320 18 Advanced Self-Modification: A Possible Path to Superhuman AGI ‘ implicati ee Fido —™Pication Dog Dog _implication _ _— PLN Deduction Rule (hard-coded in C++ or Python) (8) Fido : —— > Nice implication (a) * imnplicats — N PLN is a set Fido ‘Pucanon Dog Dog impleaten Nice of Schema Nodes that can modify the Atomspace, including modifying PLN rules via their declarative AND versions 1 Declarative representation of Execution Output Link PLN deduction rule > in atomspace % Schema Node PLN deduction Rule List 4—__* MOSES can learn new versions of the PLN deduction rule 2 re Fido 2 Nice . (8) PLN deduction rule Represented as a program Tree in the Procedure Repository (©) Fig. 18.1: Representation of PLN Deduction Rule as Cognitive Content. Top: the current, hard-coded representation of the deduction rule. Bottom: representation of the same rule in the Atomspace as cognitive content, susceptible to analysis and improvement by the system’s own cognitive processes. Furthermore, we suspect that the internal representation of programs used for supercompila- tion is highly relevant for other kinds of self-modification as well. Supercompilation requires one kind of reasoning on complex programs, and goal-directed program creation requires another, but both, we conjecture, can benefit from the same way of looking at programs.