I've been working on an information-theoretic system that demonstrates how metacognitive capabilities can emerge from elementary learning mechanisms. This may have implications for how we think about self-modeling in artificial systems.
The Problem
Current approaches to metacognition in AI typically rely on explicitly programmed hierarchical architectures…
Keep reading with a 7-day free trial
Subscribe to Axiomata to keep reading this post and get 7 days of free access to the full post archives.