On Thu, Jul 6, 2023 at 1:09 AM Rob Freeman <[email protected]>
wrote:

> ...

I just always believed the goal of compression was wrong.

You're really confused.

First, you're conflating lossless compression with lossy compression.
Lossless compression is simply Occam's Razor.
Lossy compression is Confirmation Bias or what I like to call Occam's
Chainsaw Massacre.  Whenever you see someone dissing Occam's Razor you're
always seeing someone dissing Occam's Chainsaw Massacre, not Occam's Razor.

Second, it doesn't matter what you do -- you can't escape the fact that
buried in your premises is Occam's Razor if what you are doing is natural
science.  Even Wigner screwed this up so don't feel bad.  But just consider
this:

If you're going to try to model the world you're going to be doing so in
the form of arithmetic so that you can calculate predictions based on your
model.  If you use arithmetic to do calculations you've just
unintentionally adopted the assumption of Solomonoff Induction.  Until you
understand that, you don't understand the *aspect* of "intelligence" that
involves *understanding*.  So you really are just off in the philosophical
weeds.  Better get that straight before you try to go further with
"intelligence" including, say, deriving the laws of physics so you can
construct dynamical systems that exhibit chaos.

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T42db51de471cbcb9-Me4a8de90718ea5a5b75563e3
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to