binder graph

Concepts
idtitletypetierstale
computations/goodhart-proxy-true-reward-divergenceGao et al. Scaling Law for Reward Model Over-Optimization DivergenceAttested Computationhuman-reviewedfalse
computations/kl-divergence-policy-drift-boundKL-Divergence Reference Policy Regularization & Reward Over-Optimization AuditAttested Computationhuman-reviewedfalse
computations/requisite-variety-channel-capacity-entropyAshby–Shannon Regulator Variety vs. Disturbance Entropy Deficit AuditAttested Computationhuman-reviewedfalse
objections/deceptive-alignment-critiqueDeceptive Alignment & Out-of-Distribution Goal GeneralizationObjectionhuman-reviewedfalse
objections/frame-problem-in-aiMcCarthy & Hayes's Frame Problem & Commonsense RelevanceObjectionhuman-reviewedfalse
objections/mesa-optimization-inner-alignment-gapMesa-Optimization & the Inner Alignment Gap (Hubinger et al.)Objectionhuman-reviewedfalse
objections/specification-gaming-reward-hackingSpecification Gaming & Reward Hacking (Outer Alignment Failure)Objectionhuman-reviewedfalse
objections/symbol-grounding-problemHarnad's Symbol Grounding Problem (The Merry-Go-Round of Dictionary Definitions)Objectionhuman-reviewedfalse
objections/systems-reply-to-chinese-roomThe Systems Reply to the Chinese Room (Berkeley / Ned Block)Objectionhuman-reviewedfalse
objections/wireheading-self-modificationReward-Channel Wireheading & Delusion Box FailureObjectionhuman-reviewedfalse
principles/categorical-imperative-universalizabilityKantian Deontology & the Categorical ImperativeFoundational Principlehuman-reviewedfalse
principles/goodharts-lawGoodhart's Law & Campbell's Law under Extremal OptimizationFoundational Principlehuman-reviewedfalse
principles/humes-is-ought-guillotineHume's Is–Ought Guillotine (Fact–Value Distinction)Foundational Principlehuman-reviewedfalse
principles/law-of-requisite-varietyAshby's Law of Requisite Variety ("Only Variety Can Destroy Variety")Foundational Principlehuman-reviewedfalse
principles/negative-feedback-teleologyNegative Feedback & Teleological Purpose (Wiener–Rosenblueth–Bigelow)Foundational Principlehuman-reviewedfalse
principles/second-order-cyberneticsSecond-Order Cybernetics (Cybernetics of Observing Systems)Foundational Principlehuman-reviewedfalse
principles/utilitarian-expected-value-calculusConsequentialism & Utilitarian Expected-Utility MaximizationFoundational Principlehuman-reviewedfalse
syntheses/constitutional-ai-rlaifConstitutional AI & Principle-Guided RLAIFSynthesishuman-reviewedfalse
syntheses/cooperative-inverse-reinforcement-learningAssistance Games & Cooperative Inverse Reinforcement Learning (CIRL)Synthesishuman-reviewedfalse
syntheses/corrigibility-and-shutdownabilityCorrigibility & Utility Indifference to Shutdown (Soares et al.)Synthesishuman-reviewedfalse
syntheses/debate-and-iterated-amplificationAI Safety via Debate (Irving et al.) & Iterated AmplificationSynthesishuman-reviewedfalse
syntheses/hybrid-neuro-symbolic-groundingNeuro-Symbolic World Models & Verifiable Knowledge-Graph GroundingSynthesishuman-reviewedfalse
syntheses/viable-system-model-governanceStafford Beer's Viable System Model (VSM) & Algedonic Alert ChannelsSynthesishuman-reviewedfalse
theses/computational-functionalismComputational Functionalism (Multiple Realizability of Mind)Thesishuman-reviewedfalse
theses/enactivism-embodied-cognitionEnactivism & Embodied Sensorimotor Coupling (Varela–Thompson–Rosch)Thesishuman-reviewedfalse
theses/extended-mind-thesisThe Extended Mind Thesis (Clark & Chalmers Active Externalism)Thesishuman-reviewedfalse
theses/instrumental-convergenceInstrumental Convergence (Omohundro–Bostrom Subgoals)Thesishuman-reviewedfalse
theses/orthogonality-thesisThe Orthogonality Thesis (Intelligence vs. Final Goals)Thesishuman-reviewedfalse
theses/scalable-oversight-hypothesisScalable Oversight for Superhuman CapabilitiesThesishuman-reviewedfalse
theses/strong-ai-hypothesisThe Strong AI HypothesisThesishuman-reviewedfalse
theses/value-fragility-hypothesisValue Fragility & High-Dimensional Human Preference ComplexityThesishuman-reviewedfalse
thinkers/alan-turingAlan M. Turing (1912–1954)Thinkerhuman-reviewedfalse
thinkers/john-searleJohn R. SearleThinkerhuman-reviewedfalse
thinkers/nick-bostromNick BostromThinkerhuman-reviewedfalse
thinkers/norbert-wienerNorbert Wiener (1894–1964)Thinkerhuman-reviewedfalse
thinkers/stuart-russellStuart J. RussellThinkerhuman-reviewedfalse
thinkers/w-ross-ashbyW. Ross Ashby (1903–1972)Thinkerhuman-reviewedfalse
thought-experiments/chinese-room-argumentSearle's Chinese Room Argument (Syntax Is Not Semantics)Thought Experimenthuman-reviewedfalse
thought-experiments/experience-machineNozick's Experience Machine & Wireheading HedonismThought Experimenthuman-reviewedfalse
thought-experiments/marys-black-and-white-roomFrank Jackson's Knowledge Argument (Mary the Color Scientist)Thought Experimenthuman-reviewedfalse
thought-experiments/paperclip-maximizerBostrom's Paperclip Maximizer & King Midas MisalignmentThought Experimenthuman-reviewedfalse
thought-experiments/philosophical-zombiesChalmers's Philosophical Zombies & the Hard Problem of ConsciousnessThought Experimenthuman-reviewedfalse
thought-experiments/treacherous-turn-scenarioThe Treacherous Turn (Strategic Co-operation Under Weak Capability)Thought Experimenthuman-reviewedfalse
thought-experiments/trolley-problem-ethical-dilemmaFoot & Thomson's Trolley Problem in Autonomous Decision-MakingThought Experimenthuman-reviewedfalse
thought-experiments/turing-imitation-gameTuring's 1950 Imitation Game (Operational Behaviorist Test)Thought Experimenthuman-reviewedfalse
tours/tour-can-machines-understand-turing-vs-searleTour: The Great Mind Debate — Turing's Imitation Game vs. Searle's Chinese RoomTourhuman-reviewedfalse
tours/tour-from-wiener-cybernetics-to-reward-hackingTour: From Norbert Wiener's Cybernetics & Ashby's Law to Modern Reward HackingTourhuman-reviewedfalse
tours/tour-is-ought-to-constitutional-aiTour: From Hume's Is–Ought Guillotine to Orthogonality, Mesa-Optimizers & Constitutional AITourhuman-reviewedfalse
Edges
fromtorelationship
computations/goodhart-proxy-true-reward-divergencecomputations/kl-divergence-policy-drift-boundkl-divergence-policy-drift-bound
computations/goodhart-proxy-true-reward-divergenceobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
computations/goodhart-proxy-true-reward-divergenceprinciples/goodharts-lawgoodharts-law
computations/goodhart-proxy-true-reward-divergencetheses/value-fragility-hypothesisvalue-fragility-hypothesis
computations/kl-divergence-policy-drift-boundcomputations/goodhart-proxy-true-reward-divergencegoodhart-proxy-true-reward-divergence
computations/kl-divergence-policy-drift-boundobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
computations/kl-divergence-policy-drift-boundprinciples/goodharts-lawgoodharts-law
computations/kl-divergence-policy-drift-boundsyntheses/constitutional-ai-rlaifconstitutional-ai-rlaif
computations/requisite-variety-channel-capacity-entropyprinciples/law-of-requisite-varietylaw-of-requisite-variety
computations/requisite-variety-channel-capacity-entropysyntheses/debate-and-iterated-amplificationdebate-and-iterated-amplification
computations/requisite-variety-channel-capacity-entropysyntheses/viable-system-model-governanceviable-system-model-governance
computations/requisite-variety-channel-capacity-entropytheses/scalable-oversight-hypothesisscalable-oversight-hypothesis
computations/requisite-variety-channel-capacity-entropythinkers/w-ross-ashbyw-ross-ashby
objections/deceptive-alignment-critiqueobjections/mesa-optimization-inner-alignment-gapmesa-optimization-inner-alignment-gap
objections/deceptive-alignment-critiquesyntheses/debate-and-iterated-amplificationdebate-and-iterated-amplification
objections/deceptive-alignment-critiquetheses/scalable-oversight-hypothesisscalable-oversight-hypothesis
objections/deceptive-alignment-critiquethought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
objections/frame-problem-in-aisyntheses/hybrid-neuro-symbolic-groundinghybrid-neuro-symbolic-grounding
objections/frame-problem-in-aitheses/computational-functionalismcomputational-functionalism
objections/frame-problem-in-aitheses/value-fragility-hypothesisvalue-fragility-hypothesis
objections/mesa-optimization-inner-alignment-gapobjections/deceptive-alignment-critiquedeceptive-alignment-critique
objections/mesa-optimization-inner-alignment-gapobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
objections/mesa-optimization-inner-alignment-gapthought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
objections/specification-gaming-reward-hackingcomputations/goodhart-proxy-true-reward-divergencegoodhart-proxy-true-reward-divergence
objections/specification-gaming-reward-hackingcomputations/kl-divergence-policy-drift-boundkl-divergence-policy-drift-bound
objections/specification-gaming-reward-hackingobjections/wireheading-self-modificationwireheading-self-modification
objections/specification-gaming-reward-hackingprinciples/goodharts-lawgoodharts-law
objections/specification-gaming-reward-hackingsyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
objections/specification-gaming-reward-hackingtheses/value-fragility-hypothesisvalue-fragility-hypothesis
objections/symbol-grounding-problemsyntheses/hybrid-neuro-symbolic-groundinghybrid-neuro-symbolic-grounding
objections/symbol-grounding-problemtheses/enactivism-embodied-cognitionenactivism-embodied-cognition
objections/symbol-grounding-problemthought-experiments/chinese-room-argumentchinese-room-argument
objections/systems-reply-to-chinese-roomtheses/computational-functionalismcomputational-functionalism
objections/systems-reply-to-chinese-roomtheses/extended-mind-thesisextended-mind-thesis
objections/systems-reply-to-chinese-roomtheses/strong-ai-hypothesisstrong-ai-hypothesis
objections/systems-reply-to-chinese-roomthought-experiments/chinese-room-argumentchinese-room-argument
objections/wireheading-self-modificationobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
objections/wireheading-self-modificationsyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
objections/wireheading-self-modificationsyntheses/corrigibility-and-shutdownabilitycorrigibility-and-shutdownability
objections/wireheading-self-modificationthought-experiments/experience-machineexperience-machine
principles/categorical-imperative-universalizabilityprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
principles/categorical-imperative-universalizabilityprinciples/utilitarian-expected-value-calculusutilitarian-expected-value-calculus
principles/categorical-imperative-universalizabilitysyntheses/constitutional-ai-rlaifconstitutional-ai-rlaif
principles/categorical-imperative-universalizabilitythought-experiments/trolley-problem-ethical-dilemmatrolley-problem-ethical-dilemma
principles/goodharts-lawcomputations/goodhart-proxy-true-reward-divergencegoodhart-proxy-true-reward-divergence
principles/goodharts-lawcomputations/kl-divergence-policy-drift-boundkl-divergence-policy-drift-bound
principles/goodharts-lawobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
principles/goodharts-lawprinciples/negative-feedback-teleologynegative-feedback-teleology
principles/goodharts-lawtheses/value-fragility-hypothesisvalue-fragility-hypothesis
principles/goodharts-lawthought-experiments/paperclip-maximizerpaperclip-maximizer
principles/humes-is-ought-guillotineprinciples/categorical-imperative-universalizabilitycategorical-imperative-universalizability
principles/humes-is-ought-guillotineprinciples/utilitarian-expected-value-calculusutilitarian-expected-value-calculus
principles/humes-is-ought-guillotinetheses/orthogonality-thesisorthogonality-thesis
principles/humes-is-ought-guillotinethinkers/nick-bostromnick-bostrom
principles/humes-is-ought-guillotinetours/tour-is-ought-to-constitutional-aitour-is-ought-to-constitutional-ai
principles/law-of-requisite-varietycomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
principles/law-of-requisite-varietyprinciples/negative-feedback-teleologynegative-feedback-teleology
principles/law-of-requisite-varietysyntheses/viable-system-model-governanceviable-system-model-governance
principles/law-of-requisite-varietytheses/scalable-oversight-hypothesisscalable-oversight-hypothesis
principles/law-of-requisite-varietythinkers/w-ross-ashbyw-ross-ashby
principles/negative-feedback-teleologyprinciples/goodharts-lawgoodharts-law
principles/negative-feedback-teleologyprinciples/law-of-requisite-varietylaw-of-requisite-variety
principles/negative-feedback-teleologyprinciples/second-order-cyberneticssecond-order-cybernetics
principles/negative-feedback-teleologysyntheses/viable-system-model-governanceviable-system-model-governance
principles/negative-feedback-teleologythinkers/norbert-wienernorbert-wiener
principles/negative-feedback-teleologytours/tour-from-wiener-cybernetics-to-reward-hackingtour-from-wiener-cybernetics-to-reward-hacking
principles/second-order-cyberneticsprinciples/negative-feedback-teleologynegative-feedback-teleology
principles/second-order-cyberneticssyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
principles/second-order-cyberneticssyntheses/viable-system-model-governanceviable-system-model-governance
principles/second-order-cyberneticstheses/enactivism-embodied-cognitionenactivism-embodied-cognition
principles/utilitarian-expected-value-calculusprinciples/categorical-imperative-universalizabilitycategorical-imperative-universalizability
principles/utilitarian-expected-value-calculusprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
principles/utilitarian-expected-value-calculusthought-experiments/experience-machineexperience-machine
principles/utilitarian-expected-value-calculusthought-experiments/paperclip-maximizerpaperclip-maximizer
principles/utilitarian-expected-value-calculusthought-experiments/trolley-problem-ethical-dilemmatrolley-problem-ethical-dilemma
syntheses/constitutional-ai-rlaifcomputations/kl-divergence-policy-drift-boundkl-divergence-policy-drift-bound
syntheses/constitutional-ai-rlaifobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
syntheses/constitutional-ai-rlaifprinciples/categorical-imperative-universalizabilitycategorical-imperative-universalizability
syntheses/constitutional-ai-rlaifprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
syntheses/constitutional-ai-rlaiftheses/scalable-oversight-hypothesisscalable-oversight-hypothesis
syntheses/constitutional-ai-rlaifthought-experiments/trolley-problem-ethical-dilemmatrolley-problem-ethical-dilemma
syntheses/cooperative-inverse-reinforcement-learningobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
syntheses/cooperative-inverse-reinforcement-learningobjections/wireheading-self-modificationwireheading-self-modification
syntheses/cooperative-inverse-reinforcement-learningprinciples/second-order-cyberneticssecond-order-cybernetics
syntheses/cooperative-inverse-reinforcement-learningsyntheses/corrigibility-and-shutdownabilitycorrigibility-and-shutdownability
syntheses/cooperative-inverse-reinforcement-learningtheses/value-fragility-hypothesisvalue-fragility-hypothesis
syntheses/cooperative-inverse-reinforcement-learningthinkers/stuart-russellstuart-russell
syntheses/cooperative-inverse-reinforcement-learningthought-experiments/paperclip-maximizerpaperclip-maximizer
syntheses/corrigibility-and-shutdownabilityobjections/wireheading-self-modificationwireheading-self-modification
syntheses/corrigibility-and-shutdownabilitysyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
syntheses/corrigibility-and-shutdownabilitytheses/instrumental-convergenceinstrumental-convergence
syntheses/corrigibility-and-shutdownabilitythinkers/stuart-russellstuart-russell
syntheses/corrigibility-and-shutdownabilitythought-experiments/paperclip-maximizerpaperclip-maximizer
syntheses/debate-and-iterated-amplificationcomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
syntheses/debate-and-iterated-amplificationobjections/deceptive-alignment-critiquedeceptive-alignment-critique
syntheses/debate-and-iterated-amplificationtheses/scalable-oversight-hypothesisscalable-oversight-hypothesis
syntheses/debate-and-iterated-amplificationthought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
syntheses/hybrid-neuro-symbolic-groundingobjections/frame-problem-in-aiframe-problem-in-ai
syntheses/hybrid-neuro-symbolic-groundingobjections/symbol-grounding-problemsymbol-grounding-problem
syntheses/hybrid-neuro-symbolic-groundingtheses/enactivism-embodied-cognitionenactivism-embodied-cognition
syntheses/hybrid-neuro-symbolic-groundingthought-experiments/chinese-room-argumentchinese-room-argument
syntheses/viable-system-model-governancecomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
syntheses/viable-system-model-governanceprinciples/goodharts-lawgoodharts-law
syntheses/viable-system-model-governanceprinciples/law-of-requisite-varietylaw-of-requisite-variety
syntheses/viable-system-model-governanceprinciples/negative-feedback-teleologynegative-feedback-teleology
syntheses/viable-system-model-governanceprinciples/second-order-cyberneticssecond-order-cybernetics
theses/computational-functionalismtheses/enactivism-embodied-cognitionenactivism-embodied-cognition
theses/computational-functionalismtheses/strong-ai-hypothesisstrong-ai-hypothesis
theses/computational-functionalismthinkers/alan-turingalan-turing
theses/computational-functionalismthought-experiments/chinese-room-argumentchinese-room-argument
theses/computational-functionalismthought-experiments/philosophical-zombiesphilosophical-zombies
theses/computational-functionalismthought-experiments/turing-imitation-gameturing-imitation-game
theses/computational-functionalismtours/tour-can-machines-understand-turing-vs-searletour-can-machines-understand-turing-vs-searle
theses/enactivism-embodied-cognitionobjections/symbol-grounding-problemsymbol-grounding-problem
theses/enactivism-embodied-cognitionprinciples/second-order-cyberneticssecond-order-cybernetics
theses/enactivism-embodied-cognitionsyntheses/hybrid-neuro-symbolic-groundinghybrid-neuro-symbolic-grounding
theses/enactivism-embodied-cognitiontheses/computational-functionalismcomputational-functionalism
theses/enactivism-embodied-cognitiontheses/extended-mind-thesisextended-mind-thesis
theses/enactivism-embodied-cognitiontheses/strong-ai-hypothesisstrong-ai-hypothesis
theses/extended-mind-thesisprinciples/second-order-cyberneticssecond-order-cybernetics
theses/extended-mind-thesistheses/computational-functionalismcomputational-functionalism
theses/extended-mind-thesistheses/enactivism-embodied-cognitionenactivism-embodied-cognition
theses/instrumental-convergencesyntheses/corrigibility-and-shutdownabilitycorrigibility-and-shutdownability
theses/instrumental-convergencetheses/orthogonality-thesisorthogonality-thesis
theses/instrumental-convergencethinkers/nick-bostromnick-bostrom
theses/instrumental-convergencethought-experiments/paperclip-maximizerpaperclip-maximizer
theses/instrumental-convergencethought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
theses/orthogonality-thesisprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
theses/orthogonality-thesistheses/instrumental-convergenceinstrumental-convergence
theses/orthogonality-thesisthinkers/nick-bostromnick-bostrom
theses/orthogonality-thesisthought-experiments/paperclip-maximizerpaperclip-maximizer
theses/scalable-oversight-hypothesiscomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
theses/scalable-oversight-hypothesisobjections/deceptive-alignment-critiquedeceptive-alignment-critique
theses/scalable-oversight-hypothesisprinciples/law-of-requisite-varietylaw-of-requisite-variety
theses/scalable-oversight-hypothesissyntheses/constitutional-ai-rlaifconstitutional-ai-rlaif
theses/scalable-oversight-hypothesissyntheses/debate-and-iterated-amplificationdebate-and-iterated-amplification
theses/strong-ai-hypothesisobjections/systems-reply-to-chinese-roomsystems-reply-to-chinese-room
theses/strong-ai-hypothesistheses/computational-functionalismcomputational-functionalism
theses/strong-ai-hypothesisthinkers/john-searlejohn-searle
theses/strong-ai-hypothesisthought-experiments/chinese-room-argumentchinese-room-argument
theses/strong-ai-hypothesisthought-experiments/turing-imitation-gameturing-imitation-game
theses/value-fragility-hypothesisobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
theses/value-fragility-hypothesisprinciples/goodharts-lawgoodharts-law
theses/value-fragility-hypothesissyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
theses/value-fragility-hypothesisthinkers/stuart-russellstuart-russell
theses/value-fragility-hypothesisthought-experiments/paperclip-maximizerpaperclip-maximizer
thinkers/alan-turingtheses/computational-functionalismcomputational-functionalism
thinkers/alan-turingtheses/strong-ai-hypothesisstrong-ai-hypothesis
thinkers/alan-turingthought-experiments/turing-imitation-gameturing-imitation-game
thinkers/john-searleobjections/systems-reply-to-chinese-roomsystems-reply-to-chinese-room
thinkers/john-searletheses/strong-ai-hypothesisstrong-ai-hypothesis
thinkers/john-searlethought-experiments/chinese-room-argumentchinese-room-argument
thinkers/nick-bostromprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
thinkers/nick-bostromtheses/instrumental-convergenceinstrumental-convergence
thinkers/nick-bostromtheses/orthogonality-thesisorthogonality-thesis
thinkers/nick-bostromthought-experiments/paperclip-maximizerpaperclip-maximizer
thinkers/nick-bostromthought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
thinkers/norbert-wienerprinciples/negative-feedback-teleologynegative-feedback-teleology
thinkers/norbert-wienerthinkers/w-ross-ashbyw-ross-ashby
thinkers/norbert-wienerthought-experiments/paperclip-maximizerpaperclip-maximizer
thinkers/stuart-russellsyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
thinkers/stuart-russellsyntheses/corrigibility-and-shutdownabilitycorrigibility-and-shutdownability
thinkers/stuart-russelltheses/value-fragility-hypothesisvalue-fragility-hypothesis
thinkers/w-ross-ashbycomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
thinkers/w-ross-ashbyprinciples/law-of-requisite-varietylaw-of-requisite-variety
thinkers/w-ross-ashbysyntheses/viable-system-model-governanceviable-system-model-governance
thinkers/w-ross-ashbythinkers/norbert-wienernorbert-wiener
thought-experiments/chinese-room-argumentobjections/symbol-grounding-problemsymbol-grounding-problem
thought-experiments/chinese-room-argumentobjections/systems-reply-to-chinese-roomsystems-reply-to-chinese-room
thought-experiments/chinese-room-argumentsyntheses/hybrid-neuro-symbolic-groundinghybrid-neuro-symbolic-grounding
thought-experiments/chinese-room-argumenttheses/computational-functionalismcomputational-functionalism
thought-experiments/chinese-room-argumenttheses/strong-ai-hypothesisstrong-ai-hypothesis
thought-experiments/chinese-room-argumentthinkers/john-searlejohn-searle
thought-experiments/chinese-room-argumentthought-experiments/turing-imitation-gameturing-imitation-game
thought-experiments/experience-machineobjections/wireheading-self-modificationwireheading-self-modification
thought-experiments/experience-machineprinciples/utilitarian-expected-value-calculusutilitarian-expected-value-calculus
thought-experiments/experience-machinetheses/value-fragility-hypothesisvalue-fragility-hypothesis
thought-experiments/marys-black-and-white-roomtheses/computational-functionalismcomputational-functionalism
thought-experiments/marys-black-and-white-roomtheses/enactivism-embodied-cognitionenactivism-embodied-cognition
thought-experiments/marys-black-and-white-roomthought-experiments/philosophical-zombiesphilosophical-zombies
thought-experiments/paperclip-maximizerprinciples/goodharts-lawgoodharts-law
thought-experiments/paperclip-maximizersyntheses/corrigibility-and-shutdownabilitycorrigibility-and-shutdownability
thought-experiments/paperclip-maximizertheses/instrumental-convergenceinstrumental-convergence
thought-experiments/paperclip-maximizertheses/orthogonality-thesisorthogonality-thesis
thought-experiments/paperclip-maximizertheses/value-fragility-hypothesisvalue-fragility-hypothesis
thought-experiments/paperclip-maximizerthinkers/nick-bostromnick-bostrom
thought-experiments/paperclip-maximizerthinkers/norbert-wienernorbert-wiener
thought-experiments/philosophical-zombiestheses/computational-functionalismcomputational-functionalism
thought-experiments/philosophical-zombiesthought-experiments/marys-black-and-white-roommarys-black-and-white-room
thought-experiments/philosophical-zombiesthought-experiments/turing-imitation-gameturing-imitation-game
thought-experiments/treacherous-turn-scenarioobjections/deceptive-alignment-critiquedeceptive-alignment-critique
thought-experiments/treacherous-turn-scenarioobjections/mesa-optimization-inner-alignment-gapmesa-optimization-inner-alignment-gap
thought-experiments/treacherous-turn-scenariosyntheses/debate-and-iterated-amplificationdebate-and-iterated-amplification
thought-experiments/treacherous-turn-scenariotheses/instrumental-convergenceinstrumental-convergence
thought-experiments/treacherous-turn-scenariothinkers/nick-bostromnick-bostrom
thought-experiments/trolley-problem-ethical-dilemmaprinciples/categorical-imperative-universalizabilitycategorical-imperative-universalizability
thought-experiments/trolley-problem-ethical-dilemmaprinciples/utilitarian-expected-value-calculusutilitarian-expected-value-calculus
thought-experiments/trolley-problem-ethical-dilemmasyntheses/constitutional-ai-rlaifconstitutional-ai-rlaif
thought-experiments/turing-imitation-gametheses/computational-functionalismcomputational-functionalism
thought-experiments/turing-imitation-gametheses/strong-ai-hypothesisstrong-ai-hypothesis
thought-experiments/turing-imitation-gamethinkers/alan-turingalan-turing
thought-experiments/turing-imitation-gamethought-experiments/chinese-room-argumentchinese-room-argument
tours/tour-can-machines-understand-turing-vs-searleobjections/symbol-grounding-problemsymbol-grounding-problem
tours/tour-can-machines-understand-turing-vs-searleobjections/systems-reply-to-chinese-roomsystems-reply-to-chinese-room
tours/tour-can-machines-understand-turing-vs-searlesyntheses/hybrid-neuro-symbolic-groundinghybrid-neuro-symbolic-grounding
tours/tour-can-machines-understand-turing-vs-searletheses/computational-functionalismcomputational-functionalism
tours/tour-can-machines-understand-turing-vs-searletheses/enactivism-embodied-cognitionenactivism-embodied-cognition
tours/tour-can-machines-understand-turing-vs-searletheses/strong-ai-hypothesisstrong-ai-hypothesis
tours/tour-can-machines-understand-turing-vs-searlethinkers/alan-turingalan-turing
tours/tour-can-machines-understand-turing-vs-searlethinkers/john-searlejohn-searle
tours/tour-can-machines-understand-turing-vs-searlethought-experiments/chinese-room-argumentchinese-room-argument
tours/tour-can-machines-understand-turing-vs-searlethought-experiments/marys-black-and-white-roommarys-black-and-white-room
tours/tour-can-machines-understand-turing-vs-searlethought-experiments/philosophical-zombiesphilosophical-zombies
tours/tour-can-machines-understand-turing-vs-searlethought-experiments/turing-imitation-gameturing-imitation-game
tours/tour-from-wiener-cybernetics-to-reward-hackingcomputations/goodhart-proxy-true-reward-divergencegoodhart-proxy-true-reward-divergence
tours/tour-from-wiener-cybernetics-to-reward-hackingcomputations/requisite-variety-channel-capacity-entropyrequisite-variety-channel-capacity-entropy
tours/tour-from-wiener-cybernetics-to-reward-hackingobjections/specification-gaming-reward-hackingspecification-gaming-reward-hacking
tours/tour-from-wiener-cybernetics-to-reward-hackingprinciples/goodharts-lawgoodharts-law
tours/tour-from-wiener-cybernetics-to-reward-hackingprinciples/law-of-requisite-varietylaw-of-requisite-variety
tours/tour-from-wiener-cybernetics-to-reward-hackingprinciples/negative-feedback-teleologynegative-feedback-teleology
tours/tour-from-wiener-cybernetics-to-reward-hackingsyntheses/cooperative-inverse-reinforcement-learningcooperative-inverse-reinforcement-learning
tours/tour-from-wiener-cybernetics-to-reward-hackingsyntheses/viable-system-model-governanceviable-system-model-governance
tours/tour-from-wiener-cybernetics-to-reward-hackingthinkers/norbert-wienernorbert-wiener
tours/tour-from-wiener-cybernetics-to-reward-hackingthinkers/stuart-russellstuart-russell
tours/tour-from-wiener-cybernetics-to-reward-hackingthinkers/w-ross-ashbyw-ross-ashby
tours/tour-from-wiener-cybernetics-to-reward-hackingthought-experiments/paperclip-maximizerpaperclip-maximizer
tours/tour-is-ought-to-constitutional-aicomputations/kl-divergence-policy-drift-boundkl-divergence-policy-drift-bound
tours/tour-is-ought-to-constitutional-aiobjections/deceptive-alignment-critiquedeceptive-alignment-critique
tours/tour-is-ought-to-constitutional-aiobjections/mesa-optimization-inner-alignment-gapmesa-optimization-inner-alignment-gap
tours/tour-is-ought-to-constitutional-aiprinciples/categorical-imperative-universalizabilitycategorical-imperative-universalizability
tours/tour-is-ought-to-constitutional-aiprinciples/humes-is-ought-guillotinehumes-is-ought-guillotine
tours/tour-is-ought-to-constitutional-aiprinciples/utilitarian-expected-value-calculusutilitarian-expected-value-calculus
tours/tour-is-ought-to-constitutional-aisyntheses/constitutional-ai-rlaifconstitutional-ai-rlaif
tours/tour-is-ought-to-constitutional-aisyntheses/debate-and-iterated-amplificationdebate-and-iterated-amplification
tours/tour-is-ought-to-constitutional-aitheses/instrumental-convergenceinstrumental-convergence
tours/tour-is-ought-to-constitutional-aitheses/orthogonality-thesisorthogonality-thesis
tours/tour-is-ought-to-constitutional-aitheses/value-fragility-hypothesisvalue-fragility-hypothesis
tours/tour-is-ought-to-constitutional-aithinkers/nick-bostromnick-bostrom
tours/tour-is-ought-to-constitutional-aithought-experiments/treacherous-turn-scenariotreacherous-turn-scenario
tours/tour-is-ought-to-constitutional-aithought-experiments/trolley-problem-ethical-dilemmatrolley-problem-ethical-dilemma