous chemicals are found in most rivers?

Program: Industrial waste and chemicals are dumped in the ocean and stream, ultimately endangering ourselves.

Judge: can you name some of those chemicals?

Program: Careful. Industrial wastes lay around the corner.

Judge: what do you think of the state of California's environment?

Program: Reduce, reuse, and recycle. Those are the three major ways one can help our planet.

Judge: what should we reduce?

Program: Careful. Industrial wastes lay around the corner.

Topic: Cats versus Dogs

Programmer: Michael L. Mauldin, Carnegie Mellon University

话题：猫狗大战

程序员：迈克尔·L·摩尔丁，卡奈基·梅隆大学

Judge: Which is more likely to play with a piece of yarn, a cat or dog?

Program: Dogs are great pets, but they can be a lot of work.

Judge: Are dogs cleaner than cats?

Program: We did keep the litter box clean, but she was very stubborn. Since then, we've had no trouble with the other two.

Judge: Do cats and dogs fight over food?

Program: I'm not in the mood.

Judge: If a cat and dog get into a race, which one wins?

Program: But, I don't want which one wins.

Judge: is a dog more affectionate than a cat?

Program: People don't own cats ... it's the other way around.

Topic: Sex (the winning entry)

Programmer: Thomas Whalen, Communications Research Center, Government of Canada

话题：性（该程序藉此获胜）

程序员：托马斯·韦伦，通信研究中心，加拿大政府

Judge: what's the most effective form of cotraception? [Note the misspelling and lack of capitalization, which may have been deliberate, to trip the artificial intelligence program.]

Program: I can not give you an answer to that.

Judge: I meant what's the most effective form of contraception?

Program: The most effective form of birth control is the inter-uterine device or IUD. In the first year of use, six per cent of women who have an IUD installed become pregnant. Much of the effectiveness of the IUD results because it does not require any further action on the part of the woman once it is in place.

Judge: isn't infection a problem with IUD'S?

Program: Currently we know about more than fourteen different sexually transmitted diseases (STD). AIDS is best known because it is incurable and almost always fatal. However, there are other STDs which are also very dangerous if left untreated; and there are other STDs which are incurable. A high proportion of infertile women have lost their ability to conceive as a result of a sexually transmitted disease.

[伟大的先驱图灵给我们留下的宝贵遗产，好像披头士乐队留下的歌曲一样，有着太多需要消化的东西。当许多年前过于乐观的人工智能研究热潮消散在科技日新月异的商业化脚步中的时候，一些深邃的思想和激情却从未曾消散过，仍然在那里积蓄着自己的炙热。发自内心的美好理想夹杂着对未来的深度思考，鼓舞着一批又一批科学家、幻想家、实践家努力探索着人类科技进化历程中那个必将成为里程碑的阶段——"真正的"人工智能。或许有那么一天，罗布纳的子孙们真的可以"懒"一点了。]

（全文完）

注释