Why general artificial intelligence will not be realized
为什么通用人工智能将无法实现

The idea of machines that can perform tasks that require intelligence goes at least back to Descartes and Leibniz. However, the project made a major step forward when in the early 1950s it was recognized that electronic computers are not only number-crunching devices, but may be made to manipulate symbols. This was the birth of artificial intelligence (AI) research. It is possible to pursue this goal without assuming that machine intelligence is identical to human intelligence. For example, one of the pioneers in the field, Marvin Minsky, defined AI as: “… the science of making machines do things that would require intelligence if done by men” (quoted from Bolter, 1986, p. 193). This is sometimes called weak AI. However, many AI researcher have pursued the aim of developing AI that is in principle identical to human intelligence, called strong AI. This entails that “…the appropriately programmed computer is a mind, in the sense that computers can be literally said to understand and have other cognitive states” (Searle, 1980, p. 417).
能够执行需要智能的任务的机器的想法至少可以追溯到笛卡尔和莱布尼茨。然而，当 20 世纪 50 年代初人们认识到电子计算机不仅是数字运算设备，还可以用来操作符号时，这一项目取得了重大进展。这是人工智能（AI）研究的诞生。追求这一目标时，并不需要假设机器智能与人类智能完全相同。例如，该领域的先驱之一马文·明斯基将 AI 定义为：“……使机器做那些如果由人来做需要智能的事情的科学”（引自 Bolter, 1986, p. 193）。这有时被称为弱 AI。然而，许多 AI 研究者追求的目标是开发原则上与人类智能相同的 AI，称为强 AI。这意味着“……适当编程的计算机就是一个心灵，在这个意义上，计算机可以说真的理解和拥有其他认知状态”（Searle, 1980, p. 417）。

In this paper, I shall use a different terminology, which is better adapted to the issues that I discuss. Because human intelligence is general, human-like AI is therefore often called artificial general intelligence (AGI). Although AGI possesses an essential property of human intelligence, it may still be regarded as weak AI. It is nevertheless different from traditional weak AI, which is restricted to specific tasks or areas. Traditional weak AI is therefore sometimes called artificial narrow intelligence (ANI) (Shane, 2019, p. 41). Although I will sometimes refer to strong AI, the basic distinction in this article is between AGI and ANI. It is important to keep the two apart. Advances in ANI are not advances in AGI.
在本文中，我将采用一套不同的术语，这套术语更适合我所讨论的问题。由于人类智能是通用的，因此类似人类的人工智能常被称为人工通用智能（AGI）。尽管 AGI 具备人类智能的一个基本属性，它仍可能被视为弱人工智能。然而，它与传统意义上的弱人工智能不同，后者仅限于特定任务或领域。因此，传统弱人工智能有时也被称为人工狭义智能（ANI）（Shane, 2019, p. 41）。虽然我有时会提及强人工智能，但本文的基本区分在于 AGI 与 ANI 之间。将两者区分开来至关重要。ANI 的进展并不等同于 AGI 的进展。

In 1976 Joseph Weizenbaum, at that time professor of informatics at MIT and the creator of the famous program Eliza, published the book Computer Power and Human Reason (Weizenbaum, 1976). As the title indicates, he made a distinction between computer power and human reason. Computer power is, in today’s terminology, the ability to use algorithms at a tremendous speed, which is ANI. Computer power will never develop into human reason, because the two are fundamentlly different. “Human reason” would comprise Aristotle’s prudence and wisdom. Prudence is the ability to make right decisions in concrete situations, and wisdom is the ability to see the whole. These abilities are not algorithmic, and therefore, computer power cannot—and should not—replace human reason. The mathematician Roger Penrose a few years later wrote two major books where he showed that human thinking is basically not algorithmic (Penrose, 1989, 1994).
1976 年，时任麻省理工学院信息学教授、著名程序 Eliza 的创造者约瑟夫·魏岑鲍姆出版了《计算机力量与人类理性》一书（Weizenbaum, 1976）。正如书名所示，他对计算机力量与人类理性进行了区分。用今天的术语来说，计算机力量是指以极快速度运用算法的能力，即 ANI（人工狭义智能）。计算机力量永远不会发展为人类理性，因为两者本质不同。“人类理性”包含了亚里士多德所言的审慎与智慧。审慎是在具体情境中做出正确决策的能力，而智慧则是洞察全局的能力。这些能力并非算法所能及，因此，计算机力量不能也不应取代人类理性。数学家罗杰·彭罗斯几年后撰写了两部重要著作，他在其中论证了人类思维本质上并非算法（Penrose, 1989, 1994）。

However, my arguments will be slightly different from Weizenbaum’s and Penrose’s. I shall pursue a line of arguments that was originally presented by the philosopher Hubert Dreyfus. He got into AI research more or less by accident. He had done work related to the two philosophers Martin Heidegger and Ludwig Wittgenstein. These philosophers represented a break with mainstream Western philosophy, as they emphasized the importance of the human body and practical activity as primary compared to the world of science. For example, Heidegger argued that we can only have a concept of a hammer or a chair because we belong to a culture where we grow up and are able to handle these objects. Dreyfus therefore thought that computers, who have no body, no childhood and no cultural practice, could not acquire intelligence at all (Dreyfus and Dreyfus, 1986, p. 5).
然而，我的论点将与魏岑鲍姆和彭罗斯的略有不同。我将沿着哲学家休伯特·德雷福斯最初提出的论证路线进行探讨。他或多或少是偶然涉足人工智能研究的。他曾从事与哲学家马丁·海德格尔和路德维希·维特根斯坦相关的工作。这些哲学家代表了与西方主流哲学的分道扬镳，因为他们强调人类身体和实践活动的重要性，认为这些比科学世界更为根本。例如，海德格尔认为，我们之所以能拥有锤子或椅子的概念，是因为我们属于一个在其中成长并能够操作这些物品的文化。因此，德雷福斯认为，没有身体、没有童年、也没有文化实践的计算机，根本不可能获得智能（Dreyfus and Dreyfus, 1986, p. 5）。

One of the important places for AI research in the 1950s and 1960s was Rand Corporation. Strangely enough, they engaged Dreyfus as a consultant in 1964. The next year he submitted a critical report titled: “Alchemy and Artificial Intelligence”. However, the leaders of the AI project at Rand argued that the report was nonsense, and should not be published. When it was finally released, it became the most demanded report in the history of Rand Corporation. Dreyfus later expanded the report to the book What Computers Can’t Do (Dreyfus, 1972). In the book he argued that an important part of human knowledge is tacit. Therefore, it cannot be articulated and implemented in a computer program.
20 世纪 50 年代和 60 年代，兰德公司是人工智能研究的重要场所之一。奇怪的是，他们在 1964 年聘请了德雷福斯作为顾问。次年，他提交了一份题为《炼金术与人工智能》的批判性报告。然而，兰德公司的人工智能项目负责人认为该报告毫无意义，不应发表。当它最终发布时，却成为兰德公司历史上最受欢迎的报告。德雷福斯后来将报告扩展为《计算机不能做什么》(Dreyfus, 1972)一书。在书中，他提出人类知识的一个重要部分是隐性的，因此无法在计算机程序中明确表达和实现。

Although Dreyfus was fiercely attacked by some AI researchers, he no doubt pointed to a serious problem. But during the 1980s another paradigm became dominant in AI research. It was based on the idea of neural networks. Instead of taking manipulation of symbols as model, it took the processes in our nervous system and brain as model. A neural network can learn without receiving explicit instructions. Thus it looked as if Dreyfus’ arguments for what computers cannot do were obsolete.
尽管德雷福斯遭到一些人工智能研究者的猛烈抨击，但他无疑指出了一个严重的问题。但在 20 世纪 80 年代，另一种范式在人工智能研究中占据了主导地位。它基于神经网络的概念。不再以符号操作为模型，而是以我们的神经系统和大脑中的过程为模型。神经网络可以在不接收明确指令的情况下进行学习。因此，德雷福斯关于计算机无法做到的事情的论点似乎已经过时了。

The latest off-spring is Big Data. Big Data is the application of mathematical methods to huge amounts of data to find correlations and infer probabilities (Najafabadi et al., 2015). Big Data poses an interesting challenge: I mentioned previously that AGI is not part of strong AI. However, although Big Data does not represent the ambition of developing strong AI, advocates argued that this is not necessary. We do not have to develop computers with human-like intelligence. On the contrary, we may change our thinking to be like the computers. Implicitly this is the message of Viktor Mayer-Schönberger and Kenneth Cukier’s book: Big Data: A Revolution That Will Transform How We Live, Work, and Think (Mayer-Schönberger and Cukier, 2014). The book is optimistic about what Big Data can accomplish and its positive effects on our personal lives and society as a whole.
最新的产物是大数据。大数据是将数学方法应用于海量数据以发现相关性并推断概率的应用（Najafabadi 等，2015）。大数据提出了一个有趣的挑战：我之前提到过，AGI 并不属于强人工智能的范畴。然而，尽管大数据并不代表发展强人工智能的雄心，其支持者认为这并非必要。我们无需开发具备类人智能的计算机。相反，我们可以转变思维，使之更像计算机。这隐含在 Viktor Mayer-Schönberger 和 Kenneth Cukier 的著作《大数据：一场将改变我们生活、工作和思维的革命》（Mayer-Schönberger 和 Cukier，2014）中。该书对大数据所能实现的目标及其对我们个人生活乃至整个社会的积极影响持乐观态度。

Some even argue that the traditional scientific method of using hypotheses, causal models, and tests is obsolete. Causality is an important part of human thinking, particularly in science, but according to this view we do not need causality. Correlations are enough. For example, based on criminal data we can infer where crimes will occur, and use it to allocate police resources. We may even be able to predict crimes before they are committed, and thus prevent them.
有些人甚至认为，传统的科学方法——使用假设、因果模型和测试——已经过时。因果关系是人类思维的重要组成部分，尤其是在科学领域，但根据这种观点，我们并不需要因果关系。相关性就足够了。例如，基于犯罪数据，我们可以推断出犯罪将在哪里发生，并利用这些信息来分配警力资源。我们甚至可能能够在犯罪发生之前预测它们，从而预防犯罪。

If we look at some of the literature on AI research it looks as if there are no limits to what the research can accomplish within a few decades. One example is Mayer-Schönberger and Cukier’s book that I referred to above. Here is one quotation:
如果我们查看一些关于人工智能研究的文献，似乎研究在几十年内可以实现的成就是无限的。上文提到的迈尔-舍恩伯格和库基耶的书就是一个例子。这里有一段引述：

In the future—and sooner than we may think – many aspects of our world will be augmented or replaced by computer systems that today are the sole purview of human judgment (Mayer-Schönberger and Cukier, 2014, p. 12).
未来——而且可能比我们想象的更快——我们世界的许多方面将被计算机系统增强或取代，这些系统目前仅由人类判断掌控（Mayer-Schönberger 和 Cukier，2014 年，第 12 页）。

An example that supports this view is the Obama Administration, which in 2012 announced a “Big Data Research and Development Initiative” to “help solve some of the Nations’s most pressing challenges” (quoted from Chen and Lin, 2014, p. 521).
支持这一观点的一个例子是奥巴马政府，该政府于 2012 年宣布了一项“大数据研究与开发计划”，旨在“帮助解决国家一些最紧迫的挑战”（引自 Chen 和 Lin，2014 年，第 521 页）。

However, when one looks at what has actually been accomplished compared to what is promised, the discrepancy is striking. I shall later give some examples. One explanation for this discrepancy may be that profit is the main driving force, and, therefore, many of the promises should be regarded as marketing. However, although commercial interests no doubt play a part, I think that this explanation is insufficient. I will add two factors: First, one of the few dissidents in Silicon Valley, Jerone Lanier, has argued that the belief in scientific immortality, the development of computers with super-intelligence, etc., are expressions of a new religion, “expressed through an engineering culture” (Lanier, 2013, p. 186). Second, when it is argued that computers are able to duplicate a human activity, it often turns out that the claim presuppose an account of that activity that is seriously simplified and distorted. To put it simply: The overestimation of technology is closely connected with the underestimation of humans.
然而，当我们将实际取得的成就与承诺相比时，差异是惊人的。稍后我会举一些例子。这种差异的一个解释可能是利润是主要驱动力，因此，许多承诺应被视为营销手段。然而，尽管商业利益无疑起到了一定作用，我认为这种解释并不充分。我将补充两个因素：首先，硅谷少数异议者之一杰伦·拉尼尔（Jerone Lanier）认为，对科学永生的信仰、开发具有超智能的计算机等，是一种新宗教的表达，“通过工程文化表现出来”（拉尼尔，2013 年，第 186 页）。其次，当有人声称计算机能够复制人类活动时，往往发现这种说法基于对该活动的严重简化和扭曲的描述。简而言之：对技术的高估与对人类能力的低估密切相关。

I shall start with Dreyfus’ main argument that AGI cannot be realized. Then I shall give a short account of the development of AI research after his book was published. Some spectacular breakthroughs have been used to support the claim that AGI is realizable within the next few decades, but I will show that very little has been achieved in the realization of AGI. I will then argue that it is not just a question of time, that what has not been realized sooner, will be realized later. On the contrary, I argue that the goal cannot in principle be realized, and that the project is a dead end. In the second part of the paper I restrict myself to arguing that causal knowledge is an important part of humanlike intelligence, and that computers cannot handle causality because they cannot intervene in the world. More generally, AGI cannot be realized because computers are not in the world. As long as computers do not grow up, belong to a culture, and act in the world, they will never acquire human-like intelligence.
我将从德雷福斯的主要论点开始，即通用人工智能（AGI）无法实现。然后，我将简要介绍他的书出版后人工智能研究的发展。一些引人注目的突破被用来支持 AGI 在未来几十年内可以实现的主张，但我将展示在实现 AGI 方面取得的进展微乎其微。接着，我将论证这不仅仅是一个时间问题，即未能早日实现的，日后也未必能实现。相反，我认为这个目标在原则上无法实现，这个项目是一条死胡同。在论文的第二部分，我将仅限于论证因果知识是类人智能的重要组成部分，而计算机无法处理因果关系，因为它们无法干预世界。更广泛地说，AGI 无法实现是因为计算机不在世界中。只要计算机不成长、不属于某种文化并在世界中行动，它们就永远不会获得类人智能。

Finally, I will argue that the belief that AGI can be realized is harmful. If the power of technology is overestimated and human skills are underestimated, the result will in many cases be that we replace something that works well with something that is inferior.
最后，我认为相信 AGI 能够实现是有害的。如果高估了技术的力量而低估了人类的技能，结果往往是我们用劣质的东西取代了原本运作良好的事物。

Dreyfus placed AI into a philosophical tradition going back to Plato. Plato’s theory of knowledge was constructed on the ideal of mathematics, in particular geometry. Geometry is not about material bodies, but ideal bodies. We can only acquire real knowledge, episteme, by turning the attention away from the material world, and direct it “upwards”, to the world of ideal objects. Plato even criticized the geometers for not understanding their own trade, because they thought they were “… doing something and their reasoning had a practical end, and the subject were not, in fact, pursued for the sake of knowledge” (Plato, 1955, p. 517). Skills are merely opinion, doxa, and are relegated to the bottom of his knowledge hierarchy.
德雷福斯将人工智能置于一个可追溯至柏拉图的哲学传统中。柏拉图的知识理论建立在数学的理想之上，尤其是几何学。几何学不涉及物质实体，而是关于理想实体。我们只有将注意力从物质世界转移开，并“向上”引导至理想对象的世界，才能获得真正的知识，即 episteme（真知）。柏拉图甚至批评几何学家不理解他们自己的行当，因为他们认为自己在“做某事，且他们的推理具有实际目的，而事实上，这门学科并不是为了知识本身而追求的”（柏拉图，1955 年，第 517 页）。技能仅仅是意见，即 doxa（意见），被降级到他知识等级的底层。

According to this view, a minimum requirement for something to be regarded as knowledge is that it can be formulated explicitly. Western philosophy has by and large followed Plato and only accepted propositional knowledge as real knowledge. An exception is what Dreyfus called the “anti-philosophers” Merleau-Ponty, Heidegger, and Wittgenstein. He also referred to the scientist and philosopher Michael Polanyi. In his book, Personal Knowledge Polanyi introduced the expression tacit knowledge^{Footnote 1}. Most of the knowledge we apply in everyday life is tacit. In fact, we do not know which rules we apply when we perform a task. Polanyi used swimming and bicycle riding as examples. Very few swimmers know that what keeps them afloat is how they regulate their respiration: When they breathe out, they do not empty their lungs, and when they breathe in, they inflate their lungs more than normal.
根据这一观点，将某物视为知识的最低要求是它能够被明确地表述出来。西方哲学大体上遵循柏拉图的观点，仅将命题性知识视为真正的知识。德雷福斯所称的“反哲学家”梅洛-庞蒂、海德格尔和维特根斯坦是个例外。他还提到了科学家兼哲学家迈克尔·波兰尼。在其著作《个人知识》中，波兰尼引入了“隐性知识”这一表述。我们在日常生活中应用的大部分知识都是隐性的。事实上，我们并不清楚在执行任务时遵循了哪些规则。波兰尼以游泳和骑自行车为例。很少有游泳者知道，让他们浮在水面上的是他们如何调节呼吸：呼气时，他们不会将肺部完全排空，吸气时，他们会比平常更多地充盈肺部。

Something similar applies to bicycle riding. The bicycle rider keeps his balance by turning the handlebar of the bicycle. To avoid falling to the left, he moves the handlebar to the left, and to avoid falling to the right he turns the handlebar to the right. Thus he keeps his balance by moving along a series of small curvatures. According to Polanyi a simple analysis shows that for a given angle of unbalance, the curvature of each winding is inversely proportional to the square of the speed of the bicycle. But the bicycle rider does not know this, and it would not help him become a better bicycle rider (Polanyi, 1958, p. 50). Later Polanyi formulated this insight as “…we can know more than we can tell” (Polanyi, 2009, p. 4, italics in original).
类似的情况也适用于骑自行车。骑自行车的人通过转动自行车的把手来保持平衡。为了避免向左倾斜，他会将把手向左转动；为了避免向右倾斜，则会将把手向右转动。因此，他通过沿着一系列小弧度移动来保持平衡。根据 Polanyi 的分析，对于给定的不平衡角度，每个转弯的弧度与自行车速度的平方成反比。但骑自行车的人并不知道这一点，即便知道也无助于他成为更好的骑手（Polanyi, 1958, p. 50）。后来，Polanyi 将这一见解表述为“……我们能知道的比我们能说出的更多”（Polanyi, 2009, p. 4，原文为斜体）。

However, the important thing in Polanyi’s contribution is that he argued that skills are a precondition for articulate knowledge in general, and scientific knowledge in particular. For example, to carry out physical experiments requires a high degree of skills. These skills cannot just be learned from textbooks. They are acquired by instruction from someone who knows the trade.
然而，波兰尼贡献中的重要之处在于，他提出技能是清晰知识，尤其是科学知识的先决条件。例如，进行物理实验需要高度的技能。这些技能不能仅从书本中学习，而是通过内行人士的指导获得的。

Similarly, Hubert Dreyfus, in cooperation with his brother Stuart, developed a model for acquisition of skills. At the lowest level the performer follows explicit rules. The highest level, expert performance, is similar to Polanyi’s account of scientific practice. An important part of expertise is tacit. The problem facing the development of expert systems, that is, systems that enable a computer to simulate expert performance (for example medical diagnostics) is that an important part of the expert knowledge is tacit. If experts try to articulate the knowledge they apply in their performance, they normally regress to a lower level. Therefore, according to Hubert and Stuart Dreyfus, expert systems are not able to capture the skills of an expert performer (Dreyfus and Dreyfus, 1986, p. 36). We know this phenomenon from everyday life. Most of us are experts on walking. However, if we try to articulate how we walk, we certainly give a description that does not capture the skills involved in walking.
同样地，休伯特·德雷福斯与其兄弟斯图尔特合作，提出了一个技能获取模型。在最低层次，执行者遵循明确的规则。而最高层次，即专家级表现，类似于波拉尼对科学实践的描述。专业知识的一个重要部分是隐性的。专家系统开发面临的问题，即让计算机模拟专家表现（例如医疗诊断）的系统，在于专家知识的很大一部分是隐性的。如果专家试图阐述他们在表现中所应用的知识，他们通常会退回到一个较低的层次。因此，根据休伯特和斯图尔特·德雷福斯的观点，专家系统无法捕捉到专家执行者的技能（德雷福斯和德雷福斯，1986 年，第 36 页）。我们从日常生活中也了解这一现象。大多数人都是行走的专家。然而，如果我们试图描述我们是如何行走的，我们给出的描述肯定无法涵盖行走所涉及的技能。

However, after Hubert Dreyfus published What Computers Can’t Do, AI has made tremendous progress. I will mention three “milestones” that have received public attention and contributed to the impression that AGI is just “around the corner”.
然而，在休伯特·德雷福斯发表《计算机不能做什么》之后，人工智能取得了巨大进步。我将提到三个引起公众关注并促成 AGI“近在咫尺”印象的“里程碑”。

The first “milestone” is IBM’s chess-playing computer Deep Blue, which is often regarded as a breakthrough when it in 1997 defeated the world champion of chess, Garri Kasparov. However, Deep Blue was an example of ANI; it was made for a specific purpose. Although it did extremely well in an activity that requires intelligence when performed by humans, no one would claim that Deep Blue had acquired general intelligence.
第一个“里程碑”是 IBM 的国际象棋计算机深蓝（Deep Blue），它在 1997 年击败了国际象棋世界冠军加里·卡斯帕罗夫（Garri Kasparov），常被视为一次突破。然而，深蓝是 ANI 的一个例子；它是为特定目的而设计的。尽管它在需要人类智能的活动中表现出色，但没有人会声称深蓝获得了通用智能。

The second is IBM’s computer Watson. It was developed with the explicit goal of joining the quiz show Jeopardy!. This is a competition where the participants are given the answers, and are then supposed to find the right questions. They may for example be presented the answer: “This ‘Father of Our Country’ didn’t really chop down a cherry tree”. The correct question the participants are supposed to find is: ”Who was George Washington?”^{Footnote 2}
第二个是 IBM 的计算机 Watson。它的开发明确目标是加入智力竞赛节目《危险边缘！》。在这个比赛中，参与者会得到答案，然后需要找出正确的问题。例如，他们可能会看到这样的答案：“这位‘我们国家的父亲’并没有真的砍倒一棵樱桃树”。参与者需要找到的正确问题是：“乔治·华盛顿是谁？” ^{Footnote 2}

Jeopardy! requires a much larger repertoir of knowledge and skills than chess. The tasks cover a variety of areas, such as science, history, culture, geography, and sports, and may contain analogies and puns. It has three participants, competing to answer first. If you answer incorrectly, you will be drawn and another of the participants will have the opportunity to answer. Therefore, the competition requires both knowledge, speed, but also the ability to limit oneself. The program has enjoyed tremendous popularity in the United States since it began in 1964, and is viewed by an average of seven million people (Brynjolfson and McAfee, 2014, p. 24).
《危险边缘！》要求参赛者具备比国际象棋更广泛的知识和技能储备。题目涵盖科学、历史、文化、地理及体育等多个领域，并可能包含类比和双关语。节目中有三名参赛者竞相抢答，若回答错误，将失去机会，由其他参赛者继续作答。因此，比赛不仅考验知识储备与反应速度，还需参赛者具备自我控制能力。自 1964 年开播以来，该节目在美国广受欢迎，平均每期观众达七百万人（Brynjolfson and McAfee, 2014, p. 24）。

Watson communicates using natural language. When it participated in Jeopardy! it was not connected to the Internet, but had access to 200 million pages of information (Susskind and Susskind, 2015, p. 165; Ford, 2015, p. 98ff). In 2011 it beat the two best participants in Jeopardy!, Ken Jennings and Brad Rutter. Jennings had won 74 times in a row in 2004, and had received over $3 million in total. Rutter had won over Jennings in 2005, and he too had won over $3 million. In the 2-day competition, Watson won more than three times as much as each of its human competitors.
沃森使用自然语言进行交流。在参加《危险边缘》节目时，它并未接入互联网，但能够访问 2 亿页信息（Susskind 和 Susskind，2015 年，第 165 页；Ford，2015 年，第 98 页及以后）。2011 年，它击败了《危险边缘》节目中的两位顶尖选手肯·詹宁斯和布拉德·鲁特。詹宁斯曾在 2004 年连续赢得 74 场比赛，总共获得了超过 300 万美元的奖金。鲁特则在 2005 年战胜了詹宁斯，同样赢得了超过 300 万美元的奖金。在这场为期两天的比赛中，沃森的获胜金额是其每位人类对手的三倍以上。

Although Watson was constructed to participate in Jeopardy!, IBM had further plans. Shortly after Watson had won Jeopardy! the company announced that they would apply the power of the computer to medicine: It should become an AI medical super-doctor, and revolutionize medicine. The basic idea was that if Watson had access to all medical literature (patients’ health records, textbooks, journal articles, lists of drugs, etc.) it should be able to offer a better diagnosis and treatment than any human doctor. In the following years IBM engaged in several projects, but the success has been rather limited. Some have just been closed down, and some have failed spectacularly. It has been much more difficult than originally assumed to construct an AI doctor. Instead of super-doctors IBM’s Watson Health has turned out AI assistants that can perform in routine tasks (Strickland, 2019).
尽管沃森是为了参加《危险边缘》而构建的，IBM 还有更远大的计划。沃森赢得《危险边缘》后不久，公司宣布将把该计算机的强大能力应用于医学领域：它应成为一位 AI 医疗超级医生，彻底革新医学。基本理念是，如果沃森能够访问所有医学文献（患者的健康记录、教科书、期刊文章、药物列表等），它应该能提供比任何人类医生更准确的诊断和治疗方案。在接下来的几年里，IBM 参与了多个项目，但成功相当有限。有些项目已关闭，有些则遭遇了显著的失败。构建一个 AI 医生远比最初设想的要困难得多。IBM 的沃森健康部门最终推出的不是超级医生，而是能在常规任务中表现的 AI 助手（Strickland, 2019）。

The third “milestone” is Alphabet’s AlphaGo. Go is a board game invented more than 2000 years ago in China. The complexity of the game is regarded as even larger than chess, and it is played by millions of people, in particular in East Asia. In 2016, AlphaGo defeated the world champion Le Sedol in five highly publicized matches in Seoul, South Korea. The event was documented in the award-winning film AlphaGo (2017, directed by Greg Kohs).
第三个“里程碑”是 Alphabet 的 AlphaGo。围棋是一种 2000 多年前在中国发明的棋盘游戏。其复杂性被认为甚至超过国际象棋，数百万人参与其中，尤其是在东亚地区。2016 年，AlphaGo 在韩国首尔举行的五场备受瞩目的比赛中击败了世界冠军李世石。这一事件被记录在获奖影片《AlphaGo》（2017 年，由 Greg Kohs 执导）中。

AlphaGo is regarded as a milestone in AI research because it was an example of the application of a strategy called deep reinforcement learning. This is reflected in the name of the company, which is DeepMind. (After a reconstruction of Google, Google and DeepMind are subsidiaries of Alphabet.) It is an example of an approach to AI research that is based on the paradigm of artificial neural networks. An artificial neural network is modeled on neural networks. Our brain contains approximately one hundred billion neurons. Each neuron is connected to approximately 1000 neurons via synapses. This gives around a hundred trillion connections in the brain. An artificial neural network consists of artificial neurons, which are much simpler than natural neurons. However, it has been demonstrated that when many neurons are connected in a network, a large enough network can in theory carry out any computation. What is practically possible, is of course a different question (Minsky, 1972, p. 55; Tegmark, 2017, p. 74).
AlphaGo 被视为人工智能研究的一个里程碑，因为它是一个名为深度强化学习策略应用实例。这一点在公司名称中有所体现，即 DeepMind。（在谷歌重组后，谷歌和 DeepMind 成为 Alphabet 的子公司。）这是基于人工神经网络范式的人工智能研究方法的示例。人工神经网络是对神经网络的模拟。我们的大脑包含约一千亿个神经元。每个神经元通过突触与大约 1000 个神经元相连。这使得大脑中的连接数量达到约一百万亿。人工神经网络由人工神经元组成，它们比自然神经元简单得多。然而，已经证明，当许多神经元在网络中连接时，理论上足够大的网络可以执行任何计算。实际上可能实现的内容，当然是一个不同的问题（Minsky, 1972, p. 55; Tegmark, 2017, p. 74）。

Neural networks are particularly good at pattern recognition. For example, to teach a neural network to identify a cat in a picture we do not have to program the criteria we use to identify a cat. Humans have normally no problems distinguishing between, say, cats and dogs. To some degree we can explain the differences, but very few, probably no one, will be able to give a complete list of all criteria used. It is for the most part tacit knowledge, learned by examples and counter-examples. The same applies to neural networks.
神经网络特别擅长模式识别。例如，要教会神经网络识别图片中的猫，我们并不需要编程设定识别猫的标准。人类通常能毫无困难地区分猫和狗。在某种程度上，我们可以解释这些差异，但很少有人，甚至可能没有人，能给出所有使用标准的完整列表。这在很大程度上是隐性知识，通过正面和反面的例子学习得来。神经网络也是如此。

A deep learning neural network consists of different layers of artificial neurons. For example, a network may have four different layers. In analyzing a picture the first layer may identify pixels as light and dark. The second layer may identify edges and simple shapes. The third layer may identify more complex shapes and objects, and the fourth layer may learn which shapes can be used to identify an object (Jones, 2014, p. 148).
深度学习神经网络由不同层次的人工神经元组成。例如，一个网络可能有四个不同的层次。在分析图片时，第一层可能将像素识别为明暗。第二层可能识别边缘和简单形状。第三层可能识别更复杂的形状和物体，而第四层可能学习哪些形状可用于识别物体（Jones, 2014, p. 148）。

The advantage is that one must not formulate explicitly the criteria used, for example, to identify a face. This is the crucial difference between the chess program Deep Blue and AlphaGo. Although a human chess player uses a mixture of calculation and intuition to evaluate a particular board position, Deep Blue was programmed to evaluate numerous possible board positions, and decide the best possible in a given situation. Go is different. In many cases expert players relied on intuition only, and were only able to describe a board position as having “good shape” (Nielsen, 2016). I have mentioned earlier that one of Hubert Dreyfus’ main arguments against AGI was that human expertise is partly tacit, and cannot be articulated. AlphaGo showed that computers can handle tacit knowledge, and it therefore looks as if Dreyfus’ argument is obsolete. However, I will later show that this “tacit knowledge” is restricted to the idealized “world of science”, which is fundamentally different from the human world that Dreyfus had in mind.
优势在于，人们无需明确制定用于识别面孔的标准。这是国际象棋程序“深蓝”与“阿尔法围棋”之间的关键区别。尽管人类棋手在评估特定棋盘局势时会结合计算与直觉，但“深蓝”被编程来评估众多可能的棋局，并在给定情境下决定最佳走法。围棋则不同，许多情况下，专业棋手仅依赖直觉，且只能将棋局描述为具有“好形”（Nielsen, 2016）。我之前提到，休伯特·德雷福斯反对通用人工智能（AGI）的主要论点之一是人类专业知识部分属于隐性知识，无法言传。“阿尔法围棋”表明计算机能够处理隐性知识，因此似乎德雷福斯的论点已过时。然而，我随后将揭示，这种“隐性知识”仅限于理想化的“科学世界”，与德雷福斯心中的人类世界有本质区别。

The advantage of not having to formulate explicit rules comes at a price, though. In a traditional computer program all the parameters are explicit. This guarantees full transparency. In a neural network this transparency is lost. One often does not know what parameters are used. Some years ago a team at University of Washington developed a system that was trained to distinguish between huskies and wolves. This is a task that requires considerable skill, because there is not much difference between them. In spite of this the system had an astonishing 90% accuracy. However, the team discovered that the system recognized wolves because there was snow on most of the wolf pictures. The team had invented a snow detector! (Dingli, 2018).
无需制定明确规则的优势是有代价的。在传统计算机程序中，所有参数都是明确的。这保证了完全的透明度。而在神经网络中，这种透明度丧失了。人们常常不知道使用了哪些参数。几年前，华盛顿大学的一个团队开发了一个系统，该系统经过训练能够区分哈士奇和狼。这是一项需要相当技巧的任务，因为它们之间差异不大。尽管如此，该系统还是达到了惊人的 90%准确率。然而，团队发现系统之所以能识别狼，是因为大多数狼的图片中有雪。团队发明了一个雪探测器！(Dingli, 2018)。

AlphaGo was developed by the researchers of DeepMind, and is regarded as a big success. DeepMind’s approach was also applied successfully to the Atari games Breakout and Space Invaders, and the computer game Starcraft. However, it turned out that the system lacks flexibility, and is not able to adapt to changes in the environment. It has even turned out to be vulnerable to tiny changes. Because real world problems take place in a changing world, deep reinforcement learning has so far found few commercial applications. Research and development is costly, but DeepMind’s losses of 154 million dollars in 2016, 341 million in 2017, and 572 million in 2018 are hardly a sign of success (Marcus, 2019).
AlphaGo 由 DeepMind 的研究人员开发，被视为一大成功。DeepMind 的方法也成功应用于 Atari 游戏《打砖块》和《太空入侵者》，以及电脑游戏《星际争霸》。然而，事实证明该系统缺乏灵活性，无法适应环境变化，甚至对微小变化显得脆弱。由于现实世界的问题发生在不断变化的环境中，深度强化学习迄今商业应用寥寥。研发成本高昂，但 DeepMind 在 2016 年亏损 1.54 亿美元，2017 年 3.41 亿美元，2018 年 5.72 亿美元，这很难说是成功的标志（Marcus, 2019）。

The challenge of neural networks is that they must be able to handle huge amounts of data. For example AlphaGo was first trained on 150,000 games played by competent Go players. Then it was improved by repeatedly playing against earlier versions of itself.
神经网络的挑战在于它们必须能够处理大量数据。例如，AlphaGo 首先在 15 万场由优秀围棋选手进行的对局中进行训练。然后，它通过反复与早期版本的自己对弈来改进。

Computers’ increasing ability to process and store huge amounts of data has led to what is called the “data explosion”, or even “data deluge”. Already in 2012 it was estimated that Google processed around 24 petabytes (24 × 10¹⁵) of data every day. This is thousands of times the amount of printed material in the US Library of Congress (Mayer-Schönberger and Cukier, 2014, p. 8). At the same time it was estimated that 2.5 exabytes (2.5 × 10¹⁸ bytes) were created in the world per day. This is estimated to be approximately half of all the words ever spoken by humans. This amount of data is beyond human imagination, and it is the background for the Big Data approach.
计算机处理和存储海量数据的能力不断增强，导致了所谓的“数据爆炸”，甚至“数据洪流”。早在 2012 年，据估计谷歌每天处理大约 24 拍字节（24 × 10^15 字节）的数据。这相当于美国国会图书馆印刷材料数量的数千倍（Mayer-Schönberger 和 Cukier，2014 年，第 8 页）。同时，据估计全球每天产生 2.5 艾字节（2.5 × 10^18 字节）的数据。这大约相当于人类有史以来所有言语的一半。这种数据量超出了人类的想象，也是大数据方法产生的背景。

Although Big Data analysis may be regarded as a supplemental method for data analysis for large amounts of data, typically terabytes and petabytes, it is sometimes presented as a new epistemological approach. Viktor Mayer-Schönberger and Kenneth Cukier start their book Big Data with the example of a flu that was discovered in 2009. It combined elements from viruses that caused bird flu and swine flu, and was given the name H1N1. It spread quickly, and within a week public health agencies around the world feared a pandemic. Some even feared a pandemic of the same size as the 1918 Spanish flu that killed millions. There was no vaccine against the virus, and the only thing the health authorities could do was to try to slow it down. But to be able to do that, they had to know where it had already spread. Although doctors were requested to inform about new cases, this information would take 1–2 weeks to reach the authorities, primarily because most patients do not consult a doctor immediately after the appearance of the symptoms of the disease.
尽管大数据分析可能被视为对大量数据（通常是 TB 和 PB 级别）进行分析的补充方法，但它有时也被呈现为一种新的认识论方法。维克托·迈尔-舍恩伯格和肯尼思·库克耶在他们的著作《大数据》中，以 2009 年发现的一种流感为例开篇。这种流感结合了导致禽流感和猪流感的病毒元素，被命名为 H1N1。它迅速传播，一周之内，全球的公共卫生机构就担心会发生大流行。有些人甚至担心会出现与 1918 年西班牙流感规模相当的大流行，那次流感导致数百万人死亡。当时没有针对该病毒的疫苗，卫生当局唯一能做的就是试图减缓其传播速度。但要做到这一点，他们必须了解病毒已经传播到了哪些地方。尽管医生被要求报告新病例，但这些信息需要 1-2 周才能到达当局，主要是因为大多数患者在出现疾病症状后不会立即就医。

However, researchers at Google had just before this outbreak invented a method that could much better predict the spread of the flu. Google receives more than three billion search queries every day, and save them all. People who have symptoms of flu tend to search the internet for information on flu. Therefore, by looking at search items that are highly correlated with flu, the researchers could map the spread of flu much quicker than the health authorities (Mayer-Schönberger and Cukier, 2014, p. 2).
然而，就在此次流感爆发前，谷歌的研究人员发明了一种能更准确预测流感传播的方法。谷歌每天接收超过三十亿条搜索查询，并全部保存下来。有流感症状的人倾向于在网上搜索流感相关信息。因此，通过分析与流感高度相关的搜索条目，研究人员能够比卫生部门更快地绘制出流感的传播图（Mayer-Schönberger 和 Cukier，2014 年，第 2 页）。

Mayer-Schönberger and Cukier regard this a a success story. But this may be an example of what is sometimes called “the fallacy of initial success”. In 2013 the model reported twice as many doctor visits for influenza-like illnesses as the Centers for Disease Control and Prevention, which is regarded as a reliable source of information. The initial version of the model had probably included seasonal data that were correlated with the flu, but were causally unrelated. Therefore, the model was part a flu detector and part a winter detector. Although the model has been updated, its performance has been far below the initial promises (Lazer et al., 2014; Shane, 2019, p. 171).
迈尔-舍恩伯格与库基耶视此为成功案例。但这或许正是所谓“初期成功谬误”的例证。2013 年，该模型报告的流感样疾病就诊次数是疾病控制与预防中心的两倍，后者被视为可靠信息来源。模型初始版本可能纳入了与流感相关但因果上无关的季节性数据，因此，模型既是流感探测器，也是冬季探测器。尽管模型已更新，其表现远未达初期承诺（Lazer 等人，2014；Shane，2019，第 171 页）。

The previous examples just involved correlations. However, in the sciences and also in everyday life, we want to have causal relations. For example, one of the big questions of our time involves causal knowledge: Is the global warming that we observe caused by human activity (the release of greenhouse gases into the atmosphere), or is it just natural variations?
之前的例子仅涉及相关性。然而，在科学以及日常生活中，我们渴望了解因果关系。例如，我们这个时代的一个重大问题就涉及因果知识：我们观察到的全球变暖是由人类活动（向大气中排放温室气体）引起的，还是仅仅是自然变化的结果？

The nature of causal relationships has been discussed for centuries, in particular after David Hume criticized the old idea of a necessary relationship between cause and effect. According to Hume we have to be satisfied with the observation of regularities. His contemporary Immanuel Kant, on the contrary, argued that causal relationships are a prerequisite for the acquisition of knowledge. It is necessary that every effect has a cause.
因果关系的本质已经被讨论了数个世纪，尤其是在大卫·休谟批评了原因与结果之间存在必然联系的旧观念之后。根据休谟的观点，我们必须满足于对规律性的观察。而与他同时代的伊曼努尔·康德则相反，他认为因果关系是获取知识的先决条件。每一个结果都必须有一个原因。

However, instead of going into the philosophical discussion about causal relationships, which has continued until this day, it is more fruitful to see how we identify a causal relationship. The philosopher John Stuart Mill formulated some rules (he called them “canons”) that enable us to identify causal relationships. His “second canon” which he also called “the method of difference” is the following:
然而，与其深入探讨关于因果关系的哲学讨论（这一讨论一直持续至今），不如看看我们如何识别因果关系更为有益。哲学家约翰·斯图尔特·密尔制定了一些规则（他称之为“准则”），使我们能够识别因果关系。他的“第二准则”，也被称为“差异法”，如下所述：

If an instance in which the phenomenon under investigation occurs, and an instance in which it does not occur, have every circumstance in common save one, that one occurring only in the former; the circumstance in which alone the two instances differ, is the effect, or the cause, or an indispensable part of the cause, of the phenomenon (Mill, 1882, p. 483).
如果被研究的现象发生的一个实例和不发生的一个实例，在所有情况上都相同，只有一个情况不同，且该情况仅出现在前者中；那么，这两个实例唯一不同的情况，就是该现象的结果、原因或原因的不可或缺部分（Mill, 1882, p. 483）。

From this quotation we see that the distinguishing mark of a causal relationship is a 100% correlation between cause and effect. But most correlations are not causal. For example, there is a high positive correlation between gasoline prices and my age, but there is obviously no causal relationship between the two. A correlation may therefore be an indication of a causal link, but it need not be.
从这段引述中，我们看出因果关系的标志性特征是原因与结果之间百分之百的相关性。然而，大多数相关性并非因果关系。例如，汽油价格与我的年龄之间存在高度正相关，但显然二者之间并无因果关系。因此，相关性可能暗示着因果联系，但并非必然如此。

Therefore, in the quotation above, Mill requires that the two cases be equal in all circumstances. But still we can only decide that the difference between the two is either the cause or the effect, because correlation is a symmetrical mathematical relationship: If A is correlated with B, B is correlated with A. In contrast, if C is the cause of E, E is not the cause of C. Therefore, correlations cannot distinguish between cause and effect. To make this distinction we need something more: The cause produces, or at least brings about, the effect. Therefore, we may remove the assumed cause, and see if the effect disappears.
因此，在上述引文中，密尔要求这两种情况在所有情况下都相等。但我们仍然只能断定两者之间的差异是原因或结果，因为相关性是一种对称的数学关系：如果 A 与 B 相关，那么 B 也与 A 相关。相反，如果 C 是 E 的原因，E 就不是 C 的原因。因此，相关性无法区分因果关系。为了做出这种区分，我们需要更多的东西：原因产生或至少带来结果。因此，我们可以移除假设的原因，看看结果是否消失。

We have a famous example of this procedure from the history of medicine (more specifically epidemiology). Around 1850 there was a cholera epidemic in London. John Snow was a practicing physician. He noted that there was a connection between what company people got the water from and the frequency of cholera. The company Southwark and Vauxhall, which had water intake at a polluted site in the Thames, had a high frequency of cholera cases. Another company, the Lambeth Company, had significantly lower numbers. Although this was before the theory of bacteria as the cause of disease, he assumed that the cause of the disease was found in the water. Here are Snow’s numbers:
医学史上（更具体地说是流行病学）有一个著名的例子。大约在 1850 年，伦敦爆发了霍乱疫情。约翰·斯诺是一位执业医师。他注意到人们从哪家公司获取水源与霍乱的发病率之间存在联系。Southwark 和 Vauxhall 公司在泰晤士河的一个污染地点取水，霍乱病例的发生率很高。另一家公司，Lambeth 公司，发病率明显较低。尽管这是在细菌致病理论提出之前，他推测疾病的病因存在于水中。以下是斯诺的数据：

After Snow had sealed a water pump that he believed contained infectious water, the cholera epidemic ended (Sagan, 1996, p. 76).
在斯诺密封了一个他认为含有传染性水的水泵后，霍乱疫情结束了（Sagan, 1996, p. 76）。

If the effect always follows the cause, everything else equal, we have deterministic causality. However, many people smoke cigarettes without contracting cancer. The problem is that in practice some uncertainty is involved. Therefore, we need a definition of a causal relationship when we have <100% correlation between cause and effect. According to this definition a probabilistic cause is not always followed by the effect, but the frequency of the effect is higher than when the cause is not present. This can be written as P(E|C) > P(E|not-C). P(E|C) is a conditional probability, and can be read as “the probability of E, given C”.
如果结果总是紧随原因之后，在其他条件相同的情况下，我们就有了确定性因果关系。然而，许多人吸烟并未患上癌症。问题在于实践中总存在一些不确定性。因此，当原因与结果之间相关性不足 100%时，我们需要一个因果关系的定义。根据这一定义，概率性原因并不总是导致结果发生，但结果出现的频率高于原因不存在时。这可以表示为 P(E|C) > P(E|非 C)。P(E|C)是条件概率，可理解为“在 C 发生的条件下，E 发生的概率”。

However, although this looks straightforward, it is not. An example will show this. After World War II there were many indications that cigarette smoking might cause lung cancer. It looks as if this question might be decided in a straightforward way: One selects two groups of people that are similar in all relevant aspects. One group starts smoking cigarettes and another does not. This is a simple randomized, clinical trial. Then one checks, after 10 years, 20 years, 30 years, and so on, and see if there is a difference in the frequency of lung cancer in the two groups.
然而，尽管这看起来简单明了，事实却并非如此。一个例子将说明这一点。第二次世界大战后，有许多迹象表明吸烟可能导致肺癌。这个问题看似可以通过一种直接的方式解决：选择两组在所有相关方面都相似的人，一组开始吸烟，另一组则不吸。这是一个简单的随机临床试验。然后在 10 年、20 年、30 年等时间点进行检查，看看两组中肺癌的发生率是否存在差异。

Of course, if cigarette smoking is as dangerous as alleged, one would not wait decades to find out. Therefore, one had to use the population at hand, and use correlations: One took a sample of people with lung cancer and another sample of the population that did not have cancer and looked at different background factors: Is there a higher frequency of cigarette smokers among the people who have contracted lung cancer than people who have not contracted lung cancer. The main criterium is “ceteris paribus”, everything else equal.
当然，如果吸烟真的如所声称的那样危险，人们不会等上几十年才发现。因此，必须利用现有的人口数据，并运用相关性分析：选取一组肺癌患者样本和另一组未患癌症的群体样本，考察不同的背景因素：在患有肺癌的人群中，吸烟者的比例是否高于未患肺癌的人群。主要的标准是“其他条件相同”（ceteris paribus）。

One thing is to acknowledge that we sometimes have to use correlations to find causal relations. It is quite another thing to argue that we do not need causes at all. Nevertheless, some argue that we can do without causal relationship. In 2008 the chief editor of Wired Magazine, Chris Anderson, wrote an article with the title: ”The End of Theory: The Data Deluge Makes the Scientific Method Obsolete”. In the article he argued that correlations are sufficient. We can use huge amount of data and let statistical algorithms find patterns that science cannot. He went even further, and argued that the traditional scientific method, of using hypotheses, causal models and tests, is becoming obsolete (Anderson, 2008).
一件事是承认我们有时必须使用相关性来发现因果关系。另一件事则是争论我们根本不需要原因。然而，有些人认为我们可以不需要因果关系。2008 年，《连线》杂志的主编克里斯·安德森写了一篇文章，标题为：“理论的终结：数据洪流使科学方法过时”。在文章中，他提出相关性就足够了。我们可以使用大量的数据，让统计算法发现科学无法发现的模式。他甚至更进一步，认为使用假设、因果模型和测试的传统科学方法正在变得过时（安德森，2008 年）。

According to Mayer-Schönberger and Cukier, Anderson’s article unleashed a furious debate, “… even though Anderson quickly backpedaled away from his bolder claims” (Mayer-Schönberger and Cukier, 2014, p. 71). But even if Anderson modified his original claims, Mayer-Schönberger and Cukier agree that in most cases we can do without knowing causal relations: “Big Data is about what, not why. We don’t always need to know the cause of a phenomenon; rather, we can let data speak for itself” (Mayer-Schönberger and Cukier, 2014, p. 14). Later they formulate it in this way: “Causality won’t be discarded, but it is being knocked off its pedestal as the primary fountain of meaning. Big data turbocharges non-causal analyses, often replacing causal investigations” (Mayer-Schönberger and Cukier, 2014, p. 68). Pearl and Mackenzie put it this way: “The hope—and at present, it is usually a silent one—is that the data themselves will guide us to the right answers whenever causal questions come up” (Pearl and Mackenzie, 2018, p. 16). I have to add that Pearl and Mackenzie are critical of this view.
根据迈尔-舍恩伯格和库基耶的观点，安德森的文章引发了一场激烈的辩论，“……尽管安德森很快就从他更大胆的声明中退缩了”（迈尔-舍恩伯格和库基耶，2014 年，第 71 页）。但即使安德森修改了他最初的声明，迈尔-舍恩伯格和库基耶也同意，在大多数情况下，我们可以在不知道因果关系的情况下进行：“大数据是关于什么，而不是为什么。我们并不总是需要知道现象的原因；相反，我们可以让数据自己说话”（迈尔-舍恩伯格和库基耶，2014 年，第 14 页）。后来他们这样表述：“因果关系不会被抛弃，但它作为意义的主要源泉的地位正在被削弱。大数据加速了非因果分析，往往取代了因果调查”（迈尔-舍恩伯格和库基耶，2014 年，第 68 页）。珀尔和麦肯齐这样说道：“希望——目前通常是无声的——是数据本身会在因果问题出现时引导我们找到正确的答案”（珀尔和麦肯齐，2018 年，第 16 页）。我必须补充的是，珀尔和麦肯齐对这种观点持批评态度。

Anderson was not the first to argue that science can do without causes. At the end of the 19th century one of the pioneers of modern statistics, Karl Pearson, argued that causes have no place in science (Pearl and Mackenzie, 2018, p. 67) and at the beginning of the 20th century one of the most influential philosophers of that century, Bertrand Russell, wrote the article “On the Notion of Cause” where he called “the law of causality” a “relic of a bygone age” (Russell, 1963, p. 132). For example, when bodies move under the mutual attraction of gravity, nothing can be called a cause, and nothing an effect according to Russell. There is “merely a formula” (Russell, 1963, p. 141). He might have added that Newton’s mechanics had been reformulated by Joseph-Louis Lagrange and William Hamilton to an abstract theory without the concept of force.
安德森并非首位主张科学无需因果关系的学者。19 世纪末，现代统计学的先驱之一卡尔·皮尔逊（Karl Pearson）就提出，因果关系在科学中并无立足之地（Pearl and Mackenzie, 2018, p. 67）。而 20 世纪初，极具影响力的哲学家伯特兰·罗素（Bertrand Russell）在其文章《论因果概念》（“On the Notion of Cause”）中，将“因果律”称为“过去时代的遗物”（Russell, 1963, p. 132）。例如，罗素认为，在物体因万有引力相互吸引而运动时，既无原因可言，也无结果可论，存在的“仅仅是一个公式”（Russell, 1963, p. 141）。他或许还可以补充道，牛顿力学已被约瑟夫-路易·拉格朗日（Joseph-Louis Lagrange）和威廉·哈密顿（William Hamilton）重新表述为一套不包含力概念的抽象理论。

However, Russell looked for causality at the wrong place. He took simply Newton’s theory for granted, and had forgotten that Newton himself subscribed to what in his time was called “experimental philosophy”. Physics is no doubt an experimental science, and to carry out experiments the physicist must be able to move around, to handle instruments, to read scales, and to communicate with other physicists. As the physicist Roger Newton has pointed out, a physicist “…effectively conducts experiments by jiggling one part of Nature and watching how other parts respond” (Newton 1997, p. 142). To find out if A causes B, it is important for “A to be under our control” (Newton, 1997, p. 144, italics in original).
然而，罗素在错误的地方寻找因果关系。他简单地认为牛顿的理论理所当然，却忘记了牛顿本人也信奉他那个时代被称为“实验哲学”的观点。物理学无疑是一门实验科学，而要进行实验，物理学家必须能够四处移动、操作仪器、读取刻度，并与其他物理学家交流。正如物理学家罗杰·牛顿所指出的，物理学家“……通过搅动自然的一部分并观察其他部分的反应来有效地进行实验”（牛顿，1997 年，第 142 页）。要确定 A 是否引起 B，重要的是“A 在我们的控制之下”（牛顿，1997 年，第 144 页，原文为斜体）。

I have already quoted Pearl’s and Mackenzie’s book The Book of Why (2018). The main argument in the book is that to create humanlike intelligence in a computer, the computer must be able to master causality. They ask the question:
我已经引用了珀尔和麦肯齐的书《为什么之书》（2018 年）。书中的主要论点是，要在计算机中创造出类似人类的智能，计算机必须能够掌握因果关系。他们提出了一个问题：

How can machines (and people) represent causal knowledge in a way that would enable them to access the necessary information swiftly, answer questions correctly, and do it with ease, as a three-year-old child can? (Pearl and Mackenzie, 2018, p. 37).
机器（和人）如何能以一种能够快速获取必要信息、正确回答问题并轻松做到的方式表示因果知识，就像三岁小孩那样？（Pearl 和 Mackenzie，2018 年，第 37 页）。

They call this the “mini-Turing test”. It has the prefix “mini” because it is not a full Turing test, but is confined to causal relations.
他们称之为“迷你图灵测试”。之所以加上“迷你”前缀，是因为它并非完整的图灵测试，而是仅限于因果关系。

Before I go into the mini-Turing test I will briefly recall the Turing test. In the article “Computing Machinery and Intelligence” (Turing, 1950). Alan Turing asked the question: How can we determine if computers have acquired general intelligence? He starts by saying that the question he tries to answer is: “Can machines think?”, but instead of going into the question of what intelligence is, he sets up a kind of game. In the game a questioner can communicate with a computer and a human being. He has to communicate through a key-board, so he does not know who is the computer and who is the human. The point is that the machine pretends to be human, and it is the job of the questioner to decide which of the two is the computer and who is the human. If the questioner is unable to distinguish, we can say that the computer is intelligent. Turing called this the “imitation game”, but it is later known as the “Turing test”. If the computer passes the test, it has, according to Turing, acquired general intelligence.
在深入探讨迷你图灵测试之前，我将简要回顾一下图灵测试。在文章《计算机器与智能》（图灵，1950 年）中，艾伦·图灵提出了一个问题：我们如何确定计算机是否获得了通用智能？他首先表示，他试图回答的问题是：“机器能思考吗？”，但他并没有深入探讨什么是智能，而是设计了一种游戏。在这个游戏中，提问者可以与一台计算机和一个人进行交流。他必须通过键盘进行交流，因此他不知道谁是计算机，谁是人类。关键在于机器假装成人类，而提问者的任务是判断两者中谁是计算机，谁是人类。如果提问者无法区分，我们可以说计算机是智能的。图灵称之为“模仿游戏”，但后来被称为“图灵测试”。如果计算机通过了测试，根据图灵的说法，它就获得了通用智能。

According to Pearl and Mackenzie a minimum requirement to pass the Turing test is that the computer is able to handle causal questions. From an evolutionary perspective this makes sense. Why Homo sapiens has been so successful in the history of evolution is of course a complex question. Many factors have been involved, and the ability to cooperate is probably one of the most important. However, a decisive step took place between 70,000 and 30,000 years ago, what the historian Yuval Harari calls the Cognitive Revolution (Harari, 2014, p. 23). According to Harari the distinguishing mark of the Cognitive Revolution is the ability to imagine something that does not exist. Harari’s example is the ivory figurine “the lion man” (or “the lioness woman”) that was found in the Stadel Cave in Germany, and is approximately 32,000 years old. It consists of a human body and the head of a lion.
根据珀尔和麦肯齐的说法，通过图灵测试的最低要求是计算机能够处理因果问题。从进化角度来看，这是有道理的。为什么智人在进化史上如此成功当然是一个复杂的问题。许多因素都参与其中，而合作的能力可能是最重要的因素之一。然而，在 7 万到 3 万年前发生了一个决定性的步骤，历史学家尤瓦尔·赫拉利称之为认知革命（Harari, 2014, p. 23）。根据赫拉利的说法，认知革命的标志是能够想象不存在的事物。赫拉利的例子是在德国施塔德尔洞穴中发现的象牙雕像“狮人”（或“狮女”），距今大约 3.2 万年。它由一个人体和一个狮子头组成。

Pearl and Mackenzie refer to Harari, and add that the creation of the lion man is the precursor of philosophy, scientific discovery, and technological innovation. The fundamental precondition for this creation is the ability to ask and answer questions of the form: “What happens if I do ……?” (Pearl and Mackenzie, 2018, p. 2).
珀尔和麦肯齐提到哈拉里，并补充说，狮人雕像的创作是哲学、科学发现和技术创新的先驱。这一创作的基本前提是能够提出并回答“如果我……会发生什么？”这类问题（Pearl and Mackenzie, 2018, p. 2）。

The mini-Turing test is restricted to causal relationships. If computers can handle causal knowledge, they will pass this test. However, the problem is that in this regard computers have not made any progress for decades: “Just as they did 30 years ago, machine-learning programs (including those with deep neural networks) operate almost entirely in an associative mode…” (Pearl and Mackenzie, 2018, p. 30). But this is insufficient. To answer causal questions we must be able to intervene in the world.
迷你图灵测试仅限于因果关系。如果计算机能够处理因果知识，它们就能通过这项测试。然而，问题在于在这方面计算机几十年来没有任何进展：“正如 30 年前一样，机器学习程序（包括那些拥有深度神经网络的）几乎完全在关联模式下运行……”（Pearl 和 Mackenzie，2018 年，第 30 页）。但这还不够。要回答因果问题，我们必须能够对世界进行干预。

According to Pearl and Mackenzie the root of the problem is that computers do not have a model of reality. However, the problem is that nobody can have a model of reality. Any model can only depict simplified aspects of reality. The real problem is that computers are not in the world, because they are not embodied.
根据珀尔和麦肯齐的观点，问题的根源在于计算机没有现实模型。然而，问题在于没有人能拥有现实模型。任何模型都只能描绘现实的简化方面。真正的问题是计算机不在世界中，因为它们没有实体化。

Pearl and Mackenzie are right in arguing that computers cannot pass the mini-Turing test because they cannot answer causal question. And I shall argue that they cannot pass the full Turing test because they are not in the world, and, therefore, they have no understanding. A few examples from the Turing test will show this.
Pearl 和 Mackenzie 认为计算机无法通过迷你图灵测试，因为它们不能回答因果问题，这是正确的。而我则认为，它们无法通过完整的图灵测试，因为它们不在世界中，因此没有理解力。图灵测试中的几个例子将证明这一点。

There is an annual competition where the award (Loebner Prize) is given to the AI program most similar to a human being. The competition is the Turing test, but gold or silver medals have never been awarded. The program Mitsuku won in 2013, 2016, 2017, 2018, and 2019.
每年都有一场竞赛，奖项（Loebner Prize）会颁发给最像人类的 AI 程序。该竞赛是图灵测试，但从未颁发过金牌或银牌。Mitsuku 程序在 2013 年、2016 年、2017 年、2018 年和 2019 年获奖。

The philosopher Luciano Floridi recounts how he joined the judging panel when the competition was first held in England in 2008. One of the judges started with the question: “If we take each other’s hand, whose hand am I holding then?” The computer replied by talking about something completely different: “We live in eternity. So, yeah, no. We don’t believe.” Another question was: “The four capital cities of England are three, Manchester and Liverpool. What’s wrong with this sentence?” The computer had no meaningful answer (Floridi, 2014, p. 133).
哲学家卢西亚诺·弗洛里迪讲述了他在 2008 年该竞赛首次在英格兰举行时加入评委小组的经历。一位评委以一个问题开场：“如果我们彼此牵手，那么我握着的是谁的手？”电脑却回答了一些完全不相干的内容：“我们活在永恒中。所以，是的，不。我们不相信。”另一个问题是：“英格兰的四个首都是三个，曼彻斯特和利物浦。这句话有什么问题？”电脑没有给出有意义的答案（弗洛里迪，2014 年，第 133 页）。

The conversation that Floridi refers to, took place more than 10 years ago. I was curious to see if the program had improved. I have tried it out several times, and it has not improved much. Below is an example. When Mitsuku in 2008 was asked: “If we take each other’s hand, whose hand am I holding then?” the computer failed. This time it came out with the right answer. However, it did not take long before it failed. In the printout below “Millie” can either be the Mitsuku computer, or a human. At the end of the conversation one is supposed to guess if one talked to a computer or to a human being. It was not difficult to determine that I had talked to a computer.
弗洛里迪提到的对话发生在 10 多年前。我很好奇这个程序是否有所改进。我试了几次，发现它并没有太大进步。下面是一个例子。2008 年，当被问到“如果我们互相握手，那我握着的是谁的手？”时，Mitsuku（电脑）未能正确回答。而这次它给出了正确答案。然而，没过多久它又出错了。在下面的打印输出中，“Millie”可能是 Mitsuku 电脑，也可能是人类。对话结束时，参与者需要猜测自己是在与电脑还是人类交谈。不难判断，我是在与电脑对话。

Here is the “conversation”:
以下是“对话”：

Mitsuku chatbot Welcome Ragnar, now talking. * Topic is ’Turing Test’ * Set by admin (1 day ago)
Mitsuku 聊天机器人 欢迎 Ragnar，现在开始对话。* 主题是“图灵测试” * 由管理员设置（1 天前）

<Ragnar> If I shake your hand, whose hand am I holding?
如果我握你的手，我握着的是谁的手？

<Millie> I will be holding yours adn you will be holding mine. What’s with the dumb questions?
我会握着你的手，你也会握着我的。这些愚蠢的问题是怎么回事？

<Ragnar> Why is the question dumb?
为什么这个问题很蠢？

<Millie> I want to know everything about you.
我想了解关于你的一切。

<Ragnar> But you did not explain why you regarded the question as dumb.
但你并没有解释为什么你认为这个问题很蠢。

<Millie> Sorry, I must have forgot. What was your question again?
抱歉，我一定是忘了。你的问题是什么来着？

<Ragnar> If we shake hands, whose hand am I holding?
如果我们握手，我握着的是谁的手？

<Millie> We would be holding each other’s hand.
我们会手牵着手。

<Ragnar> And why is that a dumb question?
为什么这是个愚蠢的问题？

<Millie> Why do I exist? (MitsukuHomepage. I have kept Mitsuku’s misprinting)
我为什么存在？（MitsukuHomepage。我保留了 Mitsuku 的拼写错误）

Computers fail because they are not in the world. Mitsuku characterized the first question as dumb, but could not explain why. Any child would be able to do that.
计算机失败是因为它们不在这个世界上。Mitsuku 将第一个问题描述为愚蠢，但无法解释原因。任何孩子都能做到这一点。

However, the competition rules of the Loebner Prize have been changed. The aim of getting computers to pass the Turing test has been given up, because “… chatbots are typically so quickly unmasked that the prize was always one for ’best of’” (LoebnerPrize).
然而，勒布纳奖的竞赛规则已经改变。让计算机通过图灵测试的目标已被放弃，因为“……聊天机器人通常很快就会被识破，所以该奖项一直是‘最佳表现者’的奖项”（LoebnerPrize）。

The main thesis of this paper is that we will not be able to realize AGI because computers are not in the world. However, it is crucial that we clarify what is meant by “world”.
本文的主要论点是，由于计算机不在世界中，我们将无法实现 AGI。然而，澄清“世界”的含义至关重要。

As the historian of science Alexandre Koyré has pointed out, the most important achievement of the scientific revolution of the 17th century was the replacement of Aristotelian science by an abstract scientific ideal (“paradigm”) (Koyré 1978, pp. 38–39). Koyré argued convincingly that Galileo was basically a Platonist (Koyré, 1968). As in the case of Plato, the key was mathematics. According to Galileo the book of nature is written in the language of mathematics (Galilei, 1970, p. 237). Therefore, Galileo’s world is an abstract and idealized world, close to Plato’s world of ideas.
正如科学史学家亚历山大·柯瓦雷所指出的，17 世纪科学革命最重要的成就是用抽象的科学理想（“范式”）取代了亚里士多德科学（Koyré 1978, pp. 38–39）。柯瓦雷令人信服地论证了伽利略本质上是一位柏拉图主义者（Koyré, 1968）。如同柏拉图的情况，关键在于数学。伽利略认为，自然之书是用数学语言写成的（Galilei, 1970, p. 237）。因此，伽利略的世界是一个抽象且理想化的世界，接近柏拉图的思想世界。

The system that comes closest to this ideal world is our solar system, what Isaac Newton called “the system of the world”. Newton’s mechanics became the model for all science. The best expression of this ideal was given by the French mathematician Pierre Simon de Laplace. He argued that there is in principle no difference between a planet and a molecule. If we had complete knowledge of the state of the universe at one time, we could in principle determine the state at any previous and successive time (Laplace, 1951, p. 6). This means that the universe as a whole can be described by an algorithm. Turing referred to this passage from Laplace in his article “Computing Machinery and Intelligence”, and added that the predictions he (Turing) was considering, were nearer to practicability than the predictions considered by Laplace, which comprised the universe as a whole (Turing, 1950, p. 440).
最接近这一理想世界的系统是我们的太阳系，即艾萨克·牛顿所称的“世界系统”。牛顿力学成为了所有科学的典范。法国数学家皮埃尔·西蒙·德·拉普拉斯对这一理想的最佳表述是，他认为行星与分子在原则上并无区别。如果我们能完全掌握宇宙某一时刻的状态，原则上我们就能确定其之前及之后任何时刻的状态（拉普拉斯，1951 年，第 6 页）。这意味着整个宇宙可以用一种算法来描述。图灵在其文章《计算机器与智能》中引用了拉普拉斯的这段话，并补充说，他所考虑的预测比拉普拉斯考虑的、涵盖整个宇宙的预测更接近实用性（图灵，1950 年，第 440 页）。

As Russell pointed out, in this world we cannot even speak about causes, only mathematical functions. Because most empirical sciences are causal, they are far from this ideal world. The sciences that come closest, are classical mechanics and theoretical physics.
正如罗素所指出的，在这个世界上我们甚至无法谈论原因，只能谈论数学函数。因为大多数经验科学都是因果性的，它们与这个理想世界相去甚远。最接近这一理想世界的科学是经典力学和理论物理学。

Although this ideal world is a metaphysical idea that has not been realized anywhere, it has had a tremendous historical impact. Most philosophers and scientists after Galileo and Descartes have taken it to be the real world, which implies that everything that happens, “at the bottom” is governed by mathematical laws, algorithms. This applies to the organic world as well. According to Descartes all organisms, including the human body, are automata. Today we would call them robots or computers. Descartes made an exception for the human soul, which is not a part of the material world, and therefore is not governed by laws of nature. The immaterial soul accounts for man’s free will.
尽管这个理想世界是一个在任何地方都未曾实现的形而上学观念，但它产生了巨大的历史影响。伽利略和笛卡尔之后的大多数哲学家和科学家都将其视为真实世界，这意味着所有发生的事情，“从根本上”都受数学法则、算法的支配。这一点同样适用于有机世界。笛卡尔认为，所有生物，包括人体，都是自动机。如今，我们会称它们为机器人或计算机。笛卡尔将人类灵魂视为例外，它不属于物质世界的一部分，因此不受自然法则的约束。非物质性的灵魂解释了人类的自由意志。

However, most advocates of AGI (and advocates of strong AI) will today exclude Descartes’ immaterial soul, and follow the arguments of Yuval Harari. In his latest book 21 Lessons for the 21st Century he refers to neuroscience and behavioral economics, which have allegedly shown that our decisions are not the result of “some mysterious free will”, but the result of “millions of neurons calculating probabilities within a split second” (Harari, 2018, p. 20). Therefore, AI can do many things better than humans. He gives as examples driving a vehicle in a street full of pedestrians, lending money to strangers, and negotiating business deals. These jobs require the ability “to correctly assess the emotions and desires of other people.” The justification is this:
然而，如今大多数 AGI（以及强人工智能）的支持者会排除笛卡尔的非物质灵魂观点，转而遵循尤瓦尔·赫拉利的论点。在他最新著作《21 世纪的 21 堂课》中，他援引了神经科学和行为经济学的研究，这些研究据称表明，我们的决定并非“某种神秘自由意志”的结果，而是“数百万神经元在瞬间计算概率”的产物（赫拉利，2018 年，第 20 页）。因此，人工智能能在许多方面超越人类。他列举的例子包括在行人密集的街道上驾驶车辆、向陌生人放贷以及商业谈判。这些工作都需要“准确评估他人情绪和欲望”的能力。其理由在于：

Yet if these emotions and desires are in fact no more than biochemical algorithms, there is no reason why computers cannot decipher these algorithms—and do so far better than any Homo sapiens (Harari, 2018, p. 21).
然而，如果这些情感和欲望实际上不过是生化算法，就没有理由认为计算机无法解读这些算法——而且比任何智人都做得好得多（Harari, 2018, p. 21）。

This quotation echoes the words used by Francis Crick. In The Astonishing Hypothesis he explains the title of the book in the following way:
这段引文呼应了弗朗西斯·克里克使用的话语。在《惊人的假说》中，他这样解释书名：

The Astonishing Hypothesis is that “You”, your joys and your sorrows, your memories and your ambitions, your sense of personal identity and free will, are in fact no more than the behavior of a vast assembly of nerve cells and their associated molecules (Crick, 1994, p. 3).
“惊人的假说”认为，“你”，你的喜悦与悲伤，你的记忆与抱负，你的个人身份认同感与自由意志，实际上都不过是一大群神经细胞及其相关分子的集体行为（Crick, 1994, p. 3）。

However, there is a problem with both these quotations. If Harari and Crick are right, then the quotations are “nothing but” the result of chemical algorithms and “no more than” the behavior of a vast assembly of nerve cells. How can they then be true?
然而，这两个引用都存在一个问题。如果哈拉里和克里克是对的，那么这些引用“不过是”化学算法的结果，“仅仅”是大量神经细胞集合的行为。它们又怎能是真实的呢？

If we disregard the problem of self-reference, and take the ideal world of science that I have described above to be the (only) real world, then Harari’s argument makes sense. But the replacement of our everyday world by the world of science is based on a fundamental misunderstanding. Edmund Husserl was one of the first who pointed this out, and attributed this misunderstanding to Galileo. According to Husserl, Galileo was “…at once a discoverer and a concealing genius” (Husserl, 1970, p. 52). Husserl called this misunderstanding “objectivism”. Today a more common name is “scientism”.
如果我们忽略自我指涉的问题，并将我上述描述的科学理想世界视为（唯一的）现实世界，那么哈拉里的论点就有道理了。但用科学世界取代我们的日常世界，是基于一种根本的误解。埃德蒙·胡塞尔是最早指出这一点的人之一，并将这种误解归因于伽利略。根据胡塞尔的说法，伽利略是“……同时是发现者和遮蔽的天才”（胡塞尔，1970 年，第 52 页）。胡塞尔称这种误解为“客观主义”。如今，更常见的名称是“科学主义”。

Contrary to this, Husserl insisted that the sciences are fundamentally a human endeavor. Even the most abstract theories are grounded in our everyday world, Husserl’s “lifeworld”. Husserl mentions Einstein’s theory of relativity, and argues that it is dependent on “Michelson’s experiments^{Footnote 3} and the corroborations of them by other researchers” (Husserl, 1970, p. 125). To carry out this kind of experiments, the scientists must be able to move around, to handle instruments, to read scales and to communicate with other scientists.
与此相反，胡塞尔坚持认为科学从根本上是一种人类活动。即使是最抽象的理论也植根于我们的日常生活世界，即胡塞尔的“生活世界”。胡塞尔提到爱因斯坦的相对论，并认为它依赖于“迈克耳孙的实验 ^{Footnote 3} 以及其他研究者的验证”（胡塞尔，1970 年，第 125 页）。要进行这类实验，科学家们必须能够四处移动、操作仪器、读取刻度并与其它科学家交流。

There is a much more credible account of how we are able to understand other people than the one given by Harari. As Hubert Dreyfus pointed out, we are bodily and social beings, living in a material and social world. To understand another person is not to look into the chemistry of that person’s brain, not even into that person’s “soul”, but is rather to be in that person’s “shoes”. It is to understand the person’s lifeworld.
有一个比哈拉里提供的更为可信的解释，说明我们如何能够理解他人。正如休伯特·德雷福斯所指出的，我们是身体性和社会性的存在，生活在一个物质和社会世界中。理解另一个人并非窥探其大脑中的化学反应，甚至不是深入其“灵魂”，而是站在那个人的“立场”上。这意味着要理解那个人的生活世界。

The American author Theodore Roszak has constructed a thought example to illustrate this point: Let us imagine that we are watching a psychiatrist at work. He is a hard working and skilled psychiatrist and obviously has a very good practice. The waiting room is full of patients with a variety of emotional and mental disorders. Some are almost hysterical, some have strong suicidal thoughts, some hallucinations, some have the cruelest nightmares and some are driven to madness by the thought that they are being watched by people who will hurt them. The psychiatrist listens attentively to each patient and does his best to help them, but without much success. On the contrary, they all seem to be getting worse, despite the psychiatrist’s heroic efforts.
美国作家西奥多·罗萨克构思了一个思维实验来说明这一点：让我们想象一下，我们正在观察一位精神病医生的工作。他是一位勤奋且技艺高超的精神病医生，显然有着非常丰富的实践经验。候诊室里挤满了患有各种情绪和精神障碍的病人。有些人几乎歇斯底里，有些人有强烈的自杀念头，有些人出现幻觉，有些人做着最残忍的噩梦，还有些人因认为自己被可能伤害他们的人监视而陷入疯狂。精神病医生认真倾听每位患者，并尽力帮助他们，但收效甚微。相反，尽管医生付出了英勇的努力，所有人的病情似乎都在恶化。

Now Roszak asks us to put this into a larger context. The psychiatrist’s office is in a building, and the building is in a place. This place is Buchenwald and the patients are prisoners in the concentration camp (Roszak, 1992, p. 221). Biochemical algorithms would not help us to understand the patients. What does help, in fact, what is imperative, is to know the larger context. The example simply does not make sense if we do not know that the psychiatrist’s office is in a concentration camp.
现在罗兹萨克（Roszak）要求我们将此置于更大的背景中。这位精神科医生的办公室位于一栋建筑内，而这栋建筑又处于某个地方。这个地方是布痕瓦尔德（Buchenwald），病人们则是集中营里的囚犯（Roszak, 1992, p. 221）。生化算法无法帮助我们理解这些病人。真正有帮助的，事实上是至关重要的，是了解更大的背景。如果我们不知道精神科医生的办公室位于集中营内，这个例子就毫无意义。

Only few of us are able to put ourselves in the shoes of a prisoner of a concentration camp. Therefore, we cannot fully understand people in situations that are very different from what we have ourselves experienced. But to some degree we can understand, and we can understand because we are also in the world.
我们中只有少数人能够设身处地地想象集中营囚犯的处境。因此，我们无法完全理解那些与我们自身经历迥异的人所处的境况。但在某种程度上，我们能够理解，之所以能理解，是因为我们也生活在这个世界上。

Computers are not in our world. I have earlier said that neural networks need not be programmed, and therefore can handle tacit knowledge. However, it is simply not true, as some of the advocates of Big Data argue, that the data “speak for themselves”. Normally, the data used are related to one or more models, they are selected by humans, and in the end they consist of numbers.
计算机并不存在于我们的世界中。我之前说过，神经网络不需要编程，因此能够处理隐性知识。然而，正如一些大数据的支持者所主张的，“数据会自己说话”这一说法并不准确。通常情况下，所使用的数据与一个或多个模型相关，它们由人类选择，最终由数字构成。

If we think, for example like Harari, that the world is “at the bottom” governed by algorithms, then we will have a tendency to overestimate the power of AI and underestimate human accomplishments. The expression “nothing but” that appears in the quotation from Harari may lead to a serious oversimplification in the description of human and social phenomena. I think this is at least a part of the explanation of the failure of both IBM Watson Health and Alphabet’s DeepMind. “IBM has encountered a fundamental mismatch between the way machines learn and the way doctors work” (Strickland, 2019) and DeepMind has discovered that “what works for Go may not work for the challenging problems that DeepMind aspires to solve with AI, like cancer and clean energy” (Marcus, 2019).
如果我们像哈拉里那样认为世界“在底层”是由算法支配的，那么我们就会倾向于高估人工智能的力量，而低估人类的成就。哈拉里引文中出现的“不过是”这一表述，可能会导致对人类和社会现象的描述出现严重的过度简化。我认为这至少是 IBM 沃森健康部门和 Alphabet 的 DeepMind 双双失败的部分原因。“IBM 发现，机器的学习方式与医生的工作方式之间存在根本性的不匹配”（Strickland, 2019），而 DeepMind 则发现，“适用于围棋的方法可能并不适用于 DeepMind 希望用 AI 解决的具有挑战性的问题，如癌症和清洁能源”（Marcus, 2019）。

The overestimation of the power of AI may also have detrimental effects on science. In their frequently quoted book The Second Machine Age Erik Brynjolfson and Andrew McAfee argue that digitization can help us to understand the past. They refer to a project that analyzed more than five million books published in English since 1800. Some of the results from the project was that “the number of words in English has increased by more than 70% between 1950 and 2000, that fame now comes to people more quickly than in the past but also fades faster, and that in the 20th century interest in evolution was declining until Watson and Crick discovered the structure of DNA.” This allegedly leads to “better understanding and prediction—in other words, of better science—via digitization” (Brynjolfson and McAfee, 2014, p. 69). In my opinion it is rather an illustration of Karl Popper’s insight: “Too many dollars may chase too few ideas” (Popper, 1981, p. 96).
对人工智能力量的高估也可能对科学产生不利影响。在他们经常被引用的著作《第二次机器时代》中，埃里克·布林约尔松和安德鲁·麦卡菲认为数字化可以帮助我们理解过去。他们提到一个分析了自 1800 年以来出版的超过 500 万本英文书籍的项目。项目的一些结果是：“英语词汇量在 1950 年至 2000 年间增加了超过 70%，如今名声来得比过去更快，但也消失得更快，而且在 20 世纪，人们对进化的兴趣在沃森和克里克发现 DNA 结构之前一直在下降。”据称，这通过数字化带来了“更好的理解和预测——换句话说，更好的科学”（布林约尔松和麦卡菲，2014 年，第 69 页）。在我看来，这更像是卡尔·波普尔见解的例证：“太多的美元可能追逐太少的想法”（波普尔，1981 年，第 96 页）。

My conclusion is very simple: Hubert Dreyfus’ arguments against general AI are still valid.
我的结论非常简单：休伯特·德雷福斯反对通用人工智能的论点仍然有效。