Epstein Secrets

ki, hamar Arel, Mark Waser, Randal Koene, Paul Rosenbloom, Zhongzhi Shi, Steve Omohundro, Bill Hibbard, Eray Ozkural, Brandon Rohrer, Ben Johnston, John Laird, Shane Legg, Selmer Brin&sjord, Anders Sandberg, Alexei Samsonovich, Wlodek Duch, and more • The inimitable "Artilect Warrior" Hugo de Gans, who (w

ts xix 18 Advanced Self-Modification: A Possible Path to Superhuman AGI 317 18.1 Introduction 317 18.2 Cognitive Schema Learning 318 18.3 Self-Modification via Supercompilation 319 18.3.1 Three Aspects of Supercompilation 321 18.3.2 Supercompilation for Goal-Directed Program Modification 322 18.4 Self-Modification

October 2008. Some of the ideas also trace back to discussions held during two workshops on "Evaluation and Metrics for Human-Level Al" organized by John Laird and Pat Langley (one in Ann Arbor in late 2008, and one in Tempe in early 2009). Some of the conclu- sions of the Ann Arbor workshop were recorded i

set of cognitive tools, however, is to create better cognitive tools. One form this sort of tool-building may take is cognitive EFTA00624094 18.3 Self-Modification via Supercompilation 319 schema learning the learning of schemata carrying out cognitive processes in more specialized, context-dependent ways than the general MindAge

ski, Itamar Arel, Mark Waser, Randal Koene, Paul Rosenbloom, Zhongzhi Shi, Steve Omohundro, Bill Hibbard, Eray Ozkural, Brandon Rohrer, Ben Johnston, John Laird, Shane Legg, Selmer Bringsjord, Anders Sandberg, Alexei Samsonovich, Wlodek Duch, and more The inimitable "Artilect Warrior" Hugo de Garis, who (whe

OAWEtIOH, «205 ses emtes Cees ENNOE LE SMES MEME SEMS SERS EME!s dees ems 317 18.2 Cognitive Schema Learning .......... 0.000 e cee eee eens 318 18.3 Self-Modification via Supercompilation ..............0..00 000 cee eee 319 18.3.1 Three Aspects of Supercompilation .............0..00 000022 eee eee ee 321 18.3.2 Supercompilation for Go

October 2008. Some of the ideas also trace back to discussions held during two workshops on "Evaluation and Metrics for Human-Level AI" organized by John Laird and Pat Langley (one in Ann Arbor in late 2008, and one in Tempe in early 2009). Some of the conclu- sions of the Ann Arbor workshop were recorded in

in this approach the system is thinking about its MindAgents as black boxes rather than being equipped with full knowledge of their internals. 18.3 Self-Modification via Supercompilation Now we turn to a very different form of advanced self-modification: supercompilation. Super- compilation "merely" enables procedures to run much, mu