Contents xvii
12 The Engineering and Development of Ethics..........................005. 205 121 JPOAWMEtIOH, «205 sa2ms emees Cees ENNeS LE SMES MEME OEMS SERS EME!s dees em; 205 12.2 Review of Current Thinking on the Risks of AGI ................ 00.0002 eee 206 12.3 The Value of an Explicit Goal System. ....... 0.0... eee ee ee 209 12.4 Ethical Synergy ...... 0.00. eee eee tenet eae 210
12.4.1 Stages of Development of Declarative Ethics .................2..000005 211 12.4.2 Stages of Development of Empathic Ethics .....................2.2-- 214 12.4.3 An Integrative Approach to Ethical Development..................... 215 12.4.4 Integrative Ethics and Integrative AGI ...................0 0. eee eee 216 12.5 Clarifying the Ethics of Justice: Extending the Golden Rule in to a Multifactorial Ethical Model ..........0..000 000 cc eee eee 219 12.5.1 The Golden Rule and the Stages of Ethical Development ............. 222 12.5.2 The Need for Context-Sensitivity and Adaptiveness in Deploying Ethical Principles .......0.0.000 0000 ec eee eee 223 12.6 The Ethical Treatment of AGIs ..........0...0 000 c cece ee 226 12.6.1 Possible Consequences of Depriving AGIs of Freedom ................. 228 12.6.2 AGI Ethics as Boundaries Between Humans and AGIs Become Blurred . 229 12.7 Possible Benefits of Closely Linking AGIs to the Global Brain................ 230 12.7.1 The Importance of Fostering Deep, Consensus-Building Interactions Between People with Divergent Views............... 00.0: e ee eee 231 12.8 Possible Benefits of Creating Societies of AGIS ........... 00. cece eee eee 233 12.9 AGI Ethics As Related to Various Future Scenarios ................00 00 eee 234 12.9.1 Capped Intelligence Scenarios ...........00.. 0000 eects 234 12.9.2 Superintelligent AI: Soft-Takeoff Scenarios ................0 0020.00 e eee 235 12.9.3 Superintelligent AI: Hard-Takeoff Scenarios .................2.000005 235 12.9.4 Global Brain Mindplex Scenarios ..............0.0..00 000 eee eee 237 12.10Conclusion: Eight Ways to Bias AGI Toward Friendliness.................... 239 12.10.1 Encourage Measured Co-Advancement of AGI Software and AGI Ethics TDCOLY +s esos WES UES URES UR ERISA CREE CRESS ERERG BAERS BRESS Bret 241 12.10.2Develop Advanced AGI Sooner Not Later .................0..002205- 241
Section IV Networks for Explicit and Implicit Knowledge Representation
13 Local, Global and Glocal Knowledge Representation...................... 245 13.1 Introduction ..........000 0002 eens 245 13.2 Localized Knowledge Representation using Weighted, Labeled Hypergraphs .... 246
13.2.1 Weighted, Labeled Hypergraphs............... 0000: c eee eee eee eee 246 13.3 Atoms: Their Types and Weights ............ 0.00. cee cee eee eee eee 247 13.3.1 Some Basic Atom Types .......... 0.0.00 eee eee 247 13.3.2 Variable Atoms ..........0 000000 cee teen ee 249 13.368 Logical Links o3 casms ease ones os oWams EW EMS EWES ERS BREE BREWS Bm: 251 13.3.4 Temporal Links ..........00 0.00000 tenes 252 13.3.5 Associative Links... 0.2.0.0... 0000 eee ee 253 13.3.6 Procedure Nodes .........00..00 00 cette eee 254 13.3.7 Links for Special External Data Types ..............0 002.00 eee eee eee 254 13.3.8 Truth Values and Attention Values ........... 0.00.00 eee eee eee eee 255 13.4 Knowledge Representation via Attractor Neural Networks ................... 256
HOUSE_OVERSIGHT_012913