On Mon, Feb 18, 2019 at 2:27 AM Ben Goertzel <b...@goertzel.org> wrote:
> ... > Don't get me wrong tho, I don't think this is the golden path to AGI > or anything.... By contrast, if anyone does want to look for the golden path to AGI, rather than the next step down a dead end as usual! In case someone here is looking for new ideas, rather than just pushing an agenda. I suggest people start thinking about the problem as one of finding a principle by which new, meaningful, patterns, can be created. New, but meaningful, because the principle which creates them is meaningful. Because it is distasteful to constantly push my own work, to get a flavour you might start with someone else's work I discovered recently: "Structural Emergence in Partially Ordered Sets is the Key to Intelligence" http://sergio.pissanetzky.com/Publications/AGI2011.pdf Pissanetzky defines "meaning" as "invariants" in ways of permuting cause-effect pairs in the observed world. With a focus on permutations there are no fixed patterns. Permutations reorder the world in new ways, which are nevertheless meaningful, because the principle for rearrangement, shared causality/prediction, is meaningful. -Rob ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T581199cf280badd7-M0a3e371043aaf70f562e4eec Delivery options: https://agi.topicbox.com/groups/agi/subscription