On the Computation of Meaning, Language Models and Incomprehensible Horrors
Michael Timothy Bennett
TL;DR
By linking Grice’s theory of intention with a task-grounded AGI formalism, the paper offers a mechanistic account of meaning, symbol emergence, and communication. It shows how interpretants, feelings, and weak representations can yield machines that comprehend and intend meaning, addressing limitations of current LLMs. The approach uses a formal task framework and Peircean semiosis to model symbol grounding, intent, and cooperative communication. The work has implications for AI alignment, language evolution, and the development of more robust, human-like communicative agents.
Abstract
We integrate foundational theories of meaning with a mathematical formalism of artificial general intelligence (AGI) to offer a comprehensive mechanistic explanation of meaning, communication, and symbol emergence. This synthesis holds significance for both AGI and broader debates concerning the nature of language, as it unifies pragmatics, logical truth conditional semantics, Peircean semiotics, and a computable model of enactive cognition, addressing phenomena that have traditionally evaded mechanistic explanation. By examining the conditions under which a machine can generate meaningful utterances or comprehend human meaning, we establish that the current generation of language models do not possess the same understanding of meaning as humans nor intend any meaning that we might attribute to their responses. To address this, we propose simulating human feelings and optimising models to construct weak representations. Our findings shed light on the relationship between meaning and intelligence, and how we can build machines that comprehend and intend meaning.