
TL;DR
This paper introduces a universal, quantitative framework for defining intelligence across physical systems, emphasizing generalization, domain knowledge, and contextuality, challenging traditional syntax-semantics distinctions.
Contribution
It proposes a substrate-independent measure of intelligence based on description length and introduces a new perspective on semantics and contextuality.
Findings
Defines intelligence density as log of outputs over description length
Characterizes knowing as fixed description length with diverging outputs
Refutes Searle's premise by linking correctness and independence
Abstract
We propose an operational, quantitative definition of intelligence for arbitrary physical systems. The intelligence density of a system is the ratio of the logarithm of its independent outputs to its total description length. A system memorizes if its description length grows with its output count; it knows if its description length remains fixed while its output count diverges. The criterion for knowing is generalization. A system knows its domain if a single finite mechanism can produce correct outputs across an unbounded range of inputs, rather than storing each answer individually. The definition places intelligence on a substrate-independent continuum from logic gates to brains. We then argue that meaning over a domain is a selection and ordering of functions that produces correct outputs where correctness is specifiable. We also define a measure of contextuality of an output as…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
