Epstein Secrets

Supercompilation 319 18.3.1 Three Aspects of Supercompilation 321 18.3.2 Supercompilation for Goal-Directed Program Modification 322 18.4 Self-Modification via Theorem-Proving 323 A Glossary 325 A.1 List of Specialized Acronyms 325 A.2 Glossary of Specialized Terms 326 References 343 EFTA006

n V A Path to Human-Level AGI 16 AGI Preschool 289 16.1 Introduction 289 16.1.1 Contrast to Standard AI Evaluation Methodologies 290 16.2 Elements of Preschool Design 291 16.3 Elements of Preschool Curriculum 292 16.3.1 Preschool in the Light of Intelligence Theory 293 16.4 Task-Based Assessment in AGI P

cision graph looks like: Input: List L Output: List If ( P1 (L) ) N1(L) Else If ( P2 (L) ) N2 (L) Else If ( Pk (L) ) Nk(L) EFTA00624098 18.4 Self-Modification via Theorem-Proving 323 where the Pi are predicates, and the Ni are schemata corresponding to other nodes of the decision graph (children of the c

d "transfer learning," where the goal for an AI is to learn one task quicker given another task solved previously 10%117, TM95, EFTA00624066 16.2 Elements of Preschool Design 291 )1C05j. This is one of the capabilities an AI agent will need to simultaneously lear❑ different types of tasks as proposed in the Preschool sc

cts of Supercompilation .............0..00 000022 eee eee ee 321 18.3.2 Supercompilation for Goal-Directed Program Modification............. 322 18.4 Self-Modification via Theorem-Proving ........... 0.00 eee eee eee 323 A Glossary ..... 0.00000 tne teen eee 325 A.1 List of Specialized Acronyms.........0.. 00 0c ce

een eens 289 16.1 Introduction .......... 0.0000 teen teens 289 16.1.1 Contrast to Standard AI Evaluation Methodologies ................... 290 16.2 Elements of Preschool Design ...........00 0.00 e eee eee eee 291 16.3 Elements of Preschool Curriculum ........0... 00000 c eee eee eee 292 16.3.1 Preschool in the Light of Inte

nt decision graphs. The decision graph leading to maximal optimization, may not be the one that leads CogPrime cognition in optimal directions. 18.4 Self-Modification via Theorem-Proving Supercompilation is a potentially very valuable tool for self-modification. If one wants to take an existing schema and graduall

fer learning,” where the goal for an AT is to learn one task quicker given another task solved previously [Car97, TM95, HOUSE_OVERSIGHT_013206 16.2 Elements of Preschool Design 291 BDS03, TSO07, RZDKO5]. This is one of the capabilities an AI agent will need to simultaneously learn different types of tasks as proposed in the