Reply to thread

Message

<blockquote data-quote="jmucchiello" data-source="post: 3621710" data-attributes="member: 813">There are two different kinds of &quot;modifying itself&quot;. The kind you described I understood as being able to move opcodes within its running structure to create new execution paths that never existed before. I reject that as being necessary.The other kind of self-modifying involves manipulating values in a lookup table that weighs the &quot;goodness&quot; of a code pathway based on how well its worked before, i.e. a neural network (or similar construct) where the numbers in the cells are addressable by the neural network. The underlying code is just a neural network library calling each subnet and passing the results on to the next subnet and that code is forever fixed. Each subnet is independent and responsible for a small detail in the overall &quot;intelligence&quot;. Connected correctly and bootstrapped correctly, an intelligence would emerge and begin thinking, pondering, and exploring the world outside itself.The human intelligence is bootstrapped with <a href="http://www.ornl.gov/sci/techresources/Human_Genome/posters/chromosome/faqs.shtml#sizes" target="_blank">several billion</a> data points. You then need to add vast amounts of proteins and carbohydrates in the proper order and quanity to grow the substrate I refer to. After a few years the substrate gets the point where that intelligence is apparent and somewhat communicative. Whether or not a machine substrate will attain &quot;visible&quot; intelligence faster than the biological one seems &quot;likely&quot; but I don't want to assume.</blockquote>

[QUOTE="jmucchiello, post: 3621710, member: 813"] There are two different kinds of "modifying itself". The kind you described I understood as being able to move opcodes within its running structure to create new execution paths that never existed before. I reject that as being necessary. The other kind of self-modifying involves manipulating values in a lookup table that weighs the "goodness" of a code pathway based on how well its worked before, i.e. a neural network (or similar construct) where the numbers in the cells are addressable by the neural network. The underlying code is just a neural network library calling each subnet and passing the results on to the next subnet and that code is forever fixed. Each subnet is independent and responsible for a small detail in the overall "intelligence". Connected correctly and bootstrapped correctly, an intelligence would emerge and begin thinking, pondering, and exploring the world outside itself. The human intelligence is bootstrapped with [url=http://www.ornl.gov/sci/techresources/Human_Genome/posters/chromosome/faqs.shtml#sizes]several billion[/url] data points. You then need to add vast amounts of proteins and carbohydrates in the proper order and quanity to grow the substrate I refer to. After a few years the substrate gets the point where that intelligence is apparent and somewhat communicative. Whether or not a machine substrate will attain "visible" intelligence faster than the biological one seems "likely" but I don't want to assume. [/QUOTE]

Verification