在telligence Explosion FAQ
- Consequences of an Intelligence Explosion
- Friendly AI
- 4.2.What can we expect the motivations of a superintelligent machine to be?
- 4.3.Can’t we just keep the superintelligence in a box, with no access to the internet?
- 4.4.Can’t we just program the superintelligence not to harm us?
- 4.6。Can we teach a superintelligence a moral code with machine learning?
- 4.8。Can we add friendliness to any artificial intelligence design?
- 4.9.Who is working on the Friendly AI problem?
The intelligence explosion idea was expressed by statistician I.J. Good in 1965:
Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an ‘intelligence explosion’, and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make.
The argument is this: Every year, computers surpass human abilities in new ways. A program written in 1956 was able to prove mathematical theorems, and found a more elegant proof for one of them than Russell and Whitehead had given inMathematica Principia。By the late 1990s, ‘expert systems’ had surpassed human skill for a wide range of tasks.在1997, IBM’s Deep Blue computer beat the world chess champion, and in 2011, IBM’s Watson computer beat the best human players at a much more complicated game:Jeopardy!。Recently, a robot named Adam was programmed with our scientific knowledge about yeast, then posed its own hypotheses, tested them, and assessed the results.
计算机远远远远远远远远没有人类智能，但是AID设计的资源正在积累（包括硬件，大数据集，神经科学知识和AI理论）。我们可能有一天设计一台超过人类技能的机器at designing artificial intelligences。After that, this machine could improve its own intelligence faster and better than humans can, which would make it evenmoreskilled at improving its own intelligence. This could continue in a positive feedback loop such that the machine quickly becomes vastly more intelligent than the smartest human being on Earth: an ‘intelligence explosion’ resulting in a machine superintelligence.
This is what is meant by the ‘intelligence explosion’ in this FAQ.
- Vinge,The Coming Technological Singularity
- Chalmers,The Singularity: A Philosophical Analysis
2. How Likely is an Intelligence Explosion?
Artificial intelligence researcher Shane Legg definesintelligence like this:
在telligence measures an agent’s ability to achieve goals in a wide range of environments.
This is a bit vague, but it will serve as the working definition of ‘intelligence’ for this FAQ.
- Neisser等人，在telligence: Knowns and Unknowns
- Wasserman & Zentall (eds.),Comparative Cognition: Experimental Explorations of Animal Intelligence
2.2. What is greater-than-human intelligence?
机器已经比人类在许多特定任务中都聪明：执行计算，下棋，搜索大型数据库，检测水下矿山等等。但是使人类与众不同的一件事是generalintelligence. Humans can intelligently adapt to radically new problems in the urban jungle or outer space for which evolution could not have prepared them. Humans can solve problems for which their brain hardware and software was never trained. Humans can even examine the processes that produce their own intelligence (cognitive neuroscience), and design new kinds of intelligence never seen before (artificial intelligence).
Computer scientist Marcus Hutter has describeda formal model called AIXI that he says possesses the greatest general intelligence possible. But to implement it would require more computing power than all the matter in the universe can provide. Several projects try to approximate AIXI while still being computable, for example MC-AIXI.
Still, there remains much work to be done before greater-than-human intelligence can be achieved in machines. Greater-than-human intelligence need not be achieved by directly programming a machine to be intelligent. It could also be achieved by whole brain emulation, by biological cognitive enhancement, or by brain-computer interfaces (see below).
- Goertzel & Pennachin (eds.),Artificial General Intelligence
- Sandberg & Bostrom,整个大脑仿真：路线图
- Bostrom & Sandberg,Cognitive Enhancement: Methods, Ethics, Regulatory Challenges
- 维基百科，Brain-computer interface
Whole Brain Emulation (WBE) or ‘mind uploading’ is a computer emulation of all the cells and connections in a human brain. So even if the underlying principles of general intelligence prove difficult to discover, we might still emulate an entire human brain and make it run at a million times its normal speed (computer circuits communicatemuchfaster than neurons do). Such a WBE could do more thinking in one second than a normal human can in 31 years. So this would not lead immediately to smarter-than-human intelligence, but it would lead to faster-than-human intelligence. A WBE could be backed up (leading to a kind of immortality), and it could be copied so that hundreds or millions of WBEs could work on separate problems in parallel. If WBEs are created, they may therefore be able to solve scientific problems far more rapidly than ordinary humans, accelerating further technological progress.
- Sandberg & Bostrom,整个大脑仿真：路线图
2.4. What is biological cognitive enhancement?
可能有一些基因或分子可以修改以改善一般智力。亚博体育官网研究人员已经在小鼠中做到了这一点：他们过表达了NR2B基因，从而改善了这些小鼠的记忆超出任何小鼠物种的其他小鼠的记忆。Biological cognitive enhancement in humans may cause an intelligence explosion to occur more quickly than it otherwise would.
- Bostrom & Sandberg,Cognitive Enhancement: Methods, Ethics, Regulatory Challenges
2.5. What are brain-computer interfaces?
A brain-computer interface (BCI) is a direct communication pathway between the brain and a computer device. BCI research is heavily funded, and has already met dozens of successes. Three successes in human BCIs area device恢复了盲目的（部分）视线，cochlear implantsthat restore hearing to the deaf, and a device that allows use of an artificial hand by direct thought.
这种设备恢复了功能受损的功能，但是许多研究人员期望通过BCIS增强并提高正常的人类能力。亚博体育官网Ed Boydenis researching these opportunities as the lead of the合成神经生物学组at MIT. Such devices might hasten the arrival of an intelligence explosion, if only by improving human intelligence so that the hard problems of AI can be solved more rapidly.
There are many paths to artificial general intelligence (AGI). One path is to imitate the human brain by using neural nets or evolutionary algorithms to build dozens of separate components which can then be pieced together.Another path is to start with a formal model of perfect general intelligence and try to approximate that.第三个路径是把重点放在开发一个“种子人工智能”that can recursively self-improve, such that it can learn to be intelligent on its own without needing to first achieve human-level general intelligence.Eurisko是在有限的领域中自我提高的AI，但无法实现人类水平的一般智能。
- Pennachin & Goertzel,当代人工智能的方法
2.7. What is superintelligence?
Nick Bostrom defined‘superintelligence’ as:
an intellect that is much smarter than the best human brains in practically every field, including scientific creativity, general wisdom and social skills.
This definition includes vague terms like ‘much’ and ‘practically’, but it will serve as a working definition for superintelligence in this FAQ An intelligence explosion would lead to machine superintelligence, and some believe that an intelligence explosion is the most likely path to superintelligence.
- Bostrom,How Long Before Superintelligence?
2.8. When will an intelligence explosion happen?
- Futurist Ray Kurzweil predicts that machines will reach human-level intelligence by 2030 and that we will reach “a profound and disruptive transformation in human capability” by 2045.
- 在tel’s chief technology officer, Justin Rattner,期望“a point when human and artificial intelligence merges to create something bigger than itself” by 2048.
- AI researcher Eliezer Yudkowsky期望the intelligence explosion by 2060.
- Philosopher David Chalmers has over 1/2 credence in the intelligence explosion occurring by 2100.
- Quantum computing expert Michael Nielsen估计that the probability of the intelligence explosion occurring by 2100 is between 0.2% and about 70%.
- 2009年,在AGI-09会议上,专家一样ked when AI might reach superintelligence with massive new funding. The median estimates were that machine superintelligence could be achieved by 2045 (with 50% confidence) or by 2100 (with 90% confidence). Of course, attendees to this conference were self-selected to think that near-term artificial general intelligence is plausible.
- iRobot CEORodney Brooksand cognitive scientistDouglas Hofstadterallow that the intelligence explosion may occur in the future, but probably not in the 21st century.
- 机器人汉斯·摩拉维克（Hans Moravec）预测，人工智能将超越人类的智力”well before 2050。”
- 在a 2005 survey of 26 contributors to a series of reports on emerging technologies, the median estimate for machines reaching human-level intelligence was 2085.
- On the other hand, 41% of the participants in the AI@50 conference (in 2006)statedthat machine intelligence would绝不达到人类水平。
- 鲍姆（Baum），Goertzel和Goertzel，How Long Until Human-Level AI? Results from an Expert Assessment
2.9. Might an intelligence explosion never occur?
Dreyfusand Penrosehave argued that human cognitive abilities can’t be emulated by a computational machine. Searleand Blockargue that certain kinds of machines cannot have a mind (consciousness, intentionality, etc.). But these objections need not concern those who predict an intelligence explosion.
We can reply to Dreyfus and Penrose by noting that an intelligence explosion does not require an AI to be a classical computational system. And we can reply to Searle and Block by noting that an intelligence explosion does not depend on machines having consciousness or other properties of ‘mind’, only that it be able to solve problems better than humans can in a wide variety of unpredictable environments. As Edsger Dijkstra once said, the question of whether a machine can ‘really’ think is “no more interesting than the question of whether a submarine can swim.”
Finally, a global catastrophe like nuclear war or a large asteroid impact could so damage human civilization that the intelligence explosion never occurs. Or, a stable and global totalitarianism could prevent the technological development required for an intelligence explosion to occur.
3. Consequences of an Intelligence Explosion
在telligence is powerful.One might say that “Intelligence is no match for a gun, or for someone with lots of money,” but both guns and money were produced by intelligence. If not for our intelligence, humans would still be foraging the savannah for food.
在telligence is what caused humans to dominate the planet in the blink of an eye (on evolutionary timescales). Intelligence is what allows us to eradicate diseases, and what gives us the potential to eradicate ourselves with nuclear war. Intelligence gives us superior strategic skills, superior social skills, superior economic productivity, and the power of invention.
A machine with superintelligence would be able to hack into vulnerable networks via the internet, commandeer those resources for additional computing power, take over mobile machines connected to networks connected to the internet, use them to build additional machines, perform scientific experiments to understand the world better than humans can, invent quantum computing and nanotechnology, manipulate the social world better than we can, and do whatever it can to give itself more power to achieve its goals — all at a speed much faster than humans can respond to.
A machine superintelligence, if programmed with the right motivations, could potentially solve all the problems that humans are trying to solve but haven’t had the ingenuity or processing speed to solve yet. A superintelligence might cure disabilities and diseases, achieve world peace, give humans vastly longer and healthier lives, eliminate food and energy shortages, boost scientific discovery and space exploration, and so on.
此外，人类在21世纪面临几种存在的风险，包括全球核战争，生物武器，超级病毒等。A superintelligent machine would be more capable of solving those problems than humans are.
3.3. How might an intelligence explosion be dangerous?
If programmed with the wrong motivations, a machine could be malevolent toward humans, and intentionally exterminate our species. More likely, it could be designed with motivations that initially appeared safe (and easy to program) to its designers, but that turn out to be best fulfilled (given sufficient power) by reallocating resources from sustaining human life to other projects.As Yudkowsky55]As Yudkowskywrites, “the AI does not hate you, nor does it love you, but you are made out of atoms which it can use for something else.”
Since weak AIs with many different motivations could better achieve their goal by faking benevolence until they are powerful, safety testing to avoid this could be very challenging. Alternatively, competitive pressures, both economic and military, might lead AI designers to try to use other methods to control AIs with undesirable motivations. As those AIs became more sophisticated this could eventually lead to one risk too many.
Even a machine successfully designed with superficially benevolent motivations could easily go awry when it discovers implications of its decision criteria unanticipated by its designers. For example, a superintelligence programmed to maximize human happiness might find it easier to rewire human neurology so that humans are happiest when sitting quietly in jars than to build and maintain a utopian world that caters to the complex and nuanced whims of current human neurology.
- Yudkowsky，Artificial intelligence as a positive and negative factor in global risk
- Chalmers,The Singularity: A Philosophical Analysis
4. Friendly AI
4.1. What is Friendly AI?
A Friendly Artificial Intelligence (Friendly AI or FAI) is an artificial intelligence that is ‘friendly’ to humanity — one that has a good rather than bad effect on humanity.
AI researchers continue to make progress with machines that make their own decisions, and there is a growing awareness that we need to design machines to act safely and ethically. This research program goes by many names: ‘machine ethics’，“机器道德”，“人造道德”，“计算伦理”和“计算元伦理”，“友好的ai”, and ‘robo-ethics’ or ‘robot ethics’.
The most immediate concern may be in battlefield robots; the U.S. Department of Defense contracted Ronald Arkin to design a system for ensuring ethical behavior in autonomous battlefield robots。The U.S. Congress has declared that a third of America’s ground systems must be robotic by 2025, and by 2030 the U.S. Air Forceplansto have swarms of bird-sized flying robots that operate semi-autonomously for weeks at a time.
But Friendly AI research is not concerned with battlefield robots or machine ethics in general. It is concerned with a problem of a much larger scale: designing AI that would remain safe and friendly after the intelligence explosion.
A machine superintelligence would be enormously powerful. Successful implementation of Friendly AI could mean the difference between a solar system of unprecedented happiness and a solar system in which all available matter has been converted into parts for achieving the superintelligence’s goals.
It must be noted that Friendly AI is a harder project than often supposed. As explored below, commonly suggested solutions for Friendly AI are likely to fail because of two features possessed by any superintelligence:
- Superpower: a superintelligent machine will have unprecedented powers to reshape reality, and therefore will achieve its goals with highly efficient methods that confound human expectations and desires.
- Literalness: a superintelligent machine will make decisions based on the mechanisms it is designed with, not the hopes its designers had in mind when they programmed those mechanisms. It will act only on precise specifications of rules and values, and will do so in ways that need not respect the complexity and subtletyof what humans value. A demand like “maximize human happiness” sounds simple to us because it contains few words, but philosophers and scientists have failed for centuries to explainexactly这意味着什么，并且肯定没有将其转化为足够严格的AI程序员使用的形式。
- All Things Considered,奇异性：人类的最后发明？
4.2. What can we expect the motivations of a superintelligent machine to be?
除了在整个大脑模拟的情况下,is no reason to expect a superintelligent machine to have motivations anything like those of humans. Human minds represent a tiny dot in the vast space of all possible mind designs, and very different kinds of minds are unlikely to share to complex motivations unique to humans and other mammals.
Whatever its goals, a superintelligence would tend to commandeer resources that can help it achieve its goals, including the energy and elements on which human life depends. It would not stop because of a concern for humans or other intelligences that is ‘built in’ to all possible mind designs. Rather, it would pursue its particular goal and give no thought to concerns that seem ‘natural’ to that particular species of primate calledhomo sapiens。
There are, however, some basic instrumental motivations we can expect superintelligent machines to display, because they are useful for achieving its goals, no matter what its goals are. For example, an AI will ‘want’ to self-improve, to be optimally rational, to retain its original goals, to acquire resources, and to protect itself — because all these things help it achieve the goals with which it was originally programmed.
- Omohundro,The Basic AI Drives
- 舒尔曼，Basic AI Drives and Catastrophic Risks
4.3. Can’t we just keep the superintelligence in a box, with no access to the internet?
‘AI-boxing’ is a common suggestion: why not use a superintelligent machine as a kind of question-answering oracle, and never give it access to the internet or any motors with which to move itself and acquire resources beyond what we give it? There are several reasons to suspect that AI-boxing will not work in the long run:
- Whatever goals the creators designed the superintelligence to achieve, it will be more able to achieve those goals if given access to the internet and other means of acquiring additional resources. So, there will be tremendous temptation to “let the AI out of its box.”
- Preliminary experiments在A-Boxing中，不会激发信心。而且，一个超级智能将产生更具说服力的技巧，以使人类“放开”比我们想象的。
- If one superintelligence has been created, then other labs or even independent programmers will be only weeks or decades away from creating a second superintelligence, and then a third, and then a fourth. You cannot hope to successfully contain all superintelligences created around the world by hundreds of people for hundreds of different purposes.
4.4. Can’t we just program the superintelligence not to harm us?
One approach would be to implement ‘constraints’ as rules or mechanisms that prevent a machine from taking actions that it would normally take to fulfill its goals: perhaps ‘filters’ that intercept and cancel harmful actions, or ‘censors’ that detect and suppress potentially harmful plans within a superintelligence.
If constraints在之上goals are not feasible, could we put constraintsinside ofgoals? If a superintelligence had a goal of avoiding harm to humans, it would not be motivated to remove this constraint, avoiding the problem we pointed out above. Unfortunately, the intuitive notion of ‘harm’ is very difficult to specify in a way that doesn’t lead to very bad results when used by a superintelligence. If ‘harm’ is defined in terms of human pain, a superintelligence could rewire humans so that they don’t feel pain. If ‘harm’ is defined in terms of thwarting human desires, it could rewire human desires. And so on.
如果,而不是试图完全指定一个术语‘harm’, we decide to explicitly list all of the actions a superintelligence ought to avoid, we run into a related problem: human value iscomplex and subtle, and it’s unlikely we can come up with a list of all the things we做n’twant a superintelligence to do. This would be like writing a recipe for a cake thatreads: “Don’t use avocados. Don’t use a toaster. Don’t use vegetables…” and so on. Such a list can never be long enough.
Let’s consider the likely consequences of someutilitariandesigns for Friendly AI.
An AI designed to minimize human suffering might simply kill all humans: no humans, no human suffering.
或者，考虑一种旨在最大化人类愉悦感的AI。它没有建立雄心勃勃的乌托邦，它可以满足数十亿年的复杂和苛刻的人类需求，而是可以通过将人类接线到Nozick的努力来更有效地实现其目标experience machines。或者，它可能会重新连接‘liking’ componentof the brain’sreward systemso that whichever hedonic hotspotpaints sensations with a ‘pleasure gloss’当人类坐在罐子里时，可以最大程度地发挥乐趣。对于AI来说，这将是一个比迎合大多数人类大脑中愉悦光泽的复杂和细微差别的世界国家的世界更容易建立的世界。
Likewise, an AI motivated to maximize objective desire satisfaction or reported subjective well-being could rewire human neurology so that both ends are realized whenever humans sit in jars. Or it could kill all humans (and animals) and replace them with beings made from scratch to attain objective desire satisfaction or subjective well-being when sitting in jars. Either option might be easier for the AI to achieve than maintaining a utopian society catering to the complexity of human (and animal) desires. Similar problems afflict other utilitarian AI designs.
It’s not just a problem of specifying goals, either. It is hard to predict how goals will change in a self-modifying agent. No current mathematical decision theory can process the decisions of a self-modifying agent.
4.6。Can we teach a superintelligence a moral code with machine learning?
Some have proposed我们通过基于案例的机器学习来教机器道德代码。基本思想是：人类法官将评估成千上万的行动，性格特征，欲望，法律或机构，视为具有不同程度的道德可接受性。然后，机器将找到这些情况之间的连接learn道德背后的原则，使其可以应用这些原则来确定培训期间未遇到的新案件的道德。这种机器学习已经用于设计可以例如检测水下矿山的机器喂给机器数百例矿山和非矿体后。
The first problem is that training on cases from our present reality may not result in a machine that will make correct ethical decisions in a world radically reshaped by superintelligence.
The second problem is that a superintelligence may generalize the wrong principles due to coincidental patterns in the training data.Consider the parable of the machine trained to recognize camouflaged tanks in a forest. Researchers take 100 photos of camouflaged tanks and 100 photos of trees. They then train the machine on 50 photos of each, so that it learns to distinguish camouflaged tanks from trees. As a test, they show the machine the remaining 50 photos of each, and it classifies each one correctly. Success! However, later tests show that the machine classifies additional photos of camouflaged tanks and trees poorly. The problem turns out to be that the researchers’ photos of camouflaged tanks had been taken on cloudy days, while their photos of trees had been taken on sunny days. The machine had learned to distinguish cloudy days from sunny days, not camouflaged tanks from trees.
Thus, it seems that trustworthy Friendly AI design must involve detailed models of the underlying processes generating human moral judgments, not only surface similarities of cases.
Eliezer Yudkowsky has proposedCoherent Extrapolated Volition as a solution to at least two problems facing Friendly AI design:
- The fragility of human values: Yudkowskywrites“未来不是由一个目标系统亚博体育苹果app官方下载detailed reliable inheritance from human morals and metamorals will contain almost nothing of worth.” The problem is that what humans value is complex and subtle, and difficult to specify. Consider the seemingly minor value of新奇。If a human-like value of novelty is not programmed into a superintelligent machine, it might explore the universe for valuable things up to a certain point, and then maximize the most valuable thing it finds (the exploration-exploitation tradeoff) — tiling the solar system with brains in vats wired into happiness machines, for example. When a superintelligence is in charge, you have to get its motivational systemexactly rightin order to不是make the future undesirable.
- The locality of human values:想象一下,如果面临了友好的人工智能问题ancient Greeks, and they had programmed it with the most progressive moral values of their time. That would have led the world to a rather horrifying fate. But why should we think that humans have, in the 21st century, arrived at the apex of human morality? We can’t risk programming a superintelligent machine with the moral values we happen to hold today. But then, which moral values做we give it?
Yudkowskysuggeststhat we build a ‘seed AI’ to discover and then extrapolate the ‘coherent extrapolated volition’ of humanity:
The seed AI would use the results of this examination and extrapolation of human values to program the motivational system of the superintelligence that would determine the fate of the galaxy.
但是，有些人担心人类的集体意愿不会融合一组连贯的目标。其他believethat guaranteed Friendliness is not possible, even by such elaborate and careful means.
- Yudkowsky，Coherent Extrapolated Volition
4.8。Can we add friendliness to any artificial intelligence design?
Many AI designs that would generate an intelligence explosion would not have a ‘slot’ in which a goal (such as ‘be friendly to human interests’) could be placed. For example, if AI is made via whole brain emulation, or evolutionary algorithms, or neural nets, or reinforcement learning, the AI will end up with some goal as it self-improves, but that stable eventual goal may be very difficult to predict in advance.
Thus, in order to design a friendly AI, it is not sufficient to determine what ‘friendliness’ is (and to specify it clearly enough that even a superintelligence will interpret it the way we want it to). We must also figure out how to build a general intelligence that satisfies a goal at all, and that stably retains that goal as it edits its own code to make itself smarter. This task is perhaps the primary difficulty in designing friendly AI.
4.9. Who is working on the Friendly AI problem?
今天，正在探索友好的AI研究亚博体育官网机器情报研究所亚博体育官网(in Berkeley, California), by the人类研究所的未来(in Oxford, U.K.), and by a few other researchers such as David Chalmers. Machine ethics researchers occasionally touch on the problem, for example Wendell Wallach and Colin Allen inMoral Machines。
 Yudkowsky（2001）。Creating Friendly AI 1.0。机器智能研究所。亚博体育官网
 Anderson & Anderson, eds. (2006).IEEE Intelligent Systems, 21(4)。
 Anderson & Anderson, eds. (2011).Machine Ethics。Cambridge University Press.
 Arkin (2009).自主机器人中的致命行为。Chapman and Hall.
 Capurro, Hausmanninger, Weber, Weil, Cerqui, Weber, & Weber (2006).国际信息伦理评论，第1卷。6：机器人中的道德规范。
 Danielson (1992).Artificial morality: Virtuous robots for virtual games。Routledge。
 Lokhorst (2011).Computational meta-ethics: Towards the meta-ethical robot。Minds and Machines。
 McLaren (2005). Lessons in Machine Ethics from the Perspective of Two Computational Models of Ethical Reasoning.AAAI技术报告FS-05-06: 70-77.
 Powers (2005). Deontological Machine Ethics.AAAI技术报告FS-05-06：79-86。
 Sawyer (2007). Robot ethics.Science, 318(5853): 1037.
 Wallach, Allen, & Smit (2008). Machine morality: Bottom-up and top-down approaches for modeling human moral faculties.AI and Society, 22(4): 565–582.
 Allen (2002). Calculated morality: Ethical computing in the limit. In Smit & Lasker, eds.,决策和人类行动的认知，情感和道德方面，第一卷。Baden/IIAS.
 Good（1965）。关于第一台超级智能机器的猜测。Advanced in Computers, 6：31-88。
 MacKenzie (1995). The Automation of Proof: A Historical and Sociological Exploration.IEEE Annals, 17(3): 7-29.
 Nilsson (2009).The Quest for Artificial Intelligence。Cambridge University Press.
 Campbell，Hoane和Hsu（2002）。深蓝。Artificial Intelligence, 134：57-83。
 Markoff (2011).电脑在“危险！”上获胜；琐碎，不是。纽约时报，2011年2月17日：a1。
 King et al. (2009).The automation of science。Science, 324: 85-89.
 King (2011).Rise of the robo scientists。Scientific American, January 2011。
 Legg（2008）。机器超级智能。PhD Thesis. IDSIA.
 Hutter（2005）。Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability。施普林格。
 Veness, Ng, Hutter, & Silver (2011).A Monte Carlo AIXI Approximation。Journal of Artificial Intelligence Research, 40: 95-142.
 Tang, Shimizu, Dube, Rampon, Kerchner, Zhuo, Liu, & Tsien (1999). Genetic enhancement of learning and memory in mice.Nature, 401：63–69。
 Hochberg，Serruya，Friehs，Mukand，Saleh，Caplan，Branner，Chen，Penn，＆Donoghue（2006）。神经元合奏控制四脑的人类对假体设备的控制。Nature 442: 164-171.
 Bostrom（1998）。How long before superintelligence?在ternational Journal of Future Studies, 2。
 Kurzweil (2005).奇异性在附近。Viking.
 Chalmers（2010）。The Singularity: A Philosophical Analysis。Journal of Consciousness Studies, 17：7-65。
 Baum, Goertzel, & Goertzel (forthcoming).How Long Until Human-Level AI? Results from an Expert Assessment。Technological and Forecasting Change。
 Grossberg (1992).Neural Networks and Natural Intelligence。MIT Press.
 Martinetz & Schulten (1991). A ‘neural-gas’ network learns topologies. In Kohonen, Makisara, Simula, & Kangas (eds.),人工神经网络(pp. 397-402). North Holland.
 de Garis (2010). Artificial Brains. In Goertzel & Pennachin (eds.),Artificial General Intelligence(pp. 159-174). Springer.
 Schmidhuber (2010). Gödel Machines: Fully Self-Referential Optimal Universal Self-Improvers. In Goertzel & Pennachin (eds.),Artificial General Intelligence(pp. 199-223). Springer.
 Hutter（2010）。通用算法智能：一种数学自上而下的方法。在Goertzel＆Pennachin（编辑）中，Artificial General Intelligence(pp. 227-287). Springer.
 Yudkowsky (2010).Levels of Organization in General Intelligence。在Goertzel＆Pennachin（编辑）中，Artificial General Intelligence(pp. 389-496). Springer.
 Dreyfus (1972).What Computers Can’t Do。Harper & Row.
 Penrose (1994).Shadows of the Mind。牛津大学出版社。
 Searle（1980）。思想，大脑和程序。Behavioral and Brain Sciences, 3: 417-457.
 Block (1981).Psychologism and behaviorism。哲学评论，90: 5-43.
 Asimov (1942).Runaround。Astounding Science Fiction, March 1942。Street & Smith.
 Anderson (2008). Asimov’s ‘three laws of robotics’ and machine metaethics.AI & Society, 22(4): 477-493.
 Kringelbach＆Berridge编辑。（2009）。Pleasures of the Brain。牛津大学出版社。
 Schroeder (2004).Three Faces of Desire。牛津大学出版社。
 Yudkowsky (2007).The hidden complexity of wishes。
 Smart (1958). Negative utilitarianism.智力，67: 542-543.
 Russell＆Norvig（2009）。Artificial Intelligence: A Modern Approach, 3rd edition。Prentice Hall. (see page 1037)
 Frijda（2009）。关于愉悦的性质和功能。在Kringelbach＆Berridge（编辑）中，Pleasures of the brain(pp. 99-112). Oxford University Press.
 Aldridge & Berridge (2009). Neural coding of pleasure: ‘rose-tinted glasses’ of the ventral pallidum. In Kringelbach & Berridge (eds.),Pleasures of the brain（第62-73页）。牛津大学出版社。
 Smith, Mahler, Pecina, & Berridge (2009). Hedonic hotspots: generating sensory pleasure in the brain. In Kringelbach & Berridge (eds.),Pleasures of the brain(pp. 27-49). Oxford University Press.
 Guarini, (2006). Particularism and classification and reclassification of moral cases. IEEE Intelligent Systems 21(4): 22–28.
 Anderson，Anderson和Armen（2005）。迈向机器道德：实施两种基于动作的伦理理论。在2005年AAAI的机器道德专题讨论会论文集, Arlington, Virginia, November.
 Honarvar & Ghasem-Aghaee (2009). An artificial neural network approach for creating an ethical artificial agent.第八届IEEE机器人技术计算智能国际会议论文集: 290-295.
 Rzepka & Araki (2005). What statistics could do for ethics? – The idea of common sense processing based safety valve. InMachine ethics: papers from the AAAI fall symposium。American Association of Artificial Intelligence.
 Gorman & Sejnowski (1988).Analysis of hidden units in a layered network trained to classify sonar targets。Neural Networks, 1: 75-89.
 Yudkowsky (2008).Artificial intelligence as a positive and negative factor in global risk。在Bostrom & Cirkovic (eds.),Global Catastrophic Risks。牛津大学出版社。
 Omohundro（2008）。The Basic AI Drives。
 Bostrom & Cirkovic, eds. (2008).Global Catastrophic Risks。牛津大学出版社。
 Yudkowsky (2004).连贯的外推力。机器智能研究所。亚博体育官网
 Azoulay-Schwartz, Kraus, & Wilkenfeld (2004). Exploitation vs. exploration: choosing a supplier in an environment of incomplete information.Decision Support Systems, 38: 1-18.
 Caplan (2008). The totalitarian threat. In Bostrom & Cirkovic (eds.),Global Catastrophic Risks。牛津大学出版社。
 Yudkowsky (2007).The Power of Intelligence。
 Sandberg & Bostrom (2011).Machine intelligence survey，2011-1技术报告，牛津人类研究所未来。
This page is up-to-date as of 2013, but may not represent MIRI or Luke Muehlhauser’s current views. Last modified November 10, 2015 (original).