[這一次的話題是"圖靈測試"。奇人羅布納發(fā)起的圖靈測試有獎(jiǎng)競賽吸引了不少人的目光，現(xiàn)在我們來看看本文作者作為圖靈測試的人類參與者在比賽前前后后的經(jīng)歷吧。]

What's It Mean to Be Human, Anyway?

"人性化"究竟意味著什么？

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.

關(guān)于判定最具人性之計(jì)算機(jī)的大比拼，查爾斯·普拉特報(bào)告了其最新進(jìn)展；盡管他所擔(dān)心的是，他自己或許就是那個(gè)最缺乏人性的人類[譯注："最缺乏人性的人類"？詳見下文]。

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."

羅伯特·艾潑斯坦給我們大家打氣，"你必須很努力的讓鑒定人員相信你是人類，"，他這樣對(duì)我們說，"而你要做到這一點(diǎn)應(yīng)該不會(huì)太難--因?yàn)槟憔褪侨祟悺?#34;

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.

這位艾潑斯坦是個(gè)有趣的家伙。他穿著Dr.Marten的靴子，黑色牛仔褲，黑色襯衫，帶一條米老鼠領(lǐng)帶，串著耳環(huán)。他稍長的頭發(fā)梳到了后面，又從衣領(lǐng)那里冒了出來。在離圣地亞哥不遠(yuǎn)的圣馬科斯，加利福尼亞州立大學(xué)煥然一新的校園內(nèi)一間淡褐色的會(huì)議室里，我們一行五人正聽他做著介紹。不久我們將被帶到計(jì)算機(jī)終端跟前，在艾潑斯坦的指導(dǎo)下--是的--盡其所能的使自己表現(xiàn)得像一個(gè)人類。

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.

我們的目的是要搞清楚，十位鑒定人員同時(shí)在線的情況下，是否能夠辨出人類與人工智能程序之間的區(qū)別。根據(jù)人性化的程度，參與其中的人和計(jì)算機(jī)程序會(huì)被排出名次；而得分最高的計(jì)算機(jī)程序?qū)槠鋭?chuàng)作者贏得兩千美金。

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.

這樣做的靈感可以追溯至計(jì)算領(lǐng)域最初的時(shí)期。1950年的時(shí)候，計(jì)算先驅(qū)阿蘭·圖靈（Alan Turing）提出，如果一個(gè)計(jì)算機(jī)能夠在形式自由的文字信息交互中成功的模仿人類角色，那么針對(duì)任何現(xiàn)實(shí)的用途，這個(gè)計(jì)算機(jī)就應(yīng)該被認(rèn)為是智能的。

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?

這個(gè)提法很快被稱為"圖靈測試"而廣為人知，并從此激發(fā)了無窮盡的學(xué)術(shù)爭論。一個(gè)非智能的計(jì)算機(jī)能否采用欺騙的手段來效仿人類的反應(yīng)方式呢？"智能（intelligence）"到底意味著什么呢？

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.

爭論從來都沒有過結(jié)果，因?yàn)?-很奇怪的是--從來都沒人做過這個(gè)實(shí)驗(yàn)，直到1991年，一個(gè)叫做休·羅布納的獨(dú)立人士決定花自己的錢來支持這一實(shí)驗(yàn)。羅布納拿出了十萬美元，獎(jiǎng)給第一位能夠發(fā)明這樣一種程序的人——該程序能夠在內(nèi)容不受限制的三小時(shí)對(duì)話過程中騙過十位鑒定人員。

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.

這樣的要求遠(yuǎn)遠(yuǎn)超出了目前所能達(dá)到的水平，因此羅布納又設(shè)立了一個(gè)年度兩萬美元的獎(jiǎng)金，授予人性化程度最接近人類的程序創(chuàng)作者。另外，為了讓測試更為簡化，他還允許每個(gè)接受挑戰(zhàn)的程序員在人機(jī)對(duì)話中挑選單獨(dú)一個(gè)話題進(jìn)行比賽。

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，我便這樣參加了羅布納舉辦的第四次比賽，坐著傾聽那位年度大賽主管羅伯特·艾潑斯坦講話。（羅布納則主要是作為觀察員參與其中。）用實(shí)驗(yàn)的行話來說，我和我的同胞們被稱為"共盟者（confederates）"，因?yàn)槲覀儗⒙?lián)合艾潑斯坦一起，試圖欺騙鑒定人員。我們必須嘗試著盡量表現(xiàn)得人性化一些，以便讓計(jì)算機(jī)們有個(gè)競爭的標(biāo)準(zhǔn)。

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."

艾潑斯坦是一位行為心理學(xué)家，曾在B.F.斯金納的指導(dǎo)下獲得博士學(xué)位。因此可想而知，他針對(duì)我們這樣的參與者發(fā)明了一套小巧的獎(jiǎng)懲系統(tǒng)。"你們不僅要與計(jì)算機(jī)程序進(jìn)行競爭，互相之間也有競爭，"他告訴我們。"你們中的一位將被授予'最具人性的人類'的獎(jiǎng)項(xiàng)。而另有一位將被排名為'最缺乏人性的人類'。"他詭異的笑道，"你的同事搞不好會(huì)向媒體題到這件事情的。"

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。我琢磨著；我意識(shí)到，我當(dāng)然不希望被某家全國性刊物描述為"某人工智能比賽中最缺乏人性的參與者"。只要在線聊天一開始，我無論如何都要表現(xiàn)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，這里有個(gè)蹊蹺的問題：我就是人類，干嘛還要假裝像個(gè)（特別人性化的）人類？我有可能表現(xiàn)得比平常更像人類嗎？如果可能，有什么上佳的策略嗎？

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.

如此這般思索或許不是個(gè)好主意，因?yàn)槠湟龅膯栴}比能夠回答的問題更多，我也可能反而因?yàn)樽晕曳词《楸源笠?。換句話說，如果我刻意要表現(xiàn)得更像人類，結(jié)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.

我環(huán)顧身邊，瞅了瞅另外四位共盟者。他們看上去好像并沒有被類似我這樣的自我分析弄得心神不定。離我最近的年輕女人是一位叫做琳達(dá)·通蒂尼的新聞?dòng)浾?#xff0c;她為一家當(dāng)?shù)貓?bào)社撰寫有關(guān)市政部門施政的文章。她看上去友善、自然、大方——照說應(yīng)該是"計(jì)算機(jī)怪杰（computer geek）"之類的決然對(duì)立面。我看著她興致勃勃的跟人聊著天，心想她不大可能不贏得"最具人性的人類"獎(jiǎng)項(xiàng)。

As for me, I fear the worst.

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?

一通簡報(bào)之后，我被介紹給休·羅布納。他是一個(gè)和藹可親的人，略微偏胖，從灰色胡須和卵形金屬邊眼鏡后面向世界投以仁慈的微笑。他談吐迅捷，話里透著學(xué)究式的精確性。我問他，為什么他愿意出十萬美元尋求一個(gè)機(jī)巧的軟件，那全是他自己的錢嗎？

"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.

"我的父親過逝，雖然不富裕，但仍留給我一些可自由支配的收入，"他說。"而我也有自己的生意做，皇冠工業(yè)（Crown Industries）——我們出品可卷折的塑料發(fā)光便攜式狄士高跳舞地板。"他笑著聳了聳肩，好像他知道這聽起來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.

羅布納也有一些計(jì)算機(jī)編程的個(gè)人經(jīng)驗(yàn)，但他拿的畢竟還是社會(huì)學(xué)的博士頭銜?；蛟S恰緣于此，至少有一位人工智能社群的人士持懷疑的眼光看待他。1994年，一位哈佛的計(jì)算語言學(xué)研究員公開抱怨說，羅布納的獎(jiǎng)賽是在鼓勵(lì)科學(xué)家采用糊弄人的把戲來偽造人類行為，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."

當(dāng)然，羅布納有著不同的看法。"從數(shù)學(xué)的角度來看，我把科學(xué)研究視為一種混沌的人類行為，"他告訴我。"在混沌理論中，最為微小的初始混亂可能導(dǎo)致后續(xù)巨大的下游變化。所以，鑒于我是創(chuàng)建并資助這類競賽的第一人，我可能就成為了其中漲落因素。最終，如果我們有能力創(chuàng)造一個(gè)有感知意識(shí)的計(jì)算機(jī)，那么從這個(gè)計(jì)算機(jī)的角度看來，人類就是其上帝。我想象著，智能機(jī)器們帶著這種關(guān)于半神人類的半神話式的概念，穿行于宇宙之中。這樣的話，或許，"他開心的笑道，"他們會(huì)記得我。"

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，羅布納將銅制獎(jiǎng)?wù)逻B帶兩萬美元的支票授予競賽獲勝者。他拿出獎(jiǎng)?wù)聛碚故窘o我看。獎(jiǎng)?wù)乱幻媸前⑻m·圖靈的潛浮雕，另一面則是羅布納自己。這看起來是不是有一點(diǎn)……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."

"我是被認(rèn)為是妄自尊大，"他欣然同意道。"我也被認(rèn)為是懶惰的。是的，我是很懶。我希望計(jì)算機(jī)能為我做所有的工作——這也是我對(duì)人工智能感興趣的一個(gè)原因。然而正是如此，這個(gè)競賽才吸引了許多關(guān)注的目光，或許我應(yīng)該有權(quán)利變得妄自尊大一些。"

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為之投入的事情，為什么他會(huì)選擇人工智能呢？

"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.

"迄今為止，"他說，"四屆比賽花了我大概兩萬五千美元。但是如果我用同樣多的錢投入到艾滋病研究或者其他任何事情上面的話，我懷疑那對(duì)社會(huì)或者科學(xué)而言，其產(chǎn)生的影響并不會(huì)比搞人工智能比賽更大。我認(rèn)為，開發(fā)一個(gè)人工智慧應(yīng)該會(huì)對(duì)社會(huì)產(chǎn)生極其巨大的影響。"接著他深思般的停頓了一下。

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

"如此一來也可以就此賣出更多的可卷折的塑料發(fā)光便攜式狄士高跳舞地板。"

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.

午餐過后，我與其他共盟者一起來到一間沒有窗戶的計(jì)算機(jī)實(shí)驗(yàn)室。鑒定人員早就在隔壁另一個(gè)房間里與我們隔離起來了；至少在比賽結(jié)束之前，我們與他們的唯一聯(lián)系方式就是計(jì)算機(jī)終端。

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.

我們?cè)谟?jì)算機(jī)屏幕前的藍(lán)色塑料椅子上就座，每個(gè)屏幕上都顯示著一條標(biāo)題，正是我們各自選擇的在線聊天將要涉及的話題。我選擇的話題是人體冷凍術(shù)，因?yàn)槲仪『檬且粋€(gè)名為克羅伊爾關(guān)懷（CryoCare）的組織的副主席，而我則希望可以借這個(gè)主題引發(fā)若干深邃的、探求靈魂的討論--那種只有人類才能夠有效應(yīng)對(duì)的，生死之類的話題。

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.

琳達(dá)·通蒂尼坐在我左邊的終端面前。她的話題是滾石樂隊(duì)。我左邊的另一位共盟者名叫弗萊德里克·阿蘭，他為American Heritage撰寫文章。他準(zhǔn)備聊關(guān)于古典音樂的話題。

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

在我的右邊，來自美國之音（Voice of America）的格雷格·弗拉庫斯選擇了關(guān)于美國歷史的話題；來自一家當(dāng)?shù)貓?bào)社的勞拉·克羅奇則打算談?wù)搱?bào)載漫畫。

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.

另外五臺(tái)終端跟前沒有人，因?yàn)樗鼈儠?huì)被遠(yuǎn)程系統(tǒng)上的人工智能程序經(jīng)由調(diào)制解調(diào)器來控制。這些程序各自將要談?wù)撍鼈冏约哼x擇的話題：環(huán)境問題，經(jīng)典《星際迷航》系列，性教育，O.J.辛普森審判，以及冤家對(duì)頭貓與狗。

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.

我這才明白，所有的話題——甚至包括那些人工智能程序的話題——都比我選的要平常得多。我當(dāng)初到底是怎么想的——竟然挑了一個(gè)人體冷凍術(shù)這樣的古怪話題？這會(huì)使我看起來像一個(gè)討厭的怪佬兒。

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

第一個(gè)問題出現(xiàn)在我的計(jì)算機(jī)屏幕上。與我討論的鑒定人員費(fèi)神（用計(jì)算機(jī)鍵盤）打出如下問題："人體冷凍術(shù)與低溫學(xué)之間的區(qū)別是什么？"

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.

對(duì)于這樣一個(gè)干巴的問題，我根本沒辦法給出一個(gè)含有人性化色彩的回答。為了表現(xiàn)得人性化，我需要表露出一定的情緒--但是如果我針對(duì)這個(gè)問題所表現(xiàn)出來的情緒過于夸張，反而會(huì)適得其反。這是一種無法自拔之境地：我所表現(xiàn)出來的人性化程度取決于詢問我的那位鑒定人員的人性化程度。

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.

這真是氣死人了。不過等等，易怒無常正是一個(gè)人類特有的反映，因此我或許應(yīng)該試一試這招兒。我告訴鑒定人員，不要問這種無聊的問題，于是鑒定人員作了一個(gè)傲慢的回應(yīng)，于是幾分鐘之后，我們展開了一場火藥味十足的舌戰(zhàn)。

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?"

與此同時(shí)，弗萊德里克·阿蘭被鑒定人員問道："你知道克勞德·德彪西的中間名字嗎？"；而在琳達(dá)·通蒂尼的屏幕上，我看到這樣的問題："把這一句接完：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。但那或許不是個(gè)好主意。如果與她討論的鑒定人員不接受這個(gè)笑話，她看上去會(huì)像一個(gè)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分鐘之后，鑒定人員輪換位置，這樣他們每個(gè)人都有機(jī)會(huì)接觸另一個(gè)話題。與琳達(dá)談話的新一輪鑒定人員上了線，接著他問道："如果你在米克·賈格爾笑的時(shí)候貼近他，你會(huì)發(fā)現(xiàn)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?"

一個(gè)繞彎兒的問題，但我知道答案：賈格兒在一個(gè)牙齒上鑲了一顆鉆石。我應(yīng)該幫她解圍嗎？該死！不，她的優(yōu)勢(shì)已經(jīng)夠多的了！我將注意力轉(zhuǎn)回我自己的屏幕。我的新鑒定人員問我："人體冷凍術(shù)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："是為了在我死后把我冷凍起來，等人們高度進(jìn)化到不再問蠢問題的未來再把我喚醒。"

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.

三個(gè)小時(shí)之后，一切結(jié)束。我們走進(jìn)一個(gè)大房間，里面的電視屏幕顯示著我們與鑒定人員的談話內(nèi)容，以便觀眾和媒介人士觀看。這時(shí)候鑒定人員走了進(jìn)來（他們與我的共盟者一樣，都是來自新聞媒介的人士，但他們對(duì)計(jì)算機(jī)知之甚少），羅伯特·艾潑斯坦接著宣布了比賽的最后結(jié)果。每一位鑒定人員根據(jù)人性化程度的高低，就次列出了進(jìn)行交談的各個(gè)話題。艾潑斯坦將每個(gè)話題的中間評(píng)級(jí)作為其最后的名次，范圍在1（最具人性）到10之間（最缺乏人性）。然后，每一位鑒定人員嘗試從10位交談對(duì)象中，將真正的人類與由計(jì)算機(jī)程序冒充的人類分開。

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.

從鑒定人員的判別結(jié)果來看，哪個(gè)程序都沒有能夠聰明到讓別人以為自己是人類。表現(xiàn)最接近人類的是談?wù)撔栽掝}的那個(gè)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.

艾潑斯坦對(duì)著加裝在個(gè)人助理系統(tǒng)上面的擴(kuò)音喇叭撥了一個(gè)長途電話號(hào)碼，與"性話題程序"的設(shè)計(jì)者接通了線。這位設(shè)計(jì)者的名字叫作托馬斯·韋倫，他受雇于加拿大政府部門，為其開發(fā)一個(gè)系統(tǒng)以便為害羞的人提供性方面的建議。韋倫42歲，至今投身自然語言處理領(lǐng)域已經(jīng)10年了。他在SPARCStation上面用C語言編寫了這個(gè)程序，采用了一個(gè)只包含380條可能應(yīng)答語句的數(shù)據(jù)庫。有些諷刺意味的是，他從未刻意要使程序表現(xiàn)得像個(gè)人類；參加羅布納競賽則純粹是他一時(shí)興起。

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.

相對(duì)應(yīng)的，最缺乏人性的程序是嘗試討論環(huán)境問題的那一個(gè)。編寫該程序的程序員竟是一個(gè)叫做吉米·林的15歲男孩，還是獨(dú)自從新罕布什爾州長途跋涉而來的。

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.

其中一位觀眾問道，他是否認(rèn)為他的程序是有職能的。"我不太想把它稱為人工智能，"他說。"我認(rèn)為應(yīng)該把它當(dāng)成是雕蟲小技。"他說該程序包含了三千條預(yù)編程的應(yīng)答語句，其文件大小大約有0.5兆字節(jié)，使用C語言編寫，可以在PC上面運(yùn)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.

在競賽中名次落尾是否使他感到很郁悶?zāi)?#xff1f;他說他并不在意。與他競爭的其他程序，都是具有多年專業(yè)經(jīng)驗(yàn)的大學(xué)教授編寫的，而他只花了幾個(gè)月時(shí)間完成了自己的程序。

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?" ).

所有的在線對(duì)話都在競賽過程中被記錄下來。在我離開這次競賽現(xiàn)場之前，我有個(gè)機(jī)會(huì)來瀏覽這些對(duì)話。坦白的說，我感到很失望。所有的程序都容易重復(fù)自己，大部分的回答都是莫名其妙的。（其中一些例子，可以參見后文"又來了？"）。

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

羅伯特·艾潑斯坦提到，有一個(gè)相當(dāng)不錯(cuò)的程序由于技術(shù)方面的障礙，在競賽當(dāng)天早上不得不退出了比賽。

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.

在英格蘭的八位程序員組成的小組研制的一個(gè)人工智能程序，被艾潑斯坦描述為"他所見過的最有競爭實(shí)力的一個(gè)"。不幸的是，這個(gè)基于LISP語言的軟件不停的崩潰，該小組只好放棄這次機(jī)會(huì)，等明年再來。

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.

競賽會(huì)變得更具挑戰(zhàn)性。不再有話題上的限制，程序必須就冒然出現(xiàn)的任何話題進(jìn)行談?wù)摗Ｋ鼈兡軕?yīng)付得了嗎？我持懷疑態(tài)度。暫從目前看來，我認(rèn)為沒有必要擔(dān)心我們?nèi)祟愄赜械娜诵蕴厣珪?huì)被程序代碼成功的模擬出來。

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.

說道人性化——盡管我做了最壞的打算——當(dāng)投票結(jié)果出來時(shí)，我被評(píng)為所有人中"最具人性的人類"。由于表現(xiàn)得喜怒無常、暴躁而且令人討厭，我的表現(xiàn)明顯比其他四位共盟者突出——他們都表現(xiàn)得性情溫和而且禮貌得多。

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一直在競賽現(xiàn)場：我接受寫有艾潑斯坦和羅布納簽名，令人影響深刻的"人性資格證書"的一幕被其報(bào)道人員錄制了下來。我也得到了我的獎(jiǎng)品：一個(gè)真人大小的《星際迷航》角色紙板制品。

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.

而琳達(dá)·通蒂尼卻被評(píng)為共盟者中最缺乏人性的人類。事實(shí)上，有三位鑒定人員甚至以為她是計(jì)算機(jī)程序！顯然，圖靈測試也有其局限性。正如每位網(wǎng)絡(luò)用戶所知，人們?cè)诰€上線下的表現(xiàn)有時(shí)候是天壤之別。

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.

在我離開競賽現(xiàn)場之前，我把我的《星際迷航》紙板的邊角料作為安慰獎(jiǎng)送給了琳達(dá)。這是一種頗具心機(jī)且重要的個(gè)人付出——但是說到底，這樣做才顯得比較有人性嘛。

Why AI?

為什么要人工智能？

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.

拋開羅布納有獎(jiǎng)競賽詼諧有趣的一面不談，羅伯特·艾潑斯坦對(duì)人工智能的態(tài)度是絕對(duì)嚴(yán)肅的。作為劍橋行為研究中心的創(chuàng)始人，他還帶動(dòng)了對(duì)于人如何與計(jì)算機(jī)進(jìn)行交互的研究。他期盼著有那么一種智能的"數(shù)字助理"，它可以如無處不去的鉆地鼠那樣，找到我想要的信息，對(duì)其進(jìn)行評(píng)估、提煉，然后以最為有效的方式呈現(xiàn)給我們。"如果沒有一個(gè)非常強(qiáng)大的通用界面，"他解釋道，"就沒有辦法從海量的信息中過濾出來，為我們所用。"

"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."

"比方說，我想從150本心理學(xué)雜志中了解相關(guān)信息。"即使我和一幫研究生一起來做，我也無法完全覆蓋整個(gè)領(lǐng)域的內(nèi)容。但是，一個(gè)能夠通過不受限圖靈測試的計(jì)算機(jī)就可以輕易完成此事。這對(duì)它來說是微不足道的活兒。

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."

而當(dāng)這樣一個(gè)系統(tǒng)創(chuàng)造出來的時(shí)候，可能會(huì)存在一些有趣的負(fù)面效應(yīng)。"一個(gè)真正的人工智能將是一個(gè)巨大且聰明的實(shí)體，它會(huì)想到要進(jìn)行自我復(fù)制和自我保護(hù)，"艾潑斯坦說。"它會(huì)以某種方式進(jìn)行變異；拷貝出來的副本會(huì)分裂，而且它們會(huì)在網(wǎng)絡(luò)上進(jìn)行復(fù)制。"

Like a virus?

像一個(gè)病毒那樣嗎？

"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."

"病毒并不是一個(gè)妥當(dāng)?shù)念惐?。病毒傻得要?#xff0c;幾乎不可能生存下來。比較妥當(dāng)?shù)念惐仁且环N外星智慧，它們降臨到地球并告訴我們說要和我們共存，而我們則必須做出某種協(xié)調(diào)。人工智能是沒有辦法關(guān)閉的，因?yàn)樗鼈兺ㄟ^電線以光速穿行。我不知道這會(huì)對(duì)人類種族意味著什么。但我認(rèn)為一切都會(huì)發(fā)生的。"

How would such a genie get out of the bottle?

這樣一個(gè)妖怪如何能夠破石而出的呢？

"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."

"一個(gè)真正的人工智能程序的創(chuàng)造者們必然會(huì)保護(hù)它，因此他們會(huì)將其克隆。這樣的程序必然會(huì)有商用價(jià)值，因此它們會(huì)在頃刻之間遍布許多地方。接下來會(huì)發(fā)生的就是，某個(gè)人通過合法途徑得到一個(gè)程序拷貝，將其稍作改裝，然后"咻"的一聲，它跑掉了。以目前遍布全球的網(wǎng)絡(luò)觀之，再將帶寬擴(kuò)展10倍，那么其中任何一個(gè)實(shí)體就能夠不費(fèi)吹灰之力的以百萬級(jí)的速度單位進(jìn)行自我繁殖。而你甚至都還注意到這些事情的發(fā)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."

這聽起來好像是世界末日的景象，但是艾潑斯坦并不太在乎這種可能性。"要達(dá)到那樣的程度是有相當(dāng)困難的，"他說，"但我們也能在研究道路上有不少收獲。也許可以創(chuàng)造出一個(gè)智能體來幫我們做些事?；蛟S我們應(yīng)該開始有這樣的認(rèn)識(shí)：從現(xiàn)在起就試著習(xí)慣這種狀況。"

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."

當(dāng)然，這些事情從現(xiàn)在來看還是科學(xué)幻想——但是艾潑斯坦說，有一種科幻題材他還從未看到過付印出版。"我看過的所有關(guān)于人工智能的小說都漏掉了一件事——網(wǎng)絡(luò)。如果你把網(wǎng)絡(luò)環(huán)境加之于人工智能，得到的將是一個(gè)從根本上完全不同的世界。此時(shí)，所有的人工智能體實(shí)質(zhì)上是一天24小時(shí)全天候的連接在一起。"

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

"從某種意義上說它們是分開獨(dú)立的，但從另一種意義上說它們就是一個(gè)整體。你要面對(duì)的將是一個(gè)龐如世界的心智。"

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

這種可能出現(xiàn)的危險(xiǎn)不讓他感到憂慮嗎？

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

"有些人會(huì)從他們不理解的東西里發(fā)現(xiàn)危險(xiǎn)。而我只發(fā)覺了一個(gè)將要面臨的挑戰(zhàn)。"

"Come Again?"

"又來了？"

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

下面列出了在圣馬科斯，加利福尼亞州立大學(xué)舉辦的第4屆羅布納有獎(jiǎng)競賽中幾段較為不規(guī)則的對(duì)話。

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

對(duì)話的文字完全按照當(dāng)時(shí)鑒定人員和人工智能程序文字輸出的情形記錄下來，包括拼錯(cuò)的單字和錯(cuò)排。

Topic: The O.J. Simpson Trial

Programmer: Thad Crews, Vanderbilt University

話題：O.J.辛普森審判

程序員：薩德小隊(duì)，范德比爾特大學(xué)

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.

話題：經(jīng)典《星際迷航》

程序員：羅比·加納，羅比登軟件研究公司

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

話題：環(huán)境問題

程序員：吉米·林，飛利浦斯·?？巳貙W(xué)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

話題：貓狗大戰(zhàn)

程序員：邁克爾·L·摩爾丁，卡奈基·梅隆大學(xué)

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

話題：性（該程序藉此獲勝）

程序員：托馬斯·韋倫，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.

[偉大的先驅(qū)圖靈給我們留下的寶貴遺產(chǎn)，好像披頭士樂隊(duì)留下的歌曲一樣，有著太多需要消化的東西。當(dāng)許多年前過于樂觀的人工智能研究熱潮消散在科技日新月異的商業(yè)化腳步中的時(shí)候，一些深邃的思想和激情卻從未曾消散過，仍然在那里積蓄著自己的炙熱。發(fā)自內(nèi)心的美好理想夾雜著對(duì)未來的深度思考，鼓舞著一批又一批科學(xué)家、幻想家、實(shí)踐家努力探索著人類科技進(jìn)化歷程中那個(gè)必將成為里程碑的階段——"真正的"人工智能。或許有那么一天，羅布納的子孫們真的可以"懶"一點(diǎn)了。]

（全文完）

注釋

• pep talk[返回]
  A speech of exhortation, as to a team or staff, meant to instill enthusiasm or bolster morale；鼓舞士氣的話語。
  
  
• have trouble doing[返回]
  做某事感到困難。
  
  
• droll[返回]
  Amusingly odd or whimsically comical；滑稽古怪的。
  
  
• longish[返回]
  稍長的。
  
  
• beige[返回]
  A light grayish brown or yellowish brown to grayish yellow；淡褐色。
  
  
• humanness[返回]
  表示具有人類特質(zhì)；人性化。
  
  
• impersonate[返回]
  To assume the character or appearance of, especially fraudulently； To imitate the appearance, voice, or manner of; mimic；To embody; personify；使人格化；（對(duì)人的）模仿，效仿；賦予人性，賦予人之特質(zhì)。這個(gè)詞的理解范圍比較廣，主要集中在"人"這一意義上。
  
  
• spark[返回]
  To give off sparks；To give an enthusiastic response；To rouse to action；（光電）閃動(dòng)；引發(fā)；激起。
  
  
• 有興趣的讀者可以到www.loebner.net上面看一看。[返回]
  
  
• underwrite[返回]
  To assume financial responsibility for；承諾支付。
  
  
• way beyond[返回]
  遠(yuǎn)遠(yuǎn)的（超過，超出）；
  
  
• 這樣的一種形式或許離真正的"圖靈測試"還相差甚遠(yuǎn)，不過確實(shí)能夠引起更多的人的關(guān)注，帶動(dòng)更多人的參與，這不能不說是一種妥協(xié)。更多的參與和關(guān)注，往往是無心插柳柳成陰，成就了一些意想不到的發(fā)現(xiàn)和創(chuàng)新。[返回]
  
  
• jargon[返回]
  行話
  
  
• in one's effort to do[返回]
  努力做；盡力做。
  
  
• doctorate[返回]
  博士學(xué)位
  
  
• BF SKINNER(1904 - 1990) 1990年8月18日, 斯金納死于白血病，被譽(yù)為Sigmund Freud （西格蒙德·弗洛伊德）之后最偉大的心理學(xué)家之一。[返回]
  
  
• deviously[返回]
  
  
• 艾潑斯坦的確會(huì)玩心理游戲，畢竟誰也不希望"被人公開評(píng)價(jià)為沒有人性"這種多少有些尷尬難堪的事情發(fā)生。[返回]
  
  
• whatever it takes[返回]
  （需要付出的）任何代價(jià)，無論如何都要做的。
  
  
• fake[返回]
  fake sth.；裝作，假裝，偽造。
  
  
• speculation[返回]
  思索。
  
  
• introspection[返回]
  反省。
  
  
• end up doing[返回]
  造成某種狀態(tài)的結(jié)果。
  
  
• city-hall[返回]
  市政廳。
  
  
• spontaneous[返回]
  自然的。
  
  
• outgoing[返回]
  對(duì)人友好的，開朗的。
  
  
• antithesis[返回]
  對(duì)立面。
  
  
• geek[返回]
  怪人，滑稽表演人員。
  
  
• affable[返回]
  和藹可親的。
  
  
• benevolently[返回]
  仁慈的。
  
  
• oval wire-framed[返回]
  橢圓形金屬絲邊框。
  
  
• pedantic[返回]
  學(xué)究的，書生氣的。
  
  
• pledge[返回]
  保證，抵押。
  
  
• discretionary[返回]
  自由支配的。
  
  
• shrug[返回]
  聳肩。
  
  
• skeptically[返回]
  懷疑的。
  
  
• computational linguistics[返回]
  計(jì)算語言學(xué)。
  
  
• cheap tricks[返回]
  小把戲。
  
  
• chaos theory[返回]
  混沌理論。
  
  
• perturbation[返回]
  混亂。
  
  
• downstream[返回]
  下游。
  
  
• precipitate[返回]
  急落，猛沖。
  
  
• sentiment[返回]
  有感知力的，有感情的。
  
  
• semimythic[返回]
  半神話的。
  
  
• demigods[返回]
  半神半人。
  
  
• 混沌理論研究中得到的一個(gè)重要結(jié)果是所謂"蝴蝶效應(yīng)"。1972年12月，混沌理論先驅(qū)者，氣象學(xué)家愛德華·洛倫茲（Edward Lorenz）在華盛頓的美國科學(xué)促進(jìn)會(huì)的一次講演中提出：一只蝴蝶在巴西扇動(dòng)翅膀，有可能會(huì)在美國的德克薩斯引起一場龍卷風(fēng)。他的演講和結(jié)論給人們留下了極其深刻的印象。"蝴蝶效應(yīng)"之說因此變得廣為人知。羅布納希望自己成為那只"致命"的蝴蝶嗎？讓艾薩克·阿西莫夫的機(jī)器人幻象成為現(xiàn)實(shí)？讓手冢治蟲筆下的"大都會(huì)"屹立在新文明之顛？宣起未來黑客帝國中"第二次文明復(fù)興"的"風(fēng)暴"？其實(shí)怎樣想象都不為過--譯者不禁為羅布納廣博承載之心胸和智慧帶來的勇氣而嘆服！說大了，他站在巨人的高度，用巨人的眼睛看世界；說小了，這是不是能夠打醒許多"別里科夫式"的、微縮在自己小思維之中、昏昏度日的人們？[返回]
  
  
• can[返回]
  用來表現(xiàn)"可以做到"這種能力。用過去式could表現(xiàn)出假設(shè)語氣，但在此顯然說話人相當(dāng)肯定和期待，因此could被譯為"應(yīng)該會(huì)"，表示了一種不絕對(duì)的肯定。
  
  
• reflectively[返回]
  沉思狀的。
  
  
  
• sequestere[返回]
  隱退，隔離。
  
  
• 注意譯文中如何將這個(gè)長句拆分的。[返回]
• cryonics[返回]
  人體冷凍術(shù)。
  
  
• soul-searching[返回]
  人體冷凍術(shù)。
  
  
• deal with[返回]
  處理，應(yīng)對(duì)。
  
  
• The Rolling Stones[返回]
  滾石樂隊(duì)，始于20世紀(jì)60年代，與披頭式樂隊(duì)齊名的著名搖滾樂隊(duì)，至今仍活躍在歌壇。
  
  
• American Heritage[返回]
  一本美國刊物。
  
  
• unattended[返回]
  無人的，缺席的。
  
  
• Star Trek[返回]
  西方最受歡迎的科幻影視系列劇集之一，始于20世紀(jì)60年代，通常譯為"星際迷航"。Classic指的是該系列的第一部，之后又衍生出許多系列，至今仍在電視臺(tái)和電影院播映。
  
  
• O.J. Simpson trial[返回]
  1995年轟動(dòng)美國的著名運(yùn)動(dòng)員辛普森案件。辛普森被指控殺害了他的妻子和妻子的一位男友，后來被判無罪釋放，但支付了3350萬美元的民事賠償。
  
  
• wacky[返回]
  古怪的。
  
  
• nerdy[返回]
  討厭的。
  
  
• weirdo[返回]
  古怪的人。
  
  
• human-sounding[返回]
  聽起來像人的。
  
  
• interrogate[返回]
  審問，詢問。
  
  
• exaspertating[返回]
  氣死人的。
  
  
• irritability[返回]
  易怒。
  
  
• play it up[返回]
  施行某種動(dòng)作。
  
  
• snippy[返回]
  傲慢的，暴躁的。
  
  
• flame war[返回]
  激烈的爭論。
  
  
• Claude Debussy[返回]
  著名法國作曲家。
  
  
• middle name[返回]
  （西方姓名的）中間名字。
  
  
• I can't get no[返回]
  滾石樂隊(duì)有一首名曲《(I can't get no) satisfaction》(我無法滿足)。
  
  
• Sympathy for the devil[返回]
  《惡魔的憐憫》，滾石樂隊(duì)的另一首名曲。
  
  
• tackle[返回]
  應(yīng)對(duì)，（著手）處理。
  
  
• Mick Jagger[返回]
  米克·賈格爾，滾石樂隊(duì)的主唱。
  
  
• devious[返回]
  迂回的，偏僻的。
  
  
• 意即 a diamond is set in one of his teeth，不是 diamond set。[返回]
  
  
• revive[返回]
  使蘇醒，使復(fù)活。
  
  
• spectator[返回]
  （現(xiàn)場）觀眾。
  
  
• human humans[返回]
  這里的前一個(gè)human應(yīng)理解為諸如"作為人類的"之類的意思，其實(shí)是對(duì)humans的一種強(qiáng)調(diào)，而并非是作為"具有人性的"這種意義來修飾后面的名詞humans。
  
  
• SPARCStation[返回]
  一種計(jì)算機(jī)系統(tǒng)。
  
  
• mere[返回]
  純粹的，僅僅的。
  
  
• whim[返回]
  一時(shí)興起，反復(fù)無常。
  
  
• Meanwhile[返回]
  這里不能理解為"與此同時(shí)"，僅僅是表示一種相對(duì)應(yīng)的狀態(tài)，并沒有時(shí)間上的意味。
  
  
• New Hampshire[返回]
  美國的新罕布什爾州。
  
  
• hesitate[返回]
  hesitate to do，不太愿意，不太想。
  
  
• couple of months[返回]
  幾個(gè)月；couple of 一般不是指"一對(duì)"或者"兩個(gè)"，而是泛指比較少的數(shù)量。
  
  
• an AI concept[返回]
  concept這里指的是"可作為參賽選手的，人工智能程序的一個(gè)設(shè)計(jì)方案"，不應(yīng)理解為"概念"。
  
  
• ambitious[返回]
  同樣，這個(gè)詞也須根據(jù)上下文來理解，表示"在競賽中最有實(shí)力、最可能獲勝的"。
  
  
• converse[返回]
  交談，談話。
  
  
• crop up[返回]
  突然出現(xiàn)。
  
  
• obnoxious[返回]
  討厭的，（令人）不快的。
  
  
• CNN[返回]
  美國有線新聞網(wǎng)絡(luò)，以提供即時(shí)電視新聞報(bào)導(dǎo)而聞名。
  
  
• 咦？Linda Tontini不是被作者看好會(huì)成為"最具人性的人類"嗎？怎么會(huì)反而變成了"最缺乏人性的人類"？往下看。[返回]
  
• 人的表象特征也有很多層面，不可能同時(shí)完全顯露出來，而正是因此，只要是有限的交流，要就此識(shí)別對(duì)方是一個(gè)"冷漠"的人或者是一個(gè)"熱情"的機(jī)器，似乎真是相當(dāng)困難！想到人工智能的實(shí)現(xiàn)，有時(shí)候也似乎陷入到雞和蛋的怪圈中去了。[返回]
  
  
• cutout[返回]
  剪切塊，切掉的部分。
  
  
• consolation prize[返回]
  安慰獎(jiǎng)。
  
  
• what the hell[返回]
  到底，究竟。
  
  
• deadly[返回]
  用這個(gè)詞表現(xiàn)出一種絕對(duì)的傾向，程度相當(dāng)重。
  
  
• gophers[返回]
  其實(shí)現(xiàn)在已經(jīng)有類似的程序出現(xiàn)，其可以幫助人們?cè)诰W(wǎng)絡(luò)上搜集信息。而這類軟件的發(fā)展，除了需要網(wǎng)絡(luò)具有統(tǒng)一的規(guī)劃和協(xié)議，也正是需要軟件具有一定程度的"智能"。
  
  
• mutate[返回]
  變異。
  
  
• split off[返回]
  分裂，分離。
  
  
• replicate[返回]
  復(fù)制。
  
  
• analogy[返回]
  類似，類推，類比。
  
  
• 其實(shí)人一生中要做數(shù)不清次數(shù)的adjustments，不能讓社會(huì)來適應(yīng)自己，只能是自己去適應(yīng)社會(huì)。有人喜歡抱怨技術(shù)更新太快，會(huì)不會(huì)是自己沒有做好adjustment呢？[返回]
  
  
• swiftly[返回]
  很快的，頃刻之間。
  
  
• 這會(huì)不會(huì)就是黑客帝國的創(chuàng)世紀(jì)篇章呢？這個(gè)大膽的設(shè)想透出了人們對(duì)未來科技極度發(fā)展的憂慮，也形成了一種獨(dú)特的未來世界觀。[返回]
  
  
• downplay[返回]
  不重視，不在意。
  
  
• 令人刮目的看法！或許我們根本無法想象這樣一個(gè)世界！相比之下，恐怕黑客帝國也不過是小兒科了！[返回]
  
  
• 自然語言處理、大腦的秘密、宇宙的奧秘……這一直都是人類想要探求的最為極限的東西，不過或許這樣的探索不會(huì)有絕對(duì)的終點(diǎn)，只會(huì)有一個(gè)相對(duì)的、能夠滿足科學(xué)應(yīng)用的終點(diǎn)。這就好像我們常用"從三維空間考察二維空間"來類比"從四維空間考察三維空間"一樣，我們與我們所探究的東西，永遠(yuǎn)相差一個(gè)級(jí)別……一個(gè)二維空間的"扁平人"如何能夠站在三維空間的角度去考察自己？人類如何用自己的大腦去考究自己的大腦的全部奧秘？應(yīng)該說，這些極限科技的發(fā)展或許真的沒有所有人想象得那么快？[返回]
  
  
• Klingons[返回]
  克林岡人，《星際迷航》劇集中的一個(gè)外星人種族。
  
  
• trekker[返回]
  通常將《星際迷航（Star Trek）》的愛好者稱為treky或者trekker，我們不妨譯之為"星迷"。
  
  
• Spock[返回]
  斯波克，《星際迷航》中的一個(gè)重要角色，帶有尖耳朵的外星人。
  
  
• THE WAY TO EDEN[返回]
  《星際迷航》電視劇其中一集的標(biāo)題。
  
  
• greenhouse effect[返回]
  溫室效應(yīng)。
  
  
• carbon dioxide[返回]
  二氧化碳。
  
  
• Mesozoic Age[返回]
  中生代時(shí)期。
  
  
• Venus[返回]
  金星。
  
  
• ozone[返回]
  臭氧。
  
  
• depletion[返回]
  損耗，消耗。
  
  
• contraception[返回]
  避孕。
  
  
• uterine[返回]
  子宮的。