(The below text version of the notes is for search purposes and convenience. See the PDF version for proper formatting such as bold, italics, etc., and graphics where applicable. Copyright: 2022 Retraice, Inc.)
AIMA4e Annotations
A companion to the great white brick.
As of November 27, 2022
(Start date: November 21, 2022.)
[1]retraice.com
Version notes: [2]Retraice ([3]2022/11/21) (Re57), first draft, covered Preface, Sections I, II; [4]Retraice ([5]2022/11/22) (Re58), no footnotes, covered Sections III, IV; [6]Retraice ([7]2022/11/22) (Re58) again, moved some notes from Re57 and Re58 notes to footnotes here; [8]Retraice ([9]2022/11/23) (Re59), covered Sections V, VI, VII; [10]Retraice ([11]2022/11/24) (Re60), covered Appendix A; [12]Retraice ([13]2022/11/25) (Re61), covered Appendix B, added quotation marks to chapter titles that aren't abbreviated or paraphrased; [14]Retraice ([15]2022/11/26) (Re62), added synopsis.
SYNOPSIS
Not everything in this synopsis is actually mentioned in AIMA4e, but 99% of it is.
PREFACE: Our phenomenon is intelligent agents--their `agent functions', goals, uncertainty, learning, and performance behavior. Our science, which includes building computing-machine agents, is called `artificial intelligence'. The goals we put into computing-machine agents should be fundamentally uncertain, to avoid the extreme unintended consequences of their growing power. If goals are provided without uncertainty, the machines' behavior will not be compatible with human life.[16]^1
1 INTELLIGENCE: Agents have structure and do good or bad performance behavior toward goals in environments.
2 SOLVING: Agents pursue goals by searching for solutions to goal-related problems, which can have degrees of constraints, in environments that sometimes contain other agents.
3 THINKING (KNOWLEDGE, REASONING AND PLANNING): Agents use internal representations[17]^2 of the world and how it works (logics, task nets, probability nets, Markov models, neural nets), before they act, to improve performance behavior toward goals.
4 UNCERTAIN THINKING: Most environments cannot be known completely, and so have a quantifiable element of uncertainty; doing pure logic in such environments exhausts resources and presumes knowledge which is unavailable; Bayes nets can be used in uncertain environments to simplify causal relationships of the past, present and future, shifting thinking from what's possible to what's probable; programming languages that incorporate uncertainty and probability can be made from pure logic or from traditional programming languages; no matter what the environment or representations of it, agents must have rules for making decisions, either singly or sequentially; other agents, in the same environment, face the same challenges, and the relationships between agents make all the difference to the outcomes.
5 LEARNING: Observations of the environment can improve behavior and make future environments `better'[18]^3 for the agent; this happens when the representations (models) built based on observations, are `good',[19]^4 and are usable as software to solve problems that obstruct goals; multiple observation techniques, including teacher-provided information, and information provided by reward and punishment of trial behavior, can yield good, usable representations, especially if they account for uncertainty by forming and testing hypotheses about evidence-data (instantiations of `random variables' of the relevant part of the world [domain]); hypotheses can be represented by "complex algebraic circuits with tunable connection strengths" (deep neural nets), which are somewhat analogous to animal brain tissue.
6 INTERACTING: Computing-machine agents can be connected to networks, databases, sensors and effectors, enabling them to learn from human language and the physical world outside themselves, for purposes of achieving goals; human language is complex; `language models' describe the probability of a string in a given language, and deep neural networks are the current best tool for building them; photons and other particles and waves (quantum field phenomena) can provide abundant information about environments to agents, via cameras and other sensors; electro-mechanical devices enable agent-movement in and of the physical world.
7 CONCLUSIONS: The hardest part of dealing with highly intelligent agents is knowing who, what and when to trust. It is not clear that humans will change sufficiently, or quickly enough, to adapt to the environments of the future which will contain highly intelligence computing-machine agents. Similarly, it is not clear that humans can overcome all present and future existential threats without such agents helping them.[20]^5
PREFACE
* The phenomenon: intelligent agents[21]^6 * The discipline: artificial intelligence,[22]^7 "the study of agents that receive percepts from the environment and perform actions." (vii)
* Aspects of the phenomenon: + Agent function: "Each ...agent implements a function that maps percept sequences to actions" (vii) o Ways to represent agent functions include: "reactive agents, real-time planners, decision-theoretic systems, and deep learning systems." (vii) + Learning o "a construction method for competent systems" (viii) o "a way of extending the reach of the designer into unknown environments." (viii) + Goals o Robotics and vision: # "not ...independently defined problems" # "[things] in the service of achieving goals."
I INTELLIGENCE --"Artificial Intelligence"
1 Introduction
Definitions, foundations, history, philosophy, state of the art, risks-benefits.
2 Agents
Environments, `good' behavior, agent structure and types.
II SOLVING--"Problem-solving"
3 Searching: Looking ahead to find a sequence
Algorithms, strategies, informed/heuristic[23]^8 strategies.
4 Complex Environments: More realistic environments
Local search, optimization, continuous spaces, nondeterministic actions, partially observable env.s, online search and unknown env.s.
5 Adversarial Games: Other agents competing against us
Theory, optimal decisions, alpha-beta tree search, Monte Carlo tree search, stochastic g.s, partially observable g.s, limitations.
6 Constraints: States as domains, solutions as allowable combinations of states
Constraint propagation, inference, backtracking search, local search, structure of problems
III THINKING--"Knowledge, reasoning, and planning"
7 "Logical Agents": Forming representations and reasoning before acting
Knowledge-based agents; representing[24]^9 worlds; logic, world models and `possible worlds';[25]^10 logic without objects.
8 "First-Order Logic": A formal language for objects and their relations
`Ontological commitment' (what is assumed about reality); syntax, semantics; knowledge engineering (building formal representations of important[26]^11 objects and relations in a domain).
9 First-Order Inference: Reasoning about objects and their relations
Algorithms to answer any 1st-order logic question.
10 "Knowledge Representation": Representing the real world for problem solving
What content to put into a knowledge base.
Knowledge representation languages and their uses (315): * First-order logic: reasoning about a world of objects and relations; * Hierarchical task networks: for reasoning about plans (chpt. 11); * Bayesian networks: for reasoning with uncertainty (chpt. 13); * Markov models: for reasoning over time (chpt. 17); * Deep neural networks: for reasoning about images, sounds, other data (chpt. 21).
11 "Automated Planning": Hierarchical task networks
Planning for spacecraft, factories, military campaigns; representing actions and states; efficient algorithms and heuristics.
IV UNCERTAINTY--"Uncertain knowledge and reasoning"
12 "Quantifying Uncertainty": An answer to the laziness and ignorance that kill formal logic
Causes of uncertainty are environment types (partially observable,[27]^12 nondeterministic, adversarial[28]^13 ); belief state grows big and unlikely fast (384); agents still need a way to act; absolute certainty is impossible;[29]^14 it comes down to importance, likelihood and degree of success (385-386).
Logic fails because laziness and ignorance; probability theory solves the qualification problem by summarizing the uncertainty.[30]^15 * Laziness: too much work to list everything, or use such a list; * Ignorance: (theoretical) there are no complete theories; (practical) we can never run all the tests.
13 "Probabilistic Reasoning" [big]: Bayesian networks
For reasoning with uncertainty by representing causal independence (398) and conditional independence (401) relationships to simplify probabilistic representations of the world.
14 "Probabilistic Reasoning Over Time": Comprehending the uncertain past, present and future
Belief state[31]^16 plus transition model yields prediction (chpt 4, 7, 11); percepts and sensor model yield updated belief state; add probability theory to switch from possible states to probable states.[32]^17
15 "Probabilistic Programming": Universal formal languages to represent any computable probability model, and they come with algorithms
Using formal logic and traditional programming languages to represent probabilistic information.
16 "Making Simple Decisions": Agents getting what they want in an uncertain world--as much as possible, on average
Beliefs, desires; utility theory; utility functions; decision networks; the value of information (547);[33]^18 this chapter is concerned with one-shot or episodic decisions problems (as opposed to sequential) (cf. 562, below).
17 "Making Complex Decisions": What to do today given decisions to be made tomorrow
Sequential decision problems (as opposed to one-shot episodic, cf. above): the agent's utility depends on a sequence of decisions in stochastic (explicitly probabilistic (45)) and partially observable environments. Markov models (563; cf. 463) for reasoning over time (chpt. 17).
18 "Multiagent Decision Making" [big]: When there's more than one agent in the environment
The nature of such environments and the strategies for problem-solving depend on the relationships between agents: non-cooperative and cooperative game theory; collective decision-making.
V LEARNING--"Machine learning"
19 "Learning From Examples" [big]: Improving behavior by observing the present (past?) and predicting the future
Learning is improving performance (behavior) after making observations.[34]^19
If the agent is a computer: Machine learning: "a computer observes some data, builds a model based on the data, and uses the model as both a hypothesis about the world and a piece of software that can solve problems." (651)
Subsections: * supervised learning; * learning decision trees; * model selection and optimization; * theory of learning; * linear regression (finding the best-fit line, i.e. predicting `future' [dependent] values based on plotting `past' [independent] values), classification;[35]^20 * nonparametric models (which retain all the examples, aka `instance-based' or `memory-based' learning, which is more true to large datasets [scalable?] than parametric, which summarize, and then discard, training data in fixed numbers of parameters), * ensemble learning (using multiple hypotheses instead of one, and averaging or voting--`base' models are combined into an `ensemble' model); * ML system development, the practice (software engineering and design patters in ML ops).
20 "Learning Probabilistic Models": View `learning' as "uncertain reasoning from observations" and model the world accordingly
Agents can't use probability and decision theories until they learn them from experience: treat learning itself as an inference process in a probabilistic world. Use Bayesian networks. Key concepts: data and hypotheses. "Here, the data are evidence ...instantiations of some or all of the random variables describing the domain."[36]^21
21 "Deep Learning": represent hypotheses as "complex algebraic circuits with tunable connection strengths"
The circuits are orginzed into layers, a multi-step computation path. Ideal for recognizing, translating and generating images (including objects in images) and speech; `neural networks'.
From chpt. 10 on knowledge rep. languages, above notes: "deep neural networks: for reasoning about images, sounds, other data."
Think: gradient descent, back-propagation, convolutional neural networks.
22 "Reinforcement Learning": Learning from experiences of reward and punishment instead of correct examples from a supervisor
Passive and active RL., Q-learning, apprenticeships and inverse RL.
Cf. Reward is Enough, May 2021: [37]https://www.deepmind.com/publications/reward-is-enough
VI INTERACTING--"Communicating, perceiving, and acting"
23 "Natural Language Processing": Communicating with humans and learning from what they've written
Language model: "a probability distribution describing the likelihood of any string." (824)
N-grams, grammar, syntax, semantics, parsing, vagueness, ambiguity, quantification.
24 Deep Learning NLP: Using neural nets on natural language to effectively handle the complexity
"[R]epresenting words as points in a high-dimensional space." RNNs for "long-distance context."
Cf. Attention Is All You Need, 2017: [38]https://arxiv.org/abs/1706.03762 and AIMA4e p. 868, transformer architecture, self-attention.
25 "Computer Vision": Connecting AI to cameras
Photons provide a lot of valuable information to agents--too much information.
Surveillance cameras--good and bad; cars. Lots of machines do better if they can see.
From the Preface: Robotics and vision: "not ...independently defined problems"..."[things] in the service of achieving goals."
26 "Robotics": Connecting AI to sensors, effectors and actuators
To enable movement in-and of--the physical world. Cars, spacecraft, surgeons, submarines, delivery bots.
From the Preface: Robotics and vision: "not ...independently defined problems"..."[things] in the service of achieving goals."
VII CONCLUSIONS--"Conclusions"
27 "Philosophy, Ethics, and Safety of AI": What is AI? What should we do with it? What might it do with us?
Trust--of systems, humans, ourselves, each other.
The human use of human beings. Usefulness of human beings at all?
Medicine. War.
28 "The Future of AI": Our tools will improve dramatically; our ends might remain the same.
Our preferences, our tools, our architectures. They're ours, for now.
Minimize the negative impacts, don't maximize the positive?
A: MATH--"Appendix A: Mathematical Background"
A.1 [SOLVING per §II]: "Complexity Analysis and O() Notation": Problem and algorithm analysis (computer science math)
Asymptotic and worst-case analysis of algorithms:
Approximately predicting the performance (and efficiency) of algorithms based on their steps in worst-case (or best or average) and infinite-case (asymptotic) input scenarios, in order to avoid actually implementing them, and to enable comparison of algorithms.[39]^22
Abstract over the input, and then the implementation, to find the key factors (string length; lines of code) that make the space/time difference. Ignore constants, usually; focus on the key variables.
Complexity analysis of problems:
Polynomial time O(n^k) problems, class P.
Non-polynomial time problems.
Nondeterministic polynomial problems: class NP. A problem with some algorithm that can guess and check a solution in polynomial time.
A.2 [THINKING per §III]: "Vectors, Matrices, and Linear Algebra": Line equation probing (`unknowns' math)
A vector is a pile of numbers (or unknowns or variables), a matrix is a pile of piles of numbers; some of the questions we can ask are `linear problems'[40]^23 (think prediction, interpolation, extrapolation), and algebra (finding unknowns by repairing [or completion] and balancing) on these things is `linear algebra'.
Vectors: Ordered sequences of values--represent something in the real world as just a set of values measuring specific aspects of that thing.[41]^24
Linear algebra: Doing algebra (finding unknowns by repairing [or completion] and balancing) on systems of equations of lines in planes instead of single equations and equations of points on lines (algebra). Think: finding line or plane intersections or bounded regions (based on inequalities instead of equations),[42]^25 and changing lines without affecting intersections[43]^26 --that sort of thing.
Thinking about higher dimensional objects: left-right x, up-down y, forward-backward z, wrist-watch value (time) t, color spectrum p, texture q, weight r, etc.
A.3 [UNCERTAINTY per §IV] "Probability Distributions": Quantifying `probably' (uncertainty math)
Probability is a controversial concept.[44]^27
Experiments yield outcomes; a set of outcomes is an event; the set of all possible outcomes is the sample space.[45]^28
"A `probability' is a measure over a set of events...." A probability model: sample space plus the probability measure for each outcome.
Cf. `random variable' note above.
B: CODE--"Appendix B: Notes on Languages and Algorithms"
B.1 "Defining Languages with Backus-Naur Form (BNF)": Defining formal languages
Languages: * propositional logic; * first-order logic; * English;
Formal language: strings, symbols, infinite strings, grammar, Chomsky hierarchy (context free).
BNF elements: * Terminals: symbols / words; * Non terminals that categorize: NounPhrase; * Start symbol: Sentence (English) or Expr (math) or Program (computing); * Rewrite rules: Sentence -> Expr Operator Expr | (Expr) | Number.
Think compilers:[46]^29 source language to target language, first syntax then semantics, reconstruct source logic in target logic.
1. Syntax analysis module: tokenizing + parsing (rule matching);
2. Code generation module: data translation and command translation.
Think also: (universal?) generative grammar, generating new strings, chat bots, GPT-3, Deep Blue, AlphaCode, Turing test.
B.2 "Describing Algorithms with Pseudocode": Code formatting and conventions
* Persistent variables: global state, side effects, OOP vs functional programming; agents use persistent variables for memory; implementation in OOP vs FP languages; * Functions as variable values: f(9)=3; * Indentation is significant: it scopes control structures (loops and cobditionals), also functions; but objects? Not really. They use `persistent' variable as memory, which can be implemented as an object, or a `functional closure', cf braces and `end'; * Destructuring assignment notation; * Default values for parameters: y=0; * Yield: generates an element of sequence; * Loops: for, while, repeat until; * Lists notation; * Sets notation; * Arrays index starts at 1 as in math, not code.
__
References
Aleksandrov, A. D., Kolmogorov, A. N., & Lavrent'ev, M. A. (1969). Mathematics: Its Content, Methods and Meaning (3 Volumes in One). Dover, 1999 reprint ed. ISBN: 0486409163. Searches: [47]https://www.amazon.com/s?k=0486409163 [48]https://www.google.com/search?q=isbn+0486409163 [49]https://lccn.loc.gov/99033023
Anderson, R. F. V. (1986). Introduction to Linear Algebra. Holt, Rinehard and Winston. ISBN: 003921835X. Searches: [50]https://www.amazon.com/s?k=003921835X [51]https://www.google.com/search?q=isbn+003921835X
Bittinger, M. L., & Ellenbogen, D. J. (2006). Intermediate Algebra: Concepts and Applications. Addison-Wesley, 7th ed. ISBN: 0321233867. Searches: [52]https://www.amazon.com/s?k=0321233867 [53]https://www.google.com/search?q=isbn+0321233867 [54]https://lccn.loc.gov/2004062480
Bostrom, N., & Cirkovic, M. M. (Eds.) (2008). Global Catastrophic Risks. Oxford University Press. ISBN: 978-0199606504. Searches: [55]https://www.amazon.com/s?k=978-0199606504 [56]https://www.google.com/search?q=isbn+978-0199606504 [57]https://lccn.loc.gov/2008006539
Bulmer, M. G. (1967). Principles of Statistics. Dover, 1979 reprint ed. ISBN: 0486637603. Searches: [58]https://www.amazon.com/s?k=0486637603 [59]https://www.google.com/search?q=isbn+0486637603 [60]https://lccn.loc.gov/78072991
Crawford, K. (2021). Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press. ISBN: 978-0300209570. Searches: [61]https://www.amazon.com/s?k=9780300209570 [62]https://www.google.com/search?q=isbn+9780300209570 [63]https://lccn.loc.gov/2020947842
Frankfurt, H. G. (1988). The Importance of What We Care About. Cambridge. ISBN: 978-0521336116. Searches: [64]https://www.amazon.com/s?k=978-0521336116 [65]https://www.google.com/search?q=isbn+978-0521336116 [66]https://lccn.loc.gov/87026941
Gerrish, S. (2018). How Smart Machines Think. The MIT Press. ISBN: 978-0262038409. Searches: [67]https://www.amazon.com/s?k=9780262038409 [68]https://www.google.com/search?q=isbn+9780262038409 [69]https://lccn.loc.gov/2017059862
Good, I. J. (1965). Speculations concerning the first ultraintelligent machine. Advances in Computers, 6, 31-88. [70]https://exhibits.stanford.edu/feigenbaum/catalog/gz727rg3869 Retrieved 27th Oct. 2020.
Horwich, P. (1982). Probability and Evidence. Cambridge. First published 1982; first paperback 2011; this Cambridge Philosophy Classics edition 2016. ISBN: 978-1316507018. Searches: [71]https://www.amazon.com/s?k=978-1316507018 [72]https://www.google.com/search?q=isbn+978-1316507018 [73]https://lccn.loc.gov/2015049717
Kahneman, D. (2011). Thinking, Fast and Slow. Farrar, Straus and Giroux. ISBN: 978-0374533557. Searches: [74]https://www.amazon.com/s?k=978-0374533557 [75]https://www.google.com/search?q=isbn+978-0374533557 [76]https://lccn.loc.gov/2012533187
Keynes, J. M. (1920). A Treatise on Probability: The Connection Between Philosophy and the History of Science. Wildside Press. ISBN: 978-1434406965. Searches: [77]https://www.amazon.com/s?k=9781434406965 [78]https://www.google.com/search?q=isbn+9781434406965 [79]https://lccn.loc.gov/2004041359
Kramer, E. E. (1970). The Nature and Growth of Modern Mathematics. Hawthorn Books. No ISBN. Searches: [80]https://www.amazon.com/s?k=kramer+nature+and+growth+of+modern+mathematics [81]https://www.google.com/search?q=kramer+nature+and+growth+of+modern+mathematics [82]https://lccn.loc.gov/73091317
Larson, R., Hostetler, R. P., & Edwards, B. H. (2005). College Algebra: A Graphing Approach. Houghton Mifflin, 4th ed. ISBN: 0618394370. Searches: [83]https://www.amazon.com/s?k=0618394370 [84]https://www.google.com/search?q=isbn+0618394370 [85]https://lccn.loc.gov/00104769
Macphail, E. M. (1982). Brain and Intelligence in Vertebrates. Oxford. ISBN 0198545517. Searches: [86]https://www.amazon.com/s?k=0198545517 [87]https://www.google.com/search?q=isbn+0198545517 [88]https://lccn.loc.gov/82166301
Manber, U. (1989). Introduction to Algorithms: A Creative Approach. Addison-Wesley, 1st ed. ISBN: 0201120372. Searches: [89]https://www.amazon.com/s?k=0201120372 [90]https://www.google.com/search?q=isbn+0201120372 [91]https://lccn.loc.gov/88002186
Nisan, N., & Schocken, S. (2005). The Elements of Computing Systems: Building a Modern Computer from First Principles. MIT. ISBN: 978-0262640688. Searches: [92]https://www.amazon.com/s?k=978-0262640688 [93]https://www.google.com/search?q=isbn+978-0262640688 [94]https://lccn.loc.gov/2005042807
Okasha, S. (2002). Philosophy of Science: A Very Short Introduction. Oxford University Press. ISBN: 0192802836. Searches: [95]https://www.amazon.com/s?k=0192802836 [96]https://www.google.com/search?q=isbn+0192802836 [97]https://lccn.loc.gov/2002510456
Retraice (2020/09/07). Re1: Three Kinds of Intelligence. retraice.com. [98]https://www.retraice.com/segments/re1 Retrieved 22nd Sep. 2020.
Retraice (2020/11/02). Re10: Living to Guess Another Day. retraice.com. [99]https://www.retraice.com/segments/re10 Retrieved 2nd Nov. 2020.
Retraice (2020/11/10). Re13: The Care Factor. retraice.com. [100]https://www.retraice.com/segments/re13 Retrieved 10th Nov. 2020.
Retraice (2020/11/25). Re15: Trust and Sources. retraice.com. [101]https://www.retraice.com/segments/re15 Retrieved 28th Feb. 2022.
Retraice (2022/03/07). Re18: Plan of Attack. retraice.com. [102]https://www.retraice.com/segments/re18 Retrieved 25th Mar. 2022.
Retraice (2022/10/10). Re19: Nature Is Not F-ing Around. retraice.com. [103]https://www.retraice.com/segments/re19 Retrieved 12th Oct. 2022.
Retraice (2022/10/19). Re23: You Need a World Model. retraice.com. [104]https://www.retraice.com/segments/re23 Retrieved 20th Oct. 2022.
Retraice (2022/10/23). Re27: Now That's a World Model - WM4. retraice.com. [105]https://www.retraice.com/segments/re27 Retrieved 24th Oct. 2022.
Retraice (2022/10/24). Re28: What's Good? RTFM. retraice.com. [106]https://www.retraice.com/segments/re28 Retrieved 25th Oct. 2022.
Retraice (2022/10/31). Re36: Notes on Conspiracy. retraice.com. [107]https://www.retraice.com/segments/re36 Retrieved 4th Nov. 2022.
Retraice (2022/11/12). Re48: From Drugs to Mao to Money. retraice.com. [108]https://www.retraice.com/segments/re48 Retrieved 14th Nov. 2022.
Retraice (2022/11/16). Re52: Big Questions About AI. retraice.com. [109]https://www.retraice.com/segments/re52 Retrieved 17th Nov. 2022.
Retraice (2022/11/21). Re57: AI, Agents, Problem-solving, Searching, Environments, Games (AIMA4e chpts. 1-6). retraice.com. [110]https://www.retraice.com/segments/re57 Retrieved 22nd Nov. 2022.
Retraice (2022/11/22). Re58: Thinking and Uncertainty (AIMA4e chpts. 7-18). retraice.com. [111]https://www.retraice.com/segments/re58 Retrieved 23rd Nov. 2022.
Retraice (2022/11/23). Re59: Learning, Interacting, Conclusions (AIMA4e chpts. 19-28). retraice.com. [112]https://www.retraice.com/segments/re59 Retrieved 24th Nov. 2022.
Retraice (2022/11/24). Re60: Complexity, Linear Algebra, Probability (AIMA4e Appendix A). retraice.com. [113]https://www.retraice.com/segments/re60 Retrieved 25th Nov. 2022.
Retraice (2022/11/25). Re61: Formal Languages, Pseudocode (AIMA4e Appendix B). retraice.com. [114]https://www.retraice.com/segments/re61 Retrieved 26th Nov. 2022.
Retraice (2022/11/26). Re62: AIMA4e in 5 Minutes. retraice.com. [115]https://www.retraice.com/segments/re62 Retrieved 27th Nov. 2022.
Russell, B. (1948). Human Knowledge: Its Scope and Limits. Routledge. First published in 1948. This edition 1992. ISBN: 0415083028. Searches: [116]https://archive.org/search.php?query=Human%20Knowledge%3A%20Its%20Scope%20and%20Limits [117]https://www.amazon.com/s?k=0415083028 [118]https://www.google.com/search?q=isbn+0415083028 [119]https://lccn.loc.gov/94209784
Russell, B. (1959). My Philosophical Development. Wnwin Brothers. No ISBN. [120]https://archive.org/details/myphilosophicald0000russ/page/n11/mode/2up Retrieved 06 Jun. 2021. Searches: [121]https://www.amazon.com/s?k=Russell+My+Philosophical+Development [122]https://www.google.com/search?q=Russell+My+Philosophical+Development [123]https://lccn.loc.gov/59003496
Russell, S. (2019). Human Compatible: Artificial Intelligence and the Problem of Control. Viking. ISBN: 978-0525558613. Searches: [124]https://www.amazon.com/s?k=978-0525558613 [125]https://www.google.com/search?q=isbn+978-0525558613 [126]https://lccn.loc.gov/2019029688
Thompson, K. (1984). Reflections on trusting trust. Communications of the ACM, 27(8), 761-763. Aug. 1984. [127]https://doi.org/10.1145/358198.358210 Also available at: [128]https://www.cs.cmu.edu/~rdriley/487/papers/Thompson_1984_ReflectionsonTrustingTrust.pdf Retrieved 4th Dec. 2020.
Vallee, J. (1979). Messengers of Deception: UFO Contacts and Cults. And/Or Press. ISBN: 0915904381. Different edition and searches: [129]https://archive.org/details/MessengersOfDeceptionUFOContactsAndCultsJacquesValle1979/mode/2up [130]https://www.amazon.com/s?k=0915904381 [131]https://www.google.com/search?q=isbn+0915904381 [132]https://catalog.loc.gov/vwebv/search?searchArg=0915904381
Yudkowsky, E. (2008). Artificial intelligence as a positive and negative factor in global risk. (pp. 308-345). In [133]Bostrom & Cirkovic ([134]2008).
References
1. https://retraice.com/ 2. XReSeg57 3. XReSeg57 4. XReSeg58 5. XReSeg58 6. XReSeg58 7. XReSeg58 8. XReSeg59 9. XReSeg59 10. XReSeg60 11. XReSeg60 12. XReSeg61 13. XReSeg61 14. XReSeg62 15. XReSeg62 16. fn1x0 17. fn2x0 18. fn3x0 19. fn4x0 20. fn5x0 21. fn6x0 22. fn7x0 23. fn8x0 24. fn9x0 25. fn10x0 26. fn11x0 27. fn12x0 28. fn13x0 29. fn14x0 30. fn15x0 31. fn16x0 32. fn17x0 33. fn18x0 34. fn19x0 35. fn20x0 36. fn21x0 37. https://www.deepmind.com/publications/reward-is-enough 38. https://arxiv.org/abs/1706.03762 39. fn22x0 40. fn23x0 41. fn24x0 42. fn25x0 43. fn26x0 44. fn27x0 45. fn28x0 46. fn29x0 47. https://www.amazon.com/s?k=0486409163 48. https://www.google.com/search?q=isbn+0486409163 49. https://lccn.loc.gov/99033023 50. https://www.amazon.com/s?k=003921835X 51. https://www.google.com/search?q=isbn+003921835X 52. https://www.amazon.com/s?k=0321233867 53. https://www.google.com/search?q=isbn+0321233867 54. https://lccn.loc.gov/2004062480 55. https://www.amazon.com/s?k=978-0199606504 56. https://www.google.com/search?q=isbn+978-0199606504 57. https://lccn.loc.gov/2008006539 58. https://www.amazon.com/s?k=0486637603 59. https://www.google.com/search?q=isbn+0486637603 60. https://lccn.loc.gov/78072991 61. https://www.amazon.com/s?k=9780300209570 62. https://www.google.com/search?q=isbn+9780300209570 63. https://lccn.loc.gov/2020947842 64. https://www.amazon.com/s?k=978-0521336116 65. https://www.google.com/search?q=isbn+978-0521336116 66. https://lccn.loc.gov/87026941 67. https://www.amazon.com/s?k=9780262038409 68. https://www.google.com/search?q=isbn+9780262038409 69. https://lccn.loc.gov/2017059862 70. https://exhibits.stanford.edu/feigenbaum/catalog/gz727rg3869 71. https://www.amazon.com/s?k=978-1316507018 72. https://www.google.com/search?q=isbn+978-1316507018 73. https://lccn.loc.gov/2015049717 74. https://www.amazon.com/s?k=978-0374533557 75. https://www.google.com/search?q=isbn+978-0374533557 76. https://lccn.loc.gov/2012533187 77. https://www.amazon.com/s?k=9781434406965 78. https://www.google.com/search?q=isbn+9781434406965 79. https://lccn.loc.gov/2004041359 80. https://www.amazon.com/s?k=kramer+nature+and+growth+of+modern+mathematics 81. https://www.google.com/search?q=kramer+nature+and+growth+of+modern+mathematics 82. https://lccn.loc.gov/73091317 83. https://www.amazon.com/s?k=0618394370 84. https://www.google.com/search?q=isbn+0618394370 85. https://lccn.loc.gov/00104769 86. https://www.amazon.com/s?k=0198545517 87. https://www.google.com/search?q=isbn+0198545517 88. https://lccn.loc.gov/82166301 89. https://www.amazon.com/s?k=0201120372 90. https://www.google.com/search?q=isbn+0201120372 91. https://lccn.loc.gov/88002186 92. https://www.amazon.com/s?k=978-0262640688 93. https://www.google.com/search?q=isbn+978-0262640688 94. https://lccn.loc.gov/2005042807 95. https://www.amazon.com/s?k=0192802836 96. https://www.google.com/search?q=isbn+0192802836 97. https://lccn.loc.gov/2002510456 98. https://www.retraice.com/segments/re1 99. https://www.retraice.com/segments/re10 100. https://www.retraice.com/segments/re13 101. https://www.retraice.com/segments/re15 102. https://www.retraice.com/segments/re18 103. https://www.retraice.com/segments/re19 104. https://www.retraice.com/segments/re23 105. https://www.retraice.com/segments/re27 106. https://www.retraice.com/segments/re28 107. https://www.retraice.com/segments/re36 108. https://www.retraice.com/segments/re48 109. https://www.retraice.com/segments/re52 110. https://www.retraice.com/segments/re57 111. https://www.retraice.com/segments/re58 112. https://www.retraice.com/segments/re59 113. https://www.retraice.com/segments/re60 114. https://www.retraice.com/segments/re61 115. https://www.retraice.com/segments/re62 116. https://archive.org/search.php?query=Human%20Knowledge%3A%20Its%20Scope%20and%20Limits 117. https://www.amazon.com/s?k=0415083028 118. https://www.google.com/search?q=isbn+0415083028 119. https://lccn.loc.gov/94209784 120. https://archive.org/details/myphilosophicald0000russ/page/n11/mode/2up 121. https://www.amazon.com/s?k=Russell+My+Philosophical+Development 122. https://www.google.com/search?q=Russell+My+Philosophical+Development 123. https://lccn.loc.gov/59003496 124. https://www.amazon.com/s?k=978-0525558613 125. https://www.google.com/search?q=isbn+978-0525558613 126. https://lccn.loc.gov/2019029688 127. https://doi.org/10.1145/358198.358210 128. https://www.cs.cmu.edu/~rdriley/487/papers/Thompson_1984_ReflectionsonTrustingTrust.pdf 129. https://archive.org/details/MessengersOfDeceptionUFOContactsAndCultsJacquesValle1979/mode/2up 130. https://www.amazon.com/s?k=0915904381 131. https://www.google.com/search?q=isbn+0915904381 132. https://catalog.loc.gov/vwebv/search?searchArg=0915904381 133. XGCR 134. XGCR
